From 270f609fe743d8f1230579b4c28aeb974dddde8e Mon Sep 17 00:00:00 2001 From: Gabriel Luiz Freitas Almeida Date: Tue, 1 Oct 2024 17:58:51 -0300 Subject: [PATCH] refactor: enhance tool creation logic and add FeatureFlags (#3662) * Add `required_inputs` field to `Output` model in `base.py` * Refactor ComponentTool to ComponentToolkit and enhance tool creation logic - Replaced `ComponentTool` with `ComponentToolkit` to better encapsulate component-related tools. - Introduced `build_description` and `_build_output_function` helper functions for dynamic tool creation. - Updated tool initialization to handle multiple outputs and required inputs using `StructuredTool`. - Improved schema creation for tool arguments based on component inputs. * Refactor `to_tool` method to `to_toolkit` to use `ComponentToolkit` instead of `ComponentTool` * Refactor `ComponentTool` to `ComponentToolkit` in unit tests - Updated import statements to reflect the new `ComponentToolkit` class. - Modified test logic to use `ComponentToolkit` for retrieving tools. - Adjusted assertions to match the new structure and output format. - Ensured compatibility with `Message` schema for output validation. * Refactor `test_component_to_tool` to validate `ComponentToolkit` and tool properties * Refactor `build_description` to include input types in the output format * Add method to set required inputs for outputs based on method analysis - Introduced `_set_output_required_inputs` method to determine and set required inputs for each output by analyzing the method's source code. - Added necessary imports (`ast` and `dedent`) to support the new functionality. * Update test to assert full tool description in test_component_to_tool.py * Add unit tests for verifying required inputs of various components - Added tests to ensure that required inputs for outputs are present in the inputs of `ChatInput`, `ChatOutput`, `SequentialTaskComponent`, `ToolCallingAgentComponent`, and `OpenAIModelComponent`. - Included helper functions to check if required inputs are in inputs and to assert that all outputs have different required inputs. * Add RequiredInputsVisitor to identify required inputs in AST nodes - Introduced RequiredInputsVisitor class to traverse AST nodes and collect required inputs. - The visitor checks for 'self' attributes matching the provided inputs and adds them to the required_inputs set. * Refactor required inputs extraction using `RequiredInputsVisitor` * Add feature flags configuration for toolkit output in settings * Add toolkit output handling based on feature flag in custom component utils * Add method to append 'component_as_tool' output in custom component * Add unit test for toolkit output feature flag in custom component * Add utility functions for lazy loading and instantiating input types in langflow - Introduced `get_InputTypesMap` for lazy loading of `InputTypesMap`. - Added `instantiate_input` function to create instances of input types dynamically. - Included type checking and error handling for invalid input types. * Refactor input instantiation logic and update imports - Removed `instantiate_input` function from `inputs.py` and moved it to `utils.py`. - Updated imports in `base.py` to reflect the new location of `instantiate_input`. - Added missing import for `Callable` in `base.py`. * Refactor import statement to use `instantiate_input` from `langflow.inputs.utils` in test_inputs.py * Add TOOL_OUTPUT_NAME constant to tools module * Add type checking and TOOL_OUTPUT_NAME filter in ComponentToolkit - Introduced `TYPE_CHECKING` for type hints to avoid circular imports. - Added `TOOL_OUTPUT_NAME` constant to filter specific outputs in `ComponentToolkit`. - Updated type annotations to use forward references. * Refactor component toolkit import to avoid circular dependency and use constant for tool output name * Refactor `ComponentToolkit` class to remove inheritance from `BaseToolkit` and add an initializer for `component` * Add unit test for ComponentToolkit in test_component_to_tool - Added `test_component_to_tool_has_no_component_as_tool` to verify that `ComponentToolkit` correctly initializes with a `ChatInput` component and returns the expected tools. * Refactor toolkit output handling to `custom_component` module * fix: mypy errors union-attr and arg-type * Add 'OTHER' field type to schema in langflow/io/schema.py * Add tool name formatting to ComponentToolkit to ensure valid characters * Refactor toolkit output handling and add type hint for `to_toolkit` method * Add `is_interface_component` attribute to vertex types and update import order * Add tests for ToolCallingAgentComponent and ChatOutput with API key handling - Updated `test_component_tool` to reflect new description format. - Added `test_component_tool_with_api_key` to test `ToolCallingAgentComponent` with `ChatOutput` and OpenAI API key. - Enabled `add_toolkit_output` feature flag for testing. * Refactor `_find_matching_output_method` to accept `input_name` parameter for more precise input-output matching * Replace ValueError with warning in build_description function * use chat_output component directly in set * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes * [autofix.ci] apply automated fixes (attempt 3/3) * Refactor: Reorder method calls in `__init__` for logical consistency Moved `set_class_code` method call to ensure output types and required inputs are set before class code initialization. * Update _format_tool_name to allow '.' in tool names * Refactor `_format_tool_name` to remove non-alphanumeric characters * Update test assertions for component tool name and output mapping * Handle case where 'required_inputs' is empty in 'component_tool.py' * Refactor import statements for better readability in `base.py` * [autofix.ci] apply automated fixes * Add noqa comment to suppress import warning and re-add Any import in base.py --------- Co-authored-by: italojohnny Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> --- .../langflow/base/tools/component_tool.py | 122 ++++++++++++----- .../base/langflow/base/tools/constants.py | 1 + .../custom/custom_component/component.py | 100 ++++++++++++-- .../base/langflow/custom/tree_visitor.py | 12 ++ .../base/langflow/graph/vertex/types.py | 1 + .../starter_projects/Agent Flow.json | 40 +++++- .../Basic Prompting (Hello, World).json | 22 +++- .../starter_projects/Blog Writer.json | 26 +++- .../starter_projects/Complex Agent.json | 117 +++++++++++++++-- .../starter_projects/Document QA.json | 26 +++- .../starter_projects/Hierarchical Agent.json | 59 ++++++++- .../starter_projects/Memory Chatbot.json | 24 +++- .../starter_projects/Sequential Agent.json | 33 +++-- .../Travel Planning Agents.json | 42 +++++- .../starter_projects/Vector Store RAG.json | 124 +++++++++++++++++- src/backend/base/langflow/inputs/utils.py | 32 +++++ src/backend/base/langflow/io/schema.py | 4 + .../services/settings/feature_flags.py | 11 ++ .../base/langflow/template/field/base.py | 20 ++- .../base/langflow/template/template/base.py | 3 +- src/backend/tests/conftest.py | 18 ++- .../unit/base/tools/test_component_tool.py | 62 --------- .../unit/base/tools/test_component_toolkit.py | 103 +++++++++++++++ .../component/test_component_to_tool.py | 32 ++++- .../custom/custom_component/test_component.py | 45 +++++++ .../tests/unit/graph/graph/test_base.py | 7 - src/backend/tests/unit/inputs/test_inputs.py | 2 +- src/backend/tests/unit/io/test_io_schema.py | 12 -- .../tests/unit/test_custom_component.py | 9 ++ 29 files changed, 903 insertions(+), 206 deletions(-) create mode 100644 src/backend/base/langflow/base/tools/constants.py create mode 100644 src/backend/base/langflow/custom/tree_visitor.py create mode 100644 src/backend/base/langflow/inputs/utils.py create mode 100644 src/backend/base/langflow/services/settings/feature_flags.py delete mode 100644 src/backend/tests/unit/base/tools/test_component_tool.py create mode 100644 src/backend/tests/unit/base/tools/test_component_toolkit.py diff --git a/src/backend/base/langflow/base/tools/component_tool.py b/src/backend/base/langflow/base/tools/component_tool.py index 368583581..e0fdbc369 100644 --- a/src/backend/base/langflow/base/tools/component_tool.py +++ b/src/backend/base/langflow/base/tools/component_tool.py @@ -1,42 +1,92 @@ -from typing import Any +from __future__ import annotations -from langchain_core.tools import BaseTool, ToolException +import re +import warnings +from collections.abc import Callable +from typing import TYPE_CHECKING -from langflow.custom.custom_component.component import Component +from langchain_core.tools import BaseTool +from langchain_core.tools.structured import StructuredTool + +from langflow.base.tools.constants import TOOL_OUTPUT_NAME +from langflow.io.schema import create_input_schema + +if TYPE_CHECKING: + from langflow.custom.custom_component.component import Component + from langflow.inputs.inputs import InputTypes + from langflow.io import Output -class ComponentTool(BaseTool): - name: str - description: str - component: "Component" - - def __init__(self, component: "Component") -> None: - """Initialize the tool.""" - from langflow.io.schema import create_input_schema - - name = component.name or component.__class__.__name__ - description = component.description or "" - args_schema = create_input_schema(component.inputs) - super().__init__(name=name, description=description, args_schema=args_schema, component=component) - # self.component = component - - @property - def args(self) -> dict: - schema = self.get_input_schema() - return schema.schema()["properties"] - - def _run( - self, - *args: Any, - **kwargs: Any, - ) -> dict: - """Use the tool.""" - try: - results, _ = self.component(**kwargs) - return results - except Exception as e: - msg = f"Error running {self.name}: {e}" - raise ToolException(msg) +def _get_input_type(input: InputTypes): + if input.input_types: + if len(input.input_types) == 1: + return input.input_types[0] + return " | ".join(input.input_types) + return input.field_type -ComponentTool.update_forward_refs() +def build_description(component: Component, output: Output): + if not output.required_inputs: + warnings.warn(f"Output {output.name} does not have required inputs defined") + + if output.required_inputs: + args = ", ".join( + sorted( + [ + f"{input_name}: {_get_input_type(component._inputs[input_name])}" + for input_name in output.required_inputs + ] + ) + ) + else: + args = "" + return f"{output.method}({args}) - {component.description}" + + +def _build_output_function(component: Component, output_method: Callable): + def output_function(*args, **kwargs): + component.set(*args, **kwargs) + return output_method() + + return output_function + + +def _format_tool_name(name: str): + # format to '^[a-zA-Z0-9_-]+$'." + # to do that we must remove all non-alphanumeric characters + + return re.sub(r"[^a-zA-Z0-9_-]", "-", name) + + +class ComponentToolkit: # type: ignore + def __init__(self, component: Component): + self.component = component + + def get_tools(self) -> list[BaseTool]: + tools = [] + for output in self.component.outputs: + if output.name == TOOL_OUTPUT_NAME: + continue + + if not output.method: + msg = f"Output {output.name} does not have a method defined" + raise ValueError(msg) + + output_method: Callable = getattr(self.component, output.method) + args_schema = None + if output.required_inputs: + inputs = [self.component._inputs[input_name] for input_name in output.required_inputs] + args_schema = create_input_schema(inputs) + else: + args_schema = create_input_schema(self.component.inputs) + name = f"{self.component.name}.{output.method}" + formatted_name = _format_tool_name(name) + tools.append( + StructuredTool( + name=formatted_name, + description=build_description(self.component, output), + func=_build_output_function(self.component, output_method), + args_schema=args_schema, + ) + ) + return tools diff --git a/src/backend/base/langflow/base/tools/constants.py b/src/backend/base/langflow/base/tools/constants.py new file mode 100644 index 000000000..ed308a7e9 --- /dev/null +++ b/src/backend/base/langflow/base/tools/constants.py @@ -0,0 +1 @@ +TOOL_OUTPUT_NAME = "component_as_tool" diff --git a/src/backend/base/langflow/custom/custom_component/component.py b/src/backend/base/langflow/custom/custom_component/component.py index ac6bf8154..4c03a1f08 100644 --- a/src/backend/base/langflow/custom/custom_component/component.py +++ b/src/backend/base/langflow/custom/custom_component/component.py @@ -1,8 +1,10 @@ from __future__ import annotations +import ast import inspect from collections.abc import Callable from copy import deepcopy +from textwrap import dedent from typing import TYPE_CHECKING, Any, ClassVar, get_type_hints from uuid import UUID @@ -10,13 +12,17 @@ import nanoid # type: ignore import yaml from pydantic import BaseModel +from langflow.base.tools.constants import TOOL_OUTPUT_NAME +from langflow.custom.tree_visitor import RequiredInputsVisitor from langflow.events.event_manager import EventManager +from langflow.field_typing import Tool from langflow.graph.state.model import create_state_model from langflow.helpers.custom import format_type from langflow.schema.artifact import get_artifact_type, post_process_raw from langflow.schema.data import Data from langflow.schema.log import LoggableType from langflow.schema.message import Message +from langflow.services.settings.feature_flags import FEATURE_FLAGS from langflow.services.tracing.schema import Log from langflow.template.field.base import UNDEFINED, Input, Output from langflow.template.frontend_node.custom_components import ComponentFrontendNode @@ -30,6 +36,19 @@ if TYPE_CHECKING: from langflow.graph.vertex.base import Vertex from langflow.inputs.inputs import InputTypes + +_ComponentToolkit = None + + +def _get_component_toolkit(): + global _ComponentToolkit + if _ComponentToolkit is None: + from langflow.base.tools.component_tool import ComponentToolkit + + _ComponentToolkit = ComponentToolkit + return _ComponentToolkit + + BACKWARDS_COMPATIBLE_ATTRIBUTES = ["user_id", "vertex", "tracing_service"] CONFIG_ATTRIBUTES = ["_display_name", "_description", "_icon", "_name", "_metadata"] @@ -72,6 +91,8 @@ class Component(CustomComponent): self.__inputs = inputs self.__config = config self._reset_all_output_values() + if FEATURE_FLAGS.add_toolkit_output and hasattr(self, "_append_tool_output"): + self._append_tool_output() super().__init__(**config) if hasattr(self, "_trace_type"): self.trace_type = self._trace_type @@ -84,6 +105,7 @@ class Component(CustomComponent): # Set output types self._set_output_types() self.set_class_code() + self._set_output_required_inputs() def set_event_manager(self, event_manager: EventManager | None = None): self._event_manager = event_manager @@ -305,6 +327,24 @@ class Component(CustomComponent): output.add_types(return_types) output.set_selected() + def _set_output_required_inputs(self): + for output in self.outputs: + if not output.method: + continue + method = getattr(self, output.method, None) + if not method or not callable(method): + continue + try: + source_code = inspect.getsource(method) + ast_tree = ast.parse(dedent(source_code)) + except Exception: + source_code = self._code + ast_tree = ast.parse(dedent(source_code)) + + visitor = RequiredInputsVisitor(self._inputs) + visitor.visit(ast_tree) + output.required_inputs = sorted(visitor.required_inputs) + def get_output_by_method(self, method: Callable): # method is a callable and output.method is a string # we need to find the output that has the same method @@ -335,24 +375,56 @@ class Component(CustomComponent): text += f"{output.name}[{','.join(output.types)}]->{input_.name}[{','.join(input_.input_types or [])}]\n" return text - def _find_matching_output_method(self, value: Component): - # get all outputs of the value component + def _find_matching_output_method(self, input_name: str, value: Component): + """ + Find the output method from the given component (`value`) that matches the specified input (`input_name`) + in the current component. + + This method searches through all outputs of the provided component to find outputs whose types match + the input types of the specified input in the current component. If exactly one matching output is found, + it returns the corresponding method. If multiple matching outputs are found, it raises an error indicating + ambiguity. If no matching outputs are found, it raises an error indicating that no suitable output was found. + + Args: + input_name (str): The name of the input in the current component to match. + value (Component): The component whose outputs are to be considered. + + Returns: + Callable: The method corresponding to the matching output. + + Raises: + ValueError: If multiple matching outputs are found, if no matching outputs are found, + or if the output method is invalid. + """ + # Retrieve all outputs from the given component outputs = value._outputs_map.values() - # check if the any of the types in the output.types matches ONLY one input in the current component + # Prepare to collect matching output-input pairs matching_pairs = [] + # Get the input object from the current component + input_ = self._inputs[input_name] + # Iterate over outputs to find matches based on types for output in outputs: - for input_ in self.inputs: - for output_type in output.types: - if input_.input_types and output_type in input_.input_types: - matching_pairs.append((output, input_)) + for output_type in output.types: + # Check if the output type matches the input's accepted types + if input_.input_types and output_type in input_.input_types: + matching_pairs.append((output, input_)) + # If multiple matches are found, raise an error indicating ambiguity if len(matching_pairs) > 1: matching_pairs_str = self._build_error_string_from_matching_pairs(matching_pairs) msg = ( f"There are multiple outputs from {value.__class__.__name__} " f"that can connect to inputs in {self.__class__.__name__}: {matching_pairs_str}" ) + # If no matches are found, raise an error indicating no suitable output + if not matching_pairs: + msg = ( + f"No matching output from {value.__class__.__name__} found for input '{input_name}' " + f"in {self.__class__.__name__}." + ) raise ValueError(msg) + # Get the matching output and input pair output, input_ = matching_pairs[0] + # Ensure that the output method is a valid method name (string) if not isinstance(output.method, str): msg = f"Method {output.method} is not a valid output of {value.__class__.__name__}" raise ValueError(msg) @@ -365,7 +437,7 @@ class Component(CustomComponent): # We need to find the Output that can connect to an input of the current component # if there's more than one output that matches, we need to raise an error # because we don't know which one to connect to - value = self._find_matching_output_method(value) + value = self._find_matching_output_method(key, value) if callable(value) and self._inherits_from_component(value): try: self._method_is_valid_output(value) @@ -744,11 +816,9 @@ class Component(CustomComponent): def _get_fallback_input(self, **kwargs): return Input(**kwargs) - def to_tool(self): - # TODO: This is a temporary solution to avoid circular imports - from langflow.base.tools.component_tool import ComponentTool - - return ComponentTool(component=self) + def to_toolkit(self) -> list[Tool]: + ComponentToolkit = _get_component_toolkit() + return ComponentToolkit(component=self).get_tools() def get_project_name(self): if hasattr(self, "_tracing_service") and self._tracing_service: @@ -773,3 +843,7 @@ class Component(CustomComponent): data["output"] = self._current_output data["component_id"] = self._id self._event_manager.on_log(data=data) + + def _append_tool_output(self): + if next((output for output in self.outputs if output.name == TOOL_OUTPUT_NAME), None) is None: + self.outputs.append(Output(name=TOOL_OUTPUT_NAME, display_name="Tool", method="to_toolkit", types=["Tool"])) diff --git a/src/backend/base/langflow/custom/tree_visitor.py b/src/backend/base/langflow/custom/tree_visitor.py new file mode 100644 index 000000000..48ef5f852 --- /dev/null +++ b/src/backend/base/langflow/custom/tree_visitor.py @@ -0,0 +1,12 @@ +import ast + + +class RequiredInputsVisitor(ast.NodeVisitor): + def __init__(self, inputs): + self.inputs = inputs + self.required_inputs = set() + + def visit_Attribute(self, node): + if isinstance(node.value, ast.Name) and node.value.id == "self" and node.attr in self.inputs: + self.required_inputs.add(node.attr) + self.generic_visit(node) diff --git a/src/backend/base/langflow/graph/vertex/types.py b/src/backend/base/langflow/graph/vertex/types.py index 24a656064..eb0377499 100644 --- a/src/backend/base/langflow/graph/vertex/types.py +++ b/src/backend/base/langflow/graph/vertex/types.py @@ -208,6 +208,7 @@ class InterfaceVertex(ComponentVertex): super().__init__(data, graph=graph) self._added_message = None self.steps = [self._build, self._run] + self.is_interface_component = True def build_stream_url(self): return f"/api/v1/build/{self.graph.flow_id}/{self.id}/stream" diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Agent Flow.json b/src/backend/base/langflow/initial_setup/starter_projects/Agent Flow.json index a2ddf4c34..08be22908 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Agent Flow.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Agent Flow.json @@ -598,6 +598,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -609,6 +614,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -654,7 +670,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "_input_type": "MessageInput", @@ -1197,6 +1213,9 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "expression" + ], "selected": "Data", "types": [ "Data" @@ -1208,6 +1227,9 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "expression" + ], "selected": "Tool", "types": [ "Tool" @@ -1234,7 +1256,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import ast\nimport operator\n\nfrom langchain.tools import StructuredTool\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import MessageTextInput\nfrom langflow.schema import Data\n\n\nclass CalculatorToolComponent(LCToolComponent):\n display_name = \"Calculator\"\n description = \"Perform basic arithmetic operations on a given expression.\"\n icon = \"calculator\"\n name = \"CalculatorTool\"\n\n inputs = [\n MessageTextInput(\n name=\"expression\",\n display_name=\"Expression\",\n info=\"The arithmetic expression to evaluate (e.g., '4*4*(33/22)+12-20').\",\n ),\n ]\n\n class CalculatorToolSchema(BaseModel):\n expression: str = Field(..., description=\"The arithmetic expression to evaluate.\")\n\n def run_model(self) -> list[Data]:\n return self._evaluate_expression(self.expression)\n\n def build_tool(self) -> Tool:\n return StructuredTool.from_function(\n name=\"calculator\",\n description=\"Evaluate basic arithmetic expressions. Input should be a string containing the expression.\",\n func=self._evaluate_expression,\n args_schema=self.CalculatorToolSchema,\n )\n\n def _evaluate_expression(self, expression: str) -> list[Data]:\n try:\n # Define the allowed operators\n operators = {\n ast.Add: operator.add,\n ast.Sub: operator.sub,\n ast.Mult: operator.mul,\n ast.Div: operator.truediv,\n ast.Pow: operator.pow,\n }\n\n def eval_expr(node):\n if isinstance(node, ast.Num):\n return node.n\n elif isinstance(node, ast.BinOp):\n return operators[type(node.op)](eval_expr(node.left), eval_expr(node.right))\n elif isinstance(node, ast.UnaryOp):\n return operators[type(node.op)](eval_expr(node.operand))\n else:\n raise TypeError(node)\n\n # Parse the expression and evaluate it\n tree = ast.parse(expression, mode=\"eval\")\n result = eval_expr(tree.body)\n\n # Format the result to a reasonable number of decimal places\n formatted_result = f\"{result:.6f}\".rstrip(\"0\").rstrip(\".\")\n\n self.status = formatted_result\n return [Data(data={\"result\": formatted_result})]\n\n except (SyntaxError, TypeError, KeyError) as e:\n error_message = f\"Invalid expression: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except ZeroDivisionError:\n error_message = \"Error: Division by zero\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except Exception as e:\n error_message = f\"Error: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n" + "value": "import ast\nimport operator\n\nfrom langchain.tools import StructuredTool\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import MessageTextInput\nfrom langflow.schema import Data\n\n\nclass CalculatorToolComponent(LCToolComponent):\n display_name = \"Calculator\"\n description = \"Perform basic arithmetic operations on a given expression.\"\n icon = \"calculator\"\n name = \"CalculatorTool\"\n\n inputs = [\n MessageTextInput(\n name=\"expression\",\n display_name=\"Expression\",\n info=\"The arithmetic expression to evaluate (e.g., '4*4*(33/22)+12-20').\",\n ),\n ]\n\n class CalculatorToolSchema(BaseModel):\n expression: str = Field(..., description=\"The arithmetic expression to evaluate.\")\n\n def run_model(self) -> list[Data]:\n return self._evaluate_expression(self.expression)\n\n def build_tool(self) -> Tool:\n return StructuredTool.from_function(\n name=\"calculator\",\n description=\"Evaluate basic arithmetic expressions. Input should be a string containing the expression.\",\n func=self._evaluate_expression,\n args_schema=self.CalculatorToolSchema,\n )\n\n def _evaluate_expression(self, expression: str) -> list[Data]:\n try:\n # Define the allowed operators\n operators = {\n ast.Add: operator.add,\n ast.Sub: operator.sub,\n ast.Mult: operator.mul,\n ast.Div: operator.truediv,\n ast.Pow: operator.pow,\n }\n\n def eval_expr(node):\n if isinstance(node, ast.Num):\n return node.n\n if isinstance(node, ast.BinOp):\n return operators[type(node.op)](eval_expr(node.left), eval_expr(node.right))\n if isinstance(node, ast.UnaryOp):\n return operators[type(node.op)](eval_expr(node.operand))\n raise TypeError(node)\n\n # Parse the expression and evaluate it\n tree = ast.parse(expression, mode=\"eval\")\n result = eval_expr(tree.body)\n\n # Format the result to a reasonable number of decimal places\n formatted_result = f\"{result:.6f}\".rstrip(\"0\").rstrip(\".\")\n\n self.status = formatted_result\n return [Data(data={\"result\": formatted_result})]\n\n except (SyntaxError, TypeError, KeyError) as e:\n error_message = f\"Invalid expression: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except ZeroDivisionError:\n error_message = \"Error: Division by zero\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except Exception as e:\n error_message = f\"Error: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n" }, "expression": { "_input_type": "MessageTextInput", @@ -1308,6 +1330,12 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "code", + "description", + "global_imports", + "name" + ], "selected": "Data", "types": [ "Data" @@ -1319,6 +1347,12 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "code", + "description", + "global_imports", + "name" + ], "selected": "Tool", "types": [ "Tool" @@ -1345,7 +1379,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import importlib\n\nfrom langchain.tools import StructuredTool\nfrom langchain_experimental.utilities import PythonREPL\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import StrInput\nfrom langflow.schema import Data\n\n\nclass PythonREPLToolComponent(LCToolComponent):\n display_name = \"Python REPL Tool\"\n description = \"A tool for running Python code in a REPL environment.\"\n name = \"PythonREPLTool\"\n\n inputs = [\n StrInput(\n name=\"name\",\n display_name=\"Tool Name\",\n info=\"The name of the tool.\",\n value=\"python_repl\",\n ),\n StrInput(\n name=\"description\",\n display_name=\"Tool Description\",\n info=\"A description of the tool.\",\n value=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n ),\n StrInput(\n name=\"global_imports\",\n display_name=\"Global Imports\",\n info=\"A comma-separated list of modules to import globally, e.g. 'math,numpy'.\",\n value=\"math\",\n ),\n StrInput(\n name=\"code\",\n display_name=\"Python Code\",\n info=\"The Python code to execute.\",\n value=\"print('Hello, World!')\",\n ),\n ]\n\n class PythonREPLSchema(BaseModel):\n code: str = Field(..., description=\"The Python code to execute.\")\n\n def get_globals(self, global_imports: str | list[str]) -> dict:\n global_dict = {}\n if isinstance(global_imports, str):\n modules = [module.strip() for module in global_imports.split(\",\")]\n elif isinstance(global_imports, list):\n modules = global_imports\n else:\n raise ValueError(\"global_imports must be either a string or a list\")\n\n for module in modules:\n try:\n imported_module = importlib.import_module(module)\n global_dict[imported_module.__name__] = imported_module\n except ImportError:\n raise ImportError(f\"Could not import module {module}\")\n return global_dict\n\n def build_tool(self) -> Tool:\n _globals = self.get_globals(self.global_imports)\n python_repl = PythonREPL(_globals=_globals)\n\n def run_python_code(code: str) -> str:\n try:\n return python_repl.run(code)\n except Exception as e:\n return f\"Error: {str(e)}\"\n\n tool = StructuredTool.from_function(\n name=self.name,\n description=self.description,\n func=run_python_code,\n args_schema=self.PythonREPLSchema,\n )\n\n self.status = f\"Python REPL Tool created with global imports: {self.global_imports}\"\n return tool\n\n def run_model(self) -> list[Data]:\n tool = self.build_tool()\n result = tool.run(self.code)\n return [Data(data={\"result\": result})]\n" + "value": "import importlib\n\nfrom langchain.tools import StructuredTool\nfrom langchain_experimental.utilities import PythonREPL\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import StrInput\nfrom langflow.schema import Data\n\n\nclass PythonREPLToolComponent(LCToolComponent):\n display_name = \"Python REPL Tool\"\n description = \"A tool for running Python code in a REPL environment.\"\n name = \"PythonREPLTool\"\n\n inputs = [\n StrInput(\n name=\"name\",\n display_name=\"Tool Name\",\n info=\"The name of the tool.\",\n value=\"python_repl\",\n ),\n StrInput(\n name=\"description\",\n display_name=\"Tool Description\",\n info=\"A description of the tool.\",\n value=\"A Python shell. Use this to execute python commands. \"\n \"Input should be a valid python command. \"\n \"If you want to see the output of a value, you should print it out with `print(...)`.\",\n ),\n StrInput(\n name=\"global_imports\",\n display_name=\"Global Imports\",\n info=\"A comma-separated list of modules to import globally, e.g. 'math,numpy'.\",\n value=\"math\",\n ),\n StrInput(\n name=\"code\",\n display_name=\"Python Code\",\n info=\"The Python code to execute.\",\n value=\"print('Hello, World!')\",\n ),\n ]\n\n class PythonREPLSchema(BaseModel):\n code: str = Field(..., description=\"The Python code to execute.\")\n\n def get_globals(self, global_imports: str | list[str]) -> dict:\n global_dict = {}\n if isinstance(global_imports, str):\n modules = [module.strip() for module in global_imports.split(\",\")]\n elif isinstance(global_imports, list):\n modules = global_imports\n else:\n msg = \"global_imports must be either a string or a list\"\n raise ValueError(msg)\n\n for module in modules:\n try:\n imported_module = importlib.import_module(module)\n global_dict[imported_module.__name__] = imported_module\n except ImportError:\n msg = f\"Could not import module {module}\"\n raise ImportError(msg)\n return global_dict\n\n def build_tool(self) -> Tool:\n _globals = self.get_globals(self.global_imports)\n python_repl = PythonREPL(_globals=_globals)\n\n def run_python_code(code: str) -> str:\n try:\n return python_repl.run(code)\n except Exception as e:\n return f\"Error: {str(e)}\"\n\n tool = StructuredTool.from_function(\n name=self.name,\n description=self.description,\n func=run_python_code,\n args_schema=self.PythonREPLSchema,\n )\n\n self.status = f\"Python REPL Tool created with global imports: {self.global_imports}\"\n return tool\n\n def run_model(self) -> list[Data]:\n tool = self.build_tool()\n result = tool.run(self.code)\n return [Data(data={\"result\": result})]\n" }, "description": { "_input_type": "StrInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting (Hello, World).json b/src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting (Hello, World).json index 2a3f0952c..193d1760b 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting (Hello, World).json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting (Hello, World).json @@ -315,7 +315,7 @@ "user_input" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -358,7 +358,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "template": { "advanced": false, @@ -655,6 +655,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -666,6 +671,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -711,7 +727,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json b/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json index 1d1b74c5f..02d456856 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json @@ -201,7 +201,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output format\",\n info=\"Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"fetch_content\"),\n Output(display_name=\"Text\", name=\"text\", method=\"fetch_content_text\"),\n ]\n\n def ensure_url(self, string: str) -> str:\n \"\"\"\n Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n raise ValueError(f\"Invalid URL: {string}\")\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n" + "value": "import re\n\nfrom langchain_community.document_loaders import AsyncHtmlLoader, WebBaseLoader\n\nfrom langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DropdownInput, MessageTextInput, Output\nfrom langflow.schema import Data\nfrom langflow.schema.message import Message\n\n\nclass URLComponent(Component):\n display_name = \"URL\"\n description = \"Fetch content from one or more URLs.\"\n icon = \"layout-template\"\n name = \"URL\"\n\n inputs = [\n MessageTextInput(\n name=\"urls\",\n display_name=\"URLs\",\n info=\"Enter one or more URLs, by clicking the '+' button.\",\n is_list=True,\n ),\n DropdownInput(\n name=\"format\",\n display_name=\"Output format\",\n info=\"Output format. Use 'Text' to extract the text from the HTML or 'Raw HTML' for the raw HTML content.\",\n options=[\"Text\", \"Raw HTML\"],\n value=\"Text\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"fetch_content\"),\n Output(display_name=\"Text\", name=\"text\", method=\"fetch_content_text\"),\n ]\n\n def ensure_url(self, string: str) -> str:\n \"\"\"\n Ensures the given string is a URL by adding 'http://' if it doesn't start with 'http://' or 'https://'.\n Raises an error if the string is not a valid URL.\n\n Parameters:\n string (str): The string to be checked and possibly modified.\n\n Returns:\n str: The modified string that is ensured to be a URL.\n\n Raises:\n ValueError: If the string is not a valid URL.\n \"\"\"\n if not string.startswith((\"http://\", \"https://\")):\n string = \"http://\" + string\n\n # Basic URL validation regex\n url_regex = re.compile(\n r\"^(https?:\\/\\/)?\" # optional protocol\n r\"(www\\.)?\" # optional www\n r\"([a-zA-Z0-9.-]+)\" # domain\n r\"(\\.[a-zA-Z]{2,})?\" # top-level domain\n r\"(:\\d+)?\" # optional port\n r\"(\\/[^\\s]*)?$\", # optional path\n re.IGNORECASE,\n )\n\n if not url_regex.match(string):\n msg = f\"Invalid URL: {string}\"\n raise ValueError(msg)\n\n return string\n\n def fetch_content(self) -> list[Data]:\n urls = [self.ensure_url(url.strip()) for url in self.urls if url.strip()]\n if self.format == \"Raw HTML\":\n loader = AsyncHtmlLoader(web_path=urls, encoding=\"utf-8\")\n else:\n loader = WebBaseLoader(web_paths=urls, encoding=\"utf-8\")\n docs = loader.load()\n data = [Data(text=doc.page_content, **doc.metadata) for doc in docs]\n self.status = data\n return data\n\n def fetch_content_text(self) -> Message:\n data = self.fetch_content()\n\n result_string = data_to_text(\"{text}\", data)\n self.status = result_string\n return Message(text=result_string)\n" }, "format": { "_input_type": "DropdownInput", @@ -322,7 +322,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" + "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. \"\n \"It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" }, "data": { "advanced": false, @@ -416,7 +416,7 @@ "instructions" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -459,7 +459,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "instructions": { "advanced": false, @@ -877,6 +877,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -888,6 +893,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -933,7 +949,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Complex Agent.json b/src/backend/base/langflow/initial_setup/starter_projects/Complex Agent.json index 754721375..1f5c8069c 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Complex Agent.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Complex Agent.json @@ -637,6 +637,7 @@ "display_name": "Output", "method": "build_output", "name": "output", + "required_inputs": [], "selected": "Message", "types": [ "Message" @@ -681,7 +682,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from crewai import Crew, Process # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\n\n\nclass HierarchicalCrewComponent(BaseCrewComponent):\n display_name: str = \"Hierarchical Crew\"\n description: str = (\n \"Represents a group of agents, defining how they should collaborate and the tasks they should perform.\"\n )\n documentation: str = \"https://docs.crewai.com/how-to/Hierarchical/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"agents\", display_name=\"Agents\", input_types=[\"Agent\"], is_list=True),\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"HierarchicalTask\"], is_list=True),\n HandleInput(name=\"manager_llm\", display_name=\"Manager LLM\", input_types=[\"LanguageModel\"], required=False),\n HandleInput(name=\"manager_agent\", display_name=\"Manager Agent\", input_types=[\"Agent\"], required=False),\n ]\n\n def build_crew(self) -> Crew:\n tasks, agents = self.get_tasks_and_agents()\n crew = Crew(\n agents=agents,\n tasks=tasks,\n process=Process.hierarchical,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n manager_agent=self.manager_agent,\n manager_llm=self.manager_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n return crew\n" + "value": "from crewai import Crew, Process # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\n\n\nclass HierarchicalCrewComponent(BaseCrewComponent):\n display_name: str = \"Hierarchical Crew\"\n description: str = (\n \"Represents a group of agents, defining how they should collaborate and the tasks they should perform.\"\n )\n documentation: str = \"https://docs.crewai.com/how-to/Hierarchical/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"agents\", display_name=\"Agents\", input_types=[\"Agent\"], is_list=True),\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"HierarchicalTask\"], is_list=True),\n HandleInput(name=\"manager_llm\", display_name=\"Manager LLM\", input_types=[\"LanguageModel\"], required=False),\n HandleInput(name=\"manager_agent\", display_name=\"Manager Agent\", input_types=[\"Agent\"], required=False),\n ]\n\n def build_crew(self) -> Crew:\n tasks, agents = self.get_tasks_and_agents()\n return Crew(\n agents=agents,\n tasks=tasks,\n process=Process.hierarchical,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n manager_agent=self.manager_agent,\n manager_llm=self.manager_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n" }, "function_calling_llm": { "advanced": true, @@ -883,6 +884,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -894,6 +900,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -939,7 +956,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -2034,6 +2051,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -2045,6 +2067,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -2090,7 +2123,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -2326,7 +2359,7 @@ "query" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -2375,7 +2408,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "query": { "advanced": false, @@ -2789,6 +2822,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -2800,6 +2838,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -2845,7 +2894,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -3223,6 +3272,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -3234,6 +3288,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -3279,7 +3344,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -3681,6 +3746,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -3692,6 +3762,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -3737,7 +3818,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -3975,7 +4056,7 @@ "goal" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -4024,7 +4105,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "goal": { "advanced": false, @@ -4164,6 +4245,14 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Data", "types": [ "Data" @@ -4175,6 +4264,14 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Tool", "types": [ "Tool" diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Document QA.json b/src/backend/base/langflow/initial_setup/starter_projects/Document QA.json index 58315f0c9..8c9a13ad8 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Document QA.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Document QA.json @@ -152,7 +152,7 @@ "Question" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -243,7 +243,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "template": { "advanced": false, @@ -733,6 +733,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -744,6 +749,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -789,7 +805,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -1066,7 +1082,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" + "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. \"\n \"It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" }, "data": { "advanced": false, @@ -1199,7 +1215,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from pathlib import Path\n\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parse_text_file_to_data\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, FileInput, Output\nfrom langflow.schema import Data\n\n\nclass FileComponent(Component):\n display_name = \"File\"\n description = \"A generic file loader.\"\n icon = \"file-text\"\n name = \"File\"\n\n inputs = [\n FileInput(\n name=\"path\",\n display_name=\"Path\",\n file_types=TEXT_FILE_TYPES,\n info=f\"Supported file types: {', '.join(TEXT_FILE_TYPES)}\",\n ),\n BoolInput(\n name=\"silent_errors\",\n display_name=\"Silent Errors\",\n advanced=True,\n info=\"If true, errors will not raise an exception.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"load_file\"),\n ]\n\n def load_file(self) -> Data:\n if not self.path:\n raise ValueError(\"Please, upload a file to use this component.\")\n resolved_path = self.resolve_path(self.path)\n silent_errors = self.silent_errors\n\n extension = Path(resolved_path).suffix[1:].lower()\n\n if extension == \"doc\":\n raise ValueError(\"doc files are not supported. Please save as .docx\")\n if extension not in TEXT_FILE_TYPES:\n raise ValueError(f\"Unsupported file type: {extension}\")\n\n data = parse_text_file_to_data(resolved_path, silent_errors)\n self.status = data if data else \"No data\"\n return data or Data()\n" + "value": "from pathlib import Path\n\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parse_text_file_to_data\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, FileInput, Output\nfrom langflow.schema import Data\n\n\nclass FileComponent(Component):\n display_name = \"File\"\n description = \"A generic file loader.\"\n icon = \"file-text\"\n name = \"File\"\n\n inputs = [\n FileInput(\n name=\"path\",\n display_name=\"Path\",\n file_types=TEXT_FILE_TYPES,\n info=f\"Supported file types: {', '.join(TEXT_FILE_TYPES)}\",\n ),\n BoolInput(\n name=\"silent_errors\",\n display_name=\"Silent Errors\",\n advanced=True,\n info=\"If true, errors will not raise an exception.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"load_file\"),\n ]\n\n def load_file(self) -> Data:\n if not self.path:\n msg = \"Please, upload a file to use this component.\"\n raise ValueError(msg)\n resolved_path = self.resolve_path(self.path)\n silent_errors = self.silent_errors\n\n extension = Path(resolved_path).suffix[1:].lower()\n\n if extension == \"doc\":\n msg = \"doc files are not supported. Please save as .docx\"\n raise ValueError(msg)\n if extension not in TEXT_FILE_TYPES:\n msg = f\"Unsupported file type: {extension}\"\n raise ValueError(msg)\n\n data = parse_text_file_to_data(resolved_path, silent_errors)\n self.status = data if data else \"No data\"\n return data or Data()\n" }, "path": { "advanced": false, diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Hierarchical Agent.json b/src/backend/base/langflow/initial_setup/starter_projects/Hierarchical Agent.json index 488d6feb1..09788cfb3 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Hierarchical Agent.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Hierarchical Agent.json @@ -334,6 +334,7 @@ "display_name": "Output", "method": "build_output", "name": "output", + "required_inputs": [], "selected": "Message", "types": [ "Message" @@ -378,7 +379,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from crewai import Crew, Process # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\n\n\nclass HierarchicalCrewComponent(BaseCrewComponent):\n display_name: str = \"Hierarchical Crew\"\n description: str = (\n \"Represents a group of agents, defining how they should collaborate and the tasks they should perform.\"\n )\n documentation: str = \"https://docs.crewai.com/how-to/Hierarchical/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"agents\", display_name=\"Agents\", input_types=[\"Agent\"], is_list=True),\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"HierarchicalTask\"], is_list=True),\n HandleInput(name=\"manager_llm\", display_name=\"Manager LLM\", input_types=[\"LanguageModel\"], required=False),\n HandleInput(name=\"manager_agent\", display_name=\"Manager Agent\", input_types=[\"Agent\"], required=False),\n ]\n\n def build_crew(self) -> Crew:\n tasks, agents = self.get_tasks_and_agents()\n crew = Crew(\n agents=agents,\n tasks=tasks,\n process=Process.hierarchical,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n manager_agent=self.manager_agent,\n manager_llm=self.manager_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n return crew\n" + "value": "from crewai import Crew, Process # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\n\n\nclass HierarchicalCrewComponent(BaseCrewComponent):\n display_name: str = \"Hierarchical Crew\"\n description: str = (\n \"Represents a group of agents, defining how they should collaborate and the tasks they should perform.\"\n )\n documentation: str = \"https://docs.crewai.com/how-to/Hierarchical/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"agents\", display_name=\"Agents\", input_types=[\"Agent\"], is_list=True),\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"HierarchicalTask\"], is_list=True),\n HandleInput(name=\"manager_llm\", display_name=\"Manager LLM\", input_types=[\"LanguageModel\"], required=False),\n HandleInput(name=\"manager_agent\", display_name=\"Manager Agent\", input_types=[\"Agent\"], required=False),\n ]\n\n def build_crew(self) -> Crew:\n tasks, agents = self.get_tasks_and_agents()\n return Crew(\n agents=agents,\n tasks=tasks,\n process=Process.hierarchical,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n manager_agent=self.manager_agent,\n manager_llm=self.manager_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n" }, "function_calling_llm": { "advanced": true, @@ -583,6 +584,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -594,6 +600,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -638,7 +655,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -1754,6 +1771,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -1765,6 +1787,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -1809,7 +1842,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -2050,7 +2083,7 @@ "query" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -2099,7 +2132,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "query": { "advanced": false, @@ -2662,6 +2695,14 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Data", "types": [ "Data" @@ -2673,6 +2714,14 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Tool", "types": [ "Tool" diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json b/src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json index d113cffe5..e713ee952 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json @@ -126,7 +126,7 @@ "user_message" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -169,7 +169,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "context": { "advanced": false, @@ -512,6 +512,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -523,6 +528,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -568,7 +584,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -1063,7 +1079,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain.memory import ConversationBufferMemory\n\nfrom langflow.custom import Component\nfrom langflow.field_typing import BaseChatMemory\nfrom langflow.helpers.data import data_to_text\nfrom langflow.inputs import HandleInput\nfrom langflow.io import DropdownInput, IntInput, MessageTextInput, MultilineInput, Output\nfrom langflow.memory import LCBuiltinChatMemory, get_messages\nfrom langflow.schema import Data\nfrom langflow.schema.message import Message\nfrom langflow.utils.constants import MESSAGE_SENDER_AI, MESSAGE_SENDER_USER\n\n\nclass MemoryComponent(Component):\n display_name = \"Chat Memory\"\n description = \"Retrieves stored chat messages from Langflow tables or an external memory.\"\n icon = \"message-square-more\"\n name = \"Memory\"\n\n inputs = [\n HandleInput(\n name=\"memory\",\n display_name=\"External Memory\",\n input_types=[\"BaseChatMessageHistory\"],\n info=\"Retrieve messages from an external memory. If empty, it will use the Langflow tables.\",\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER, \"Machine and User\"],\n value=\"Machine and User\",\n info=\"Filter by sender type.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Filter by sender name.\",\n advanced=True,\n ),\n IntInput(\n name=\"n_messages\",\n display_name=\"Number of Messages\",\n value=100,\n info=\"Number of messages to retrieve.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"order\",\n display_name=\"Order\",\n options=[\"Ascending\", \"Descending\"],\n value=\"Ascending\",\n info=\"Order of the messages.\",\n advanced=True,\n ),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. It can contain the keys {text}, {sender} or any other key in the message data.\",\n value=\"{sender_name}: {text}\",\n advanced=True,\n ),\n ]\n\n outputs = [\n Output(display_name=\"Messages (Data)\", name=\"messages\", method=\"retrieve_messages\"),\n Output(display_name=\"Messages (Text)\", name=\"messages_text\", method=\"retrieve_messages_as_text\"),\n Output(display_name=\"Memory\", name=\"lc_memory\", method=\"build_lc_memory\"),\n ]\n\n def retrieve_messages(self) -> Data:\n sender = self.sender\n sender_name = self.sender_name\n session_id = self.session_id\n n_messages = self.n_messages\n order = \"DESC\" if self.order == \"Descending\" else \"ASC\"\n\n if sender == \"Machine and User\":\n sender = None\n\n if self.memory:\n # override session_id\n self.memory.session_id = session_id\n\n stored = self.memory.messages\n # langchain memories are supposed to return messages in ascending order\n if order == \"DESC\":\n stored = stored[::-1]\n if n_messages:\n stored = stored[:n_messages]\n stored = [Message.from_lc_message(m) for m in stored]\n if sender:\n expected_type = MESSAGE_SENDER_AI if sender == MESSAGE_SENDER_AI else MESSAGE_SENDER_USER\n stored = [m for m in stored if m.type == expected_type]\n else:\n stored = get_messages(\n sender=sender,\n sender_name=sender_name,\n session_id=session_id,\n limit=n_messages,\n order=order,\n )\n self.status = stored\n return stored\n\n def retrieve_messages_as_text(self) -> Message:\n stored_text = data_to_text(self.template, self.retrieve_messages())\n self.status = stored_text\n return Message(text=stored_text)\n\n def build_lc_memory(self) -> BaseChatMemory:\n if self.memory:\n chat_memory = self.memory\n else:\n chat_memory = LCBuiltinChatMemory(flow_id=self.flow_id, session_id=self.session_id)\n return ConversationBufferMemory(chat_memory=chat_memory)\n" + "value": "from langchain.memory import ConversationBufferMemory\n\nfrom langflow.custom import Component\nfrom langflow.field_typing import BaseChatMemory\nfrom langflow.helpers.data import data_to_text\nfrom langflow.inputs import HandleInput\nfrom langflow.io import DropdownInput, IntInput, MessageTextInput, MultilineInput, Output\nfrom langflow.memory import LCBuiltinChatMemory, get_messages\nfrom langflow.schema import Data\nfrom langflow.schema.message import Message\nfrom langflow.utils.constants import MESSAGE_SENDER_AI, MESSAGE_SENDER_USER\n\n\nclass MemoryComponent(Component):\n display_name = \"Chat Memory\"\n description = \"Retrieves stored chat messages from Langflow tables or an external memory.\"\n icon = \"message-square-more\"\n name = \"Memory\"\n\n inputs = [\n HandleInput(\n name=\"memory\",\n display_name=\"External Memory\",\n input_types=[\"BaseChatMessageHistory\"],\n info=\"Retrieve messages from an external memory. If empty, it will use the Langflow tables.\",\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER, \"Machine and User\"],\n value=\"Machine and User\",\n info=\"Filter by sender type.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Filter by sender name.\",\n advanced=True,\n ),\n IntInput(\n name=\"n_messages\",\n display_name=\"Number of Messages\",\n value=100,\n info=\"Number of messages to retrieve.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"order\",\n display_name=\"Order\",\n options=[\"Ascending\", \"Descending\"],\n value=\"Ascending\",\n info=\"Order of the messages.\",\n advanced=True,\n ),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. \"\n \"It can contain the keys {text}, {sender} or any other key in the message data.\",\n value=\"{sender_name}: {text}\",\n advanced=True,\n ),\n ]\n\n outputs = [\n Output(display_name=\"Messages (Data)\", name=\"messages\", method=\"retrieve_messages\"),\n Output(display_name=\"Messages (Text)\", name=\"messages_text\", method=\"retrieve_messages_as_text\"),\n Output(display_name=\"Memory\", name=\"lc_memory\", method=\"build_lc_memory\"),\n ]\n\n def retrieve_messages(self) -> Data:\n sender = self.sender\n sender_name = self.sender_name\n session_id = self.session_id\n n_messages = self.n_messages\n order = \"DESC\" if self.order == \"Descending\" else \"ASC\"\n\n if sender == \"Machine and User\":\n sender = None\n\n if self.memory:\n # override session_id\n self.memory.session_id = session_id\n\n stored = self.memory.messages\n # langchain memories are supposed to return messages in ascending order\n if order == \"DESC\":\n stored = stored[::-1]\n if n_messages:\n stored = stored[:n_messages]\n stored = [Message.from_lc_message(m) for m in stored]\n if sender:\n expected_type = MESSAGE_SENDER_AI if sender == MESSAGE_SENDER_AI else MESSAGE_SENDER_USER\n stored = [m for m in stored if m.type == expected_type]\n else:\n stored = get_messages(\n sender=sender,\n sender_name=sender_name,\n session_id=session_id,\n limit=n_messages,\n order=order,\n )\n self.status = stored\n return stored\n\n def retrieve_messages_as_text(self) -> Message:\n stored_text = data_to_text(self.template, self.retrieve_messages())\n self.status = stored_text\n return Message(text=stored_text)\n\n def build_lc_memory(self) -> BaseChatMemory:\n if self.memory:\n chat_memory = self.memory\n else:\n chat_memory = LCBuiltinChatMemory(flow_id=self.flow_id, session_id=self.session_id)\n return ConversationBufferMemory(chat_memory=chat_memory)\n" }, "memory": { "advanced": false, diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Sequential Agent.json b/src/backend/base/langflow/initial_setup/starter_projects/Sequential Agent.json index 5223c371c..7917952c4 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Sequential Agent.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Sequential Agent.json @@ -398,6 +398,7 @@ "display_name": "Output", "method": "build_output", "name": "output", + "required_inputs": [], "selected": "Message", "types": [ "Message" @@ -424,7 +425,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from crewai import Agent, Crew, Process, Task # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\nfrom langflow.schema.message import Message\n\n\nclass SequentialCrewComponent(BaseCrewComponent):\n display_name: str = \"Sequential Crew\"\n description: str = \"Represents a group of agents with tasks that are executed sequentially.\"\n documentation: str = \"https://docs.crewai.com/how-to/Sequential/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"SequentialTask\"], is_list=True),\n ]\n\n def get_tasks_and_agents(self) -> tuple[list[Task], list[Agent]]:\n return self.tasks, [task.agent for task in self.tasks]\n\n def build_crew(self) -> Message:\n tasks, agents = self.get_tasks_and_agents()\n crew = Crew(\n agents=agents,\n tasks=tasks,\n process=Process.sequential,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n return crew\n" + "value": "from crewai import Agent, Crew, Process, Task # type: ignore\n\nfrom langflow.base.agents.crewai.crew import BaseCrewComponent\nfrom langflow.io import HandleInput\nfrom langflow.schema.message import Message\n\n\nclass SequentialCrewComponent(BaseCrewComponent):\n display_name: str = \"Sequential Crew\"\n description: str = \"Represents a group of agents with tasks that are executed sequentially.\"\n documentation: str = \"https://docs.crewai.com/how-to/Sequential/\"\n icon = \"CrewAI\"\n\n inputs = BaseCrewComponent._base_inputs + [\n HandleInput(name=\"tasks\", display_name=\"Tasks\", input_types=[\"SequentialTask\"], is_list=True),\n ]\n\n def get_tasks_and_agents(self) -> tuple[list[Task], list[Agent]]:\n return self.tasks, [task.agent for task in self.tasks]\n\n def build_crew(self) -> Message:\n tasks, agents = self.get_tasks_and_agents()\n return Crew(\n agents=agents,\n tasks=tasks,\n process=Process.sequential,\n verbose=self.verbose,\n memory=self.memory,\n cache=self.use_cache,\n max_rpm=self.max_rpm,\n share_crew=self.share_crew,\n function_calling_llm=self.function_calling_llm,\n step_callback=self.get_step_callback(),\n task_callback=self.get_task_callback(),\n )\n" }, "function_calling_llm": { "advanced": true, @@ -596,6 +597,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -607,6 +613,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -652,7 +669,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, @@ -1173,7 +1190,7 @@ "topic" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -1217,7 +1234,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "template": { "advanced": false, @@ -1294,7 +1311,7 @@ "topic" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -1338,7 +1355,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "template": { "advanced": false, @@ -1415,7 +1432,7 @@ "topic" ] }, - "description": "Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.", + "description": "Create a prompt template with dynamic variables.", "display_name": "Prompt", "documentation": "", "edited": false, @@ -1459,7 +1476,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.inputs.inputs import MessageInput\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables. If using an OutputParser, you must include {format_instructions} as an additional variable.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" + "value": "from langflow.base.prompts.api_utils import process_prompt_template\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DefaultPromptField\nfrom langflow.io import Output, PromptInput\nfrom langflow.schema.message import Message\nfrom langflow.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt\"\n description: str = \"Create a prompt template with dynamic variables.\"\n icon = \"prompts\"\n trace_type = \"prompt\"\n name = \"Prompt\"\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n ]\n\n outputs = [\n Output(display_name=\"Prompt Message\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(\n self,\n ) -> Message:\n prompt = await Message.from_template_and_variables(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n def post_code_processing(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"\n This function is called after the code validation is done.\n \"\"\"\n frontend_node = super().post_code_processing(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n" }, "template": { "advanced": false, diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json b/src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json index c3dad2d52..40aae146b 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json @@ -837,6 +837,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -848,6 +853,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -893,7 +909,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langchain_openai import ChatOpenAI\nfrom langflow.inputs.inputs import HandleInput\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "_input_type": "MessageInput", @@ -1436,6 +1452,14 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Data", "types": [ "Data" @@ -1447,6 +1471,14 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "api_key", + "engine", + "input_value", + "max_results", + "max_snippet_length", + "search_params" + ], "selected": "Tool", "types": [ "Tool" @@ -2297,6 +2329,9 @@ "display_name": "Data", "method": "run_model", "name": "api_run_model", + "required_inputs": [ + "expression" + ], "selected": "Data", "types": [ "Data" @@ -2308,6 +2343,9 @@ "display_name": "Tool", "method": "build_tool", "name": "api_build_tool", + "required_inputs": [ + "expression" + ], "selected": "Tool", "types": [ "Tool" @@ -2334,7 +2372,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import ast\nimport operator\n\nfrom langchain.tools import StructuredTool\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import MessageTextInput\nfrom langflow.schema import Data\n\n\nclass CalculatorToolComponent(LCToolComponent):\n display_name = \"Calculator\"\n description = \"Perform basic arithmetic operations on a given expression.\"\n icon = \"calculator\"\n name = \"CalculatorTool\"\n\n inputs = [\n MessageTextInput(\n name=\"expression\",\n display_name=\"Expression\",\n info=\"The arithmetic expression to evaluate (e.g., '4*4*(33/22)+12-20').\",\n ),\n ]\n\n class CalculatorToolSchema(BaseModel):\n expression: str = Field(..., description=\"The arithmetic expression to evaluate.\")\n\n def run_model(self) -> list[Data]:\n return self._evaluate_expression(self.expression)\n\n def build_tool(self) -> Tool:\n return StructuredTool.from_function(\n name=\"calculator\",\n description=\"Evaluate basic arithmetic expressions. Input should be a string containing the expression.\",\n func=self._evaluate_expression,\n args_schema=self.CalculatorToolSchema,\n )\n\n def _evaluate_expression(self, expression: str) -> list[Data]:\n try:\n # Define the allowed operators\n operators = {\n ast.Add: operator.add,\n ast.Sub: operator.sub,\n ast.Mult: operator.mul,\n ast.Div: operator.truediv,\n ast.Pow: operator.pow,\n }\n\n def eval_expr(node):\n if isinstance(node, ast.Num):\n return node.n\n elif isinstance(node, ast.BinOp):\n return operators[type(node.op)](eval_expr(node.left), eval_expr(node.right))\n elif isinstance(node, ast.UnaryOp):\n return operators[type(node.op)](eval_expr(node.operand))\n else:\n raise TypeError(node)\n\n # Parse the expression and evaluate it\n tree = ast.parse(expression, mode=\"eval\")\n result = eval_expr(tree.body)\n\n # Format the result to a reasonable number of decimal places\n formatted_result = f\"{result:.6f}\".rstrip(\"0\").rstrip(\".\")\n\n self.status = formatted_result\n return [Data(data={\"result\": formatted_result})]\n\n except (SyntaxError, TypeError, KeyError) as e:\n error_message = f\"Invalid expression: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except ZeroDivisionError:\n error_message = \"Error: Division by zero\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except Exception as e:\n error_message = f\"Error: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n" + "value": "import ast\nimport operator\n\nfrom langchain.tools import StructuredTool\nfrom pydantic import BaseModel, Field\n\nfrom langflow.base.langchain_utilities.model import LCToolComponent\nfrom langflow.field_typing import Tool\nfrom langflow.inputs import MessageTextInput\nfrom langflow.schema import Data\n\n\nclass CalculatorToolComponent(LCToolComponent):\n display_name = \"Calculator\"\n description = \"Perform basic arithmetic operations on a given expression.\"\n icon = \"calculator\"\n name = \"CalculatorTool\"\n\n inputs = [\n MessageTextInput(\n name=\"expression\",\n display_name=\"Expression\",\n info=\"The arithmetic expression to evaluate (e.g., '4*4*(33/22)+12-20').\",\n ),\n ]\n\n class CalculatorToolSchema(BaseModel):\n expression: str = Field(..., description=\"The arithmetic expression to evaluate.\")\n\n def run_model(self) -> list[Data]:\n return self._evaluate_expression(self.expression)\n\n def build_tool(self) -> Tool:\n return StructuredTool.from_function(\n name=\"calculator\",\n description=\"Evaluate basic arithmetic expressions. Input should be a string containing the expression.\",\n func=self._evaluate_expression,\n args_schema=self.CalculatorToolSchema,\n )\n\n def _evaluate_expression(self, expression: str) -> list[Data]:\n try:\n # Define the allowed operators\n operators = {\n ast.Add: operator.add,\n ast.Sub: operator.sub,\n ast.Mult: operator.mul,\n ast.Div: operator.truediv,\n ast.Pow: operator.pow,\n }\n\n def eval_expr(node):\n if isinstance(node, ast.Num):\n return node.n\n if isinstance(node, ast.BinOp):\n return operators[type(node.op)](eval_expr(node.left), eval_expr(node.right))\n if isinstance(node, ast.UnaryOp):\n return operators[type(node.op)](eval_expr(node.operand))\n raise TypeError(node)\n\n # Parse the expression and evaluate it\n tree = ast.parse(expression, mode=\"eval\")\n result = eval_expr(tree.body)\n\n # Format the result to a reasonable number of decimal places\n formatted_result = f\"{result:.6f}\".rstrip(\"0\").rstrip(\".\")\n\n self.status = formatted_result\n return [Data(data={\"result\": formatted_result})]\n\n except (SyntaxError, TypeError, KeyError) as e:\n error_message = f\"Invalid expression: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except ZeroDivisionError:\n error_message = \"Error: Division by zero\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n except Exception as e:\n error_message = f\"Error: {str(e)}\"\n self.status = error_message\n return [Data(data={\"error\": error_message})]\n" }, "expression": { "_input_type": "MessageTextInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json b/src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json index f458ece79..31deccbdd 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json @@ -532,6 +532,7 @@ "display_name": "Retriever", "method": "build_base_retriever", "name": "base_retriever", + "required_inputs": [], "selected": "Retriever", "types": [ "Retriever" @@ -543,6 +544,29 @@ "display_name": "Search Results", "method": "search_documents", "name": "search_results", + "required_inputs": [ + "api_endpoint", + "batch_size", + "bulk_delete_concurrency", + "bulk_insert_batch_concurrency", + "bulk_insert_overwrite_concurrency", + "collection_indexing_policy", + "collection_name", + "embedding", + "ingest_data", + "metadata_indexing_exclude", + "metadata_indexing_include", + "metric", + "namespace", + "number_of_results", + "pre_delete_collection", + "search_filter", + "search_input", + "search_score_threshold", + "search_type", + "setup_mode", + "token" + ], "selected": "Data", "types": [ "Data" @@ -554,6 +578,7 @@ "display_name": "Vector Store", "method": "cast_vector_store", "name": "vector_store", + "required_inputs": [], "selected": "VectorStore", "types": [ "VectorStore" @@ -658,7 +683,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import os\n\nfrom astrapy.admin import parse_api_endpoint\nfrom loguru import logger\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.helpers import docs_to_data\nfrom langflow.inputs import DictInput, FloatInput, MessageTextInput\nfrom langflow.io import (\n BoolInput,\n DataInput,\n DropdownInput,\n HandleInput,\n IntInput,\n MultilineInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.schema import Data\n\n\nclass AstraVectorStoreComponent(LCVectorStoreComponent):\n display_name: str = \"Astra DB\"\n description: str = \"Implementation of Vector Store using Astra DB with search capabilities\"\n documentation: str = \"https://docs.langflow.org/starter-projects-vector-store-rag\"\n name = \"AstraDB\"\n icon: str = \"AstraDB\"\n\n VECTORIZE_PROVIDERS_MAPPING = {\n \"Azure OpenAI\": [\"azureOpenAI\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Hugging Face - Dedicated\": [\"huggingfaceDedicated\", [\"endpoint-defined-model\"]],\n \"Hugging Face - Serverless\": [\n \"huggingface\",\n [\n \"sentence-transformers/all-MiniLM-L6-v2\",\n \"intfloat/multilingual-e5-large\",\n \"intfloat/multilingual-e5-large-instruct\",\n \"BAAI/bge-small-en-v1.5\",\n \"BAAI/bge-base-en-v1.5\",\n \"BAAI/bge-large-en-v1.5\",\n ],\n ],\n \"Jina AI\": [\n \"jinaAI\",\n [\n \"jina-embeddings-v2-base-en\",\n \"jina-embeddings-v2-base-de\",\n \"jina-embeddings-v2-base-es\",\n \"jina-embeddings-v2-base-code\",\n \"jina-embeddings-v2-base-zh\",\n ],\n ],\n \"Mistral AI\": [\"mistral\", [\"mistral-embed\"]],\n \"NVIDIA\": [\"nvidia\", [\"NV-Embed-QA\"]],\n \"OpenAI\": [\"openai\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Upstage\": [\"upstageAI\", [\"solar-embedding-1-large\"]],\n \"Voyage AI\": [\n \"voyageAI\",\n [\"voyage-large-2-instruct\", \"voyage-law-2\", \"voyage-code-2\", \"voyage-large-2\", \"voyage-2\"],\n ],\n }\n\n inputs = [\n SecretStrInput(\n name=\"token\",\n display_name=\"Astra DB Application Token\",\n info=\"Authentication token for accessing Astra DB.\",\n value=\"ASTRA_DB_APPLICATION_TOKEN\",\n required=True,\n advanced=os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\",\n ),\n SecretStrInput(\n name=\"api_endpoint\",\n display_name=\"Database\" if os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\" else \"API Endpoint\",\n info=\"API endpoint URL for the Astra DB service.\",\n value=\"ASTRA_DB_API_ENDPOINT\",\n required=True,\n ),\n StrInput(\n name=\"collection_name\",\n display_name=\"Collection Name\",\n info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n required=True,\n ),\n MultilineInput(\n name=\"search_input\",\n display_name=\"Search Input\",\n ),\n DataInput(\n name=\"ingest_data\",\n display_name=\"Ingest Data\",\n is_list=True,\n ),\n StrInput(\n name=\"namespace\",\n display_name=\"Namespace\",\n info=\"Optional namespace within Astra DB to use for the collection.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"embedding_service\",\n display_name=\"Embedding Model or Astra Vectorize\",\n info=\"Determines whether to use Astra Vectorize for the collection.\",\n options=[\"Embedding Model\", \"Astra Vectorize\"],\n real_time_refresh=True,\n value=\"Embedding Model\",\n ),\n HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ),\n DropdownInput(\n name=\"metric\",\n display_name=\"Metric\",\n info=\"Optional distance metric for vector comparisons in the vector store.\",\n options=[\"cosine\", \"dot_product\", \"euclidean\"],\n advanced=True,\n ),\n IntInput(\n name=\"batch_size\",\n display_name=\"Batch Size\",\n info=\"Optional number of data to process in a single batch.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_batch_concurrency\",\n display_name=\"Bulk Insert Batch Concurrency\",\n info=\"Optional concurrency level for bulk insert operations.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_overwrite_concurrency\",\n display_name=\"Bulk Insert Overwrite Concurrency\",\n info=\"Optional concurrency level for bulk insert operations that overwrite existing data.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_delete_concurrency\",\n display_name=\"Bulk Delete Concurrency\",\n info=\"Optional concurrency level for bulk delete operations.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"setup_mode\",\n display_name=\"Setup Mode\",\n info=\"Configuration mode for setting up the vector store, with options like 'Sync', 'Async', or 'Off'.\",\n options=[\"Sync\", \"Async\", \"Off\"],\n advanced=True,\n value=\"Sync\",\n ),\n BoolInput(\n name=\"pre_delete_collection\",\n display_name=\"Pre Delete Collection\",\n info=\"Boolean flag to determine whether to delete the collection before creating a new one.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_include\",\n display_name=\"Metadata Indexing Include\",\n info=\"Optional list of metadata fields to include in the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_exclude\",\n display_name=\"Metadata Indexing Exclude\",\n info=\"Optional list of metadata fields to exclude from the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"collection_indexing_policy\",\n display_name=\"Collection Indexing Policy\",\n info=\"Optional dictionary defining the indexing policy for the collection.\",\n advanced=True,\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Number of Results\",\n info=\"Number of results to return.\",\n advanced=True,\n value=4,\n ),\n DropdownInput(\n name=\"search_type\",\n display_name=\"Search Type\",\n info=\"Search type to use\",\n options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n value=\"Similarity\",\n advanced=True,\n ),\n FloatInput(\n name=\"search_score_threshold\",\n display_name=\"Search Score Threshold\",\n info=\"Minimum similarity score threshold for search results. (when using 'Similarity with score threshold')\",\n value=0,\n advanced=True,\n ),\n DictInput(\n name=\"search_filter\",\n display_name=\"Search Metadata Filter\",\n info=\"Optional dictionary of filters to apply to the search query.\",\n advanced=True,\n is_list=True,\n ),\n ]\n\n def insert_in_dict(self, build_config, field_name, new_parameters):\n # Insert the new key-value pair after the found key\n for new_field_name, new_parameter in new_parameters.items():\n # Get all the items as a list of tuples (key, value)\n items = list(build_config.items())\n\n # Find the index of the key to insert after\n for i, (key, value) in enumerate(items):\n if key == field_name:\n break\n\n items.insert(i + 1, (new_field_name, new_parameter))\n\n # Clear the original dictionary and update with the modified items\n build_config.clear()\n build_config.update(items)\n\n return build_config\n\n def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n if field_name == \"embedding_service\":\n if field_value == \"Astra Vectorize\":\n for field in [\"embedding\"]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = DropdownInput(\n name=\"provider\",\n display_name=\"Vectorize Provider\",\n options=self.VECTORIZE_PROVIDERS_MAPPING.keys(),\n value=\"\",\n required=True,\n real_time_refresh=True,\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"provider\": new_parameter})\n else:\n for field in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"embedding\": new_parameter})\n\n elif field_name == \"provider\":\n for field in [\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n model_options = self.VECTORIZE_PROVIDERS_MAPPING[field_value][1]\n\n new_parameter_0 = DropdownInput(\n name=\"z_00_model_name\",\n display_name=\"Model Name\",\n info=f\"The embedding model to use for the selected provider. Each provider has a different set of models \"\n f\"available (full list at https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html):\\n\\n{', '.join(model_options)}\",\n options=model_options,\n required=True,\n ).to_dict()\n\n new_parameter_1 = DictInput(\n name=\"z_01_model_parameters\",\n display_name=\"Model Parameters\",\n is_list=True,\n ).to_dict()\n\n new_parameter_2 = MessageTextInput(\n name=\"z_02_api_key_name\",\n display_name=\"API Key name\",\n info=\"The name of the embeddings provider API key stored on Astra. If set, it will override the 'ProviderKey' in the authentication parameters.\",\n ).to_dict()\n\n new_parameter_3 = SecretStrInput(\n name=\"z_03_provider_api_key\",\n display_name=\"Provider API Key\",\n info=\"An alternative to the Astra Authentication that passes an API key for the provider with each request to Astra DB. This may be used when Vectorize is configured for the collection, but no corresponding provider secret is stored within Astra's key management system.\",\n ).to_dict()\n\n new_parameter_4 = DictInput(\n name=\"z_04_authentication\",\n display_name=\"Authentication parameters\",\n is_list=True,\n ).to_dict()\n\n self.insert_in_dict(\n build_config,\n \"provider\",\n {\n \"z_00_model_name\": new_parameter_0,\n \"z_01_model_parameters\": new_parameter_1,\n \"z_02_api_key_name\": new_parameter_2,\n \"z_03_provider_api_key\": new_parameter_3,\n \"z_04_authentication\": new_parameter_4,\n },\n )\n\n return build_config\n\n def build_vectorize_options(self, **kwargs):\n for attribute in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if not hasattr(self, attribute):\n setattr(self, attribute, None)\n\n # Fetch values from kwargs if any self.* attributes are None\n provider_value = self.VECTORIZE_PROVIDERS_MAPPING.get(self.provider, [None])[0] or kwargs.get(\"provider\")\n authentication = {**(self.z_04_authentication or kwargs.get(\"z_04_authentication\", {}))}\n\n api_key_name = self.z_02_api_key_name or kwargs.get(\"z_02_api_key_name\")\n provider_key = self.z_03_provider_api_key or kwargs.get(\"z_03_provider_api_key\")\n if api_key_name:\n authentication[\"providerKey\"] = api_key_name\n\n return {\n # must match astrapy.info.CollectionVectorServiceOptions\n \"collection_vector_service_options\": {\n \"provider\": provider_value,\n \"modelName\": self.z_00_model_name or kwargs.get(\"z_00_model_name\"),\n \"authentication\": authentication,\n \"parameters\": self.z_01_model_parameters or kwargs.get(\"z_01_model_parameters\", {}),\n },\n \"collection_embedding_api_key\": provider_key,\n }\n\n @check_cached_vector_store\n def build_vector_store(self, vectorize_options=None):\n try:\n from langchain_astradb import AstraDBVectorStore\n from langchain_astradb.utils.astradb import SetupMode\n except ImportError:\n raise ImportError(\n \"Could not import langchain Astra DB integration package. \"\n \"Please install it with `pip install langchain-astradb`.\"\n )\n\n try:\n if not self.setup_mode:\n self.setup_mode = self._inputs[\"setup_mode\"].options[0]\n\n setup_mode_value = SetupMode[self.setup_mode.upper()]\n except KeyError:\n raise ValueError(f\"Invalid setup mode: {self.setup_mode}\")\n\n if self.embedding:\n embedding_dict = {\"embedding\": self.embedding}\n else:\n from astrapy.info import CollectionVectorServiceOptions\n\n dict_options = vectorize_options or self.build_vectorize_options()\n dict_options[\"authentication\"] = {\n k: v for k, v in dict_options.get(\"authentication\", {}).items() if k and v\n }\n dict_options[\"parameters\"] = {k: v for k, v in dict_options.get(\"parameters\", {}).items() if k and v}\n\n embedding_dict = {\n \"collection_vector_service_options\": CollectionVectorServiceOptions.from_dict(\n dict_options.get(\"collection_vector_service_options\", {})\n ),\n }\n\n vector_store_kwargs = {\n **embedding_dict,\n \"collection_name\": self.collection_name,\n \"token\": self.token,\n \"api_endpoint\": self.api_endpoint,\n \"namespace\": self.namespace or None,\n \"environment\": parse_api_endpoint(self.api_endpoint).environment,\n \"metric\": self.metric or None,\n \"batch_size\": self.batch_size or None,\n \"bulk_insert_batch_concurrency\": self.bulk_insert_batch_concurrency or None,\n \"bulk_insert_overwrite_concurrency\": self.bulk_insert_overwrite_concurrency or None,\n \"bulk_delete_concurrency\": self.bulk_delete_concurrency or None,\n \"setup_mode\": setup_mode_value,\n \"pre_delete_collection\": self.pre_delete_collection or False,\n }\n\n if self.metadata_indexing_include:\n vector_store_kwargs[\"metadata_indexing_include\"] = self.metadata_indexing_include\n elif self.metadata_indexing_exclude:\n vector_store_kwargs[\"metadata_indexing_exclude\"] = self.metadata_indexing_exclude\n elif self.collection_indexing_policy:\n vector_store_kwargs[\"collection_indexing_policy\"] = self.collection_indexing_policy\n\n try:\n vector_store = AstraDBVectorStore(**vector_store_kwargs)\n except Exception as e:\n raise ValueError(f\"Error initializing AstraDBVectorStore: {str(e)}\") from e\n\n self._add_documents_to_vector_store(vector_store)\n\n return vector_store\n\n def _add_documents_to_vector_store(self, vector_store):\n documents = []\n for _input in self.ingest_data or []:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n raise ValueError(\"Vector Store Inputs must be Data objects.\")\n\n if documents:\n logger.debug(f\"Adding {len(documents)} documents to the Vector Store.\")\n try:\n vector_store.add_documents(documents)\n except Exception as e:\n raise ValueError(f\"Error adding documents to AstraDBVectorStore: {str(e)}\") from e\n else:\n logger.debug(\"No documents to add to the Vector Store.\")\n\n def _map_search_type(self):\n if self.search_type == \"Similarity with score threshold\":\n return \"similarity_score_threshold\"\n elif self.search_type == \"MMR (Max Marginal Relevance)\":\n return \"mmr\"\n else:\n return \"similarity\"\n\n def _build_search_args(self):\n args = {\n \"k\": self.number_of_results,\n \"score_threshold\": self.search_score_threshold,\n }\n\n if self.search_filter:\n clean_filter = {k: v for k, v in self.search_filter.items() if k and v}\n if len(clean_filter) > 0:\n args[\"filter\"] = clean_filter\n return args\n\n def search_documents(self, vector_store=None) -> list[Data]:\n if not vector_store:\n vector_store = self.build_vector_store()\n\n logger.debug(f\"Search input: {self.search_input}\")\n logger.debug(f\"Search type: {self.search_type}\")\n logger.debug(f\"Number of results: {self.number_of_results}\")\n\n if self.search_input and isinstance(self.search_input, str) and self.search_input.strip():\n try:\n search_type = self._map_search_type()\n search_args = self._build_search_args()\n\n docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)\n except Exception as e:\n raise ValueError(f\"Error performing search in AstraDBVectorStore: {str(e)}\") from e\n\n logger.debug(f\"Retrieved documents: {len(docs)}\")\n\n data = docs_to_data(docs)\n logger.debug(f\"Converted documents to data: {len(data)}\")\n self.status = data\n return data\n else:\n logger.debug(\"No search input provided. Skipping search.\")\n return []\n\n def get_retriever_kwargs(self):\n search_args = self._build_search_args()\n return {\n \"search_type\": self._map_search_type(),\n \"search_kwargs\": search_args,\n }\n" + "value": "import os\n\nfrom astrapy.admin import parse_api_endpoint\nfrom loguru import logger\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.helpers import docs_to_data\nfrom langflow.inputs import DictInput, FloatInput, MessageTextInput\nfrom langflow.io import (\n BoolInput,\n DataInput,\n DropdownInput,\n HandleInput,\n IntInput,\n MultilineInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.schema import Data\n\n\nclass AstraVectorStoreComponent(LCVectorStoreComponent):\n display_name: str = \"Astra DB\"\n description: str = \"Implementation of Vector Store using Astra DB with search capabilities\"\n documentation: str = \"https://docs.langflow.org/starter-projects-vector-store-rag\"\n name = \"AstraDB\"\n icon: str = \"AstraDB\"\n\n VECTORIZE_PROVIDERS_MAPPING = {\n \"Azure OpenAI\": [\"azureOpenAI\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Hugging Face - Dedicated\": [\"huggingfaceDedicated\", [\"endpoint-defined-model\"]],\n \"Hugging Face - Serverless\": [\n \"huggingface\",\n [\n \"sentence-transformers/all-MiniLM-L6-v2\",\n \"intfloat/multilingual-e5-large\",\n \"intfloat/multilingual-e5-large-instruct\",\n \"BAAI/bge-small-en-v1.5\",\n \"BAAI/bge-base-en-v1.5\",\n \"BAAI/bge-large-en-v1.5\",\n ],\n ],\n \"Jina AI\": [\n \"jinaAI\",\n [\n \"jina-embeddings-v2-base-en\",\n \"jina-embeddings-v2-base-de\",\n \"jina-embeddings-v2-base-es\",\n \"jina-embeddings-v2-base-code\",\n \"jina-embeddings-v2-base-zh\",\n ],\n ],\n \"Mistral AI\": [\"mistral\", [\"mistral-embed\"]],\n \"NVIDIA\": [\"nvidia\", [\"NV-Embed-QA\"]],\n \"OpenAI\": [\"openai\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Upstage\": [\"upstageAI\", [\"solar-embedding-1-large\"]],\n \"Voyage AI\": [\n \"voyageAI\",\n [\"voyage-large-2-instruct\", \"voyage-law-2\", \"voyage-code-2\", \"voyage-large-2\", \"voyage-2\"],\n ],\n }\n\n inputs = [\n SecretStrInput(\n name=\"token\",\n display_name=\"Astra DB Application Token\",\n info=\"Authentication token for accessing Astra DB.\",\n value=\"ASTRA_DB_APPLICATION_TOKEN\",\n required=True,\n advanced=os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\",\n ),\n SecretStrInput(\n name=\"api_endpoint\",\n display_name=\"Database\" if os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\" else \"API Endpoint\",\n info=\"API endpoint URL for the Astra DB service.\",\n value=\"ASTRA_DB_API_ENDPOINT\",\n required=True,\n ),\n StrInput(\n name=\"collection_name\",\n display_name=\"Collection Name\",\n info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n required=True,\n ),\n MultilineInput(\n name=\"search_input\",\n display_name=\"Search Input\",\n ),\n DataInput(\n name=\"ingest_data\",\n display_name=\"Ingest Data\",\n is_list=True,\n ),\n StrInput(\n name=\"namespace\",\n display_name=\"Namespace\",\n info=\"Optional namespace within Astra DB to use for the collection.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"embedding_service\",\n display_name=\"Embedding Model or Astra Vectorize\",\n info=\"Determines whether to use Astra Vectorize for the collection.\",\n options=[\"Embedding Model\", \"Astra Vectorize\"],\n real_time_refresh=True,\n value=\"Embedding Model\",\n ),\n HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ),\n DropdownInput(\n name=\"metric\",\n display_name=\"Metric\",\n info=\"Optional distance metric for vector comparisons in the vector store.\",\n options=[\"cosine\", \"dot_product\", \"euclidean\"],\n advanced=True,\n ),\n IntInput(\n name=\"batch_size\",\n display_name=\"Batch Size\",\n info=\"Optional number of data to process in a single batch.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_batch_concurrency\",\n display_name=\"Bulk Insert Batch Concurrency\",\n info=\"Optional concurrency level for bulk insert operations.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_overwrite_concurrency\",\n display_name=\"Bulk Insert Overwrite Concurrency\",\n info=\"Optional concurrency level for bulk insert operations that overwrite existing data.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_delete_concurrency\",\n display_name=\"Bulk Delete Concurrency\",\n info=\"Optional concurrency level for bulk delete operations.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"setup_mode\",\n display_name=\"Setup Mode\",\n info=\"Configuration mode for setting up the vector store, with options like 'Sync', 'Async', or 'Off'.\",\n options=[\"Sync\", \"Async\", \"Off\"],\n advanced=True,\n value=\"Sync\",\n ),\n BoolInput(\n name=\"pre_delete_collection\",\n display_name=\"Pre Delete Collection\",\n info=\"Boolean flag to determine whether to delete the collection before creating a new one.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_include\",\n display_name=\"Metadata Indexing Include\",\n info=\"Optional list of metadata fields to include in the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_exclude\",\n display_name=\"Metadata Indexing Exclude\",\n info=\"Optional list of metadata fields to exclude from the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"collection_indexing_policy\",\n display_name=\"Collection Indexing Policy\",\n info=\"Optional dictionary defining the indexing policy for the collection.\",\n advanced=True,\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Number of Results\",\n info=\"Number of results to return.\",\n advanced=True,\n value=4,\n ),\n DropdownInput(\n name=\"search_type\",\n display_name=\"Search Type\",\n info=\"Search type to use\",\n options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n value=\"Similarity\",\n advanced=True,\n ),\n FloatInput(\n name=\"search_score_threshold\",\n display_name=\"Search Score Threshold\",\n info=\"Minimum similarity score threshold for search results. \"\n \"(when using 'Similarity with score threshold')\",\n value=0,\n advanced=True,\n ),\n DictInput(\n name=\"search_filter\",\n display_name=\"Search Metadata Filter\",\n info=\"Optional dictionary of filters to apply to the search query.\",\n advanced=True,\n is_list=True,\n ),\n ]\n\n def insert_in_dict(self, build_config, field_name, new_parameters):\n # Insert the new key-value pair after the found key\n for new_field_name, new_parameter in new_parameters.items():\n # Get all the items as a list of tuples (key, value)\n items = list(build_config.items())\n\n # Find the index of the key to insert after\n for i, (key, value) in enumerate(items):\n if key == field_name:\n break\n\n items.insert(i + 1, (new_field_name, new_parameter))\n\n # Clear the original dictionary and update with the modified items\n build_config.clear()\n build_config.update(items)\n\n return build_config\n\n def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n if field_name == \"embedding_service\":\n if field_value == \"Astra Vectorize\":\n for field in [\"embedding\"]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = DropdownInput(\n name=\"provider\",\n display_name=\"Vectorize Provider\",\n options=self.VECTORIZE_PROVIDERS_MAPPING.keys(),\n value=\"\",\n required=True,\n real_time_refresh=True,\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"provider\": new_parameter})\n else:\n for field in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"embedding\": new_parameter})\n\n elif field_name == \"provider\":\n for field in [\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n model_options = self.VECTORIZE_PROVIDERS_MAPPING[field_value][1]\n\n new_parameter_0 = DropdownInput(\n name=\"z_00_model_name\",\n display_name=\"Model Name\",\n info=\"The embedding model to use for the selected provider. Each provider has a different set of \"\n \"models available (full list at \"\n \"https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html):\\n\\n\"\n f\"{', '.join(model_options)}\",\n options=model_options,\n required=True,\n ).to_dict()\n\n new_parameter_1 = DictInput(\n name=\"z_01_model_parameters\",\n display_name=\"Model Parameters\",\n is_list=True,\n ).to_dict()\n\n new_parameter_2 = MessageTextInput(\n name=\"z_02_api_key_name\",\n display_name=\"API Key name\",\n info=\"The name of the embeddings provider API key stored on Astra. \"\n \"If set, it will override the 'ProviderKey' in the authentication parameters.\",\n ).to_dict()\n\n new_parameter_3 = SecretStrInput(\n name=\"z_03_provider_api_key\",\n display_name=\"Provider API Key\",\n info=\"An alternative to the Astra Authentication that passes an API key for the provider \"\n \"with each request to Astra DB. \"\n \"This may be used when Vectorize is configured for the collection, \"\n \"but no corresponding provider secret is stored within Astra's key management system.\",\n ).to_dict()\n\n new_parameter_4 = DictInput(\n name=\"z_04_authentication\",\n display_name=\"Authentication parameters\",\n is_list=True,\n ).to_dict()\n\n self.insert_in_dict(\n build_config,\n \"provider\",\n {\n \"z_00_model_name\": new_parameter_0,\n \"z_01_model_parameters\": new_parameter_1,\n \"z_02_api_key_name\": new_parameter_2,\n \"z_03_provider_api_key\": new_parameter_3,\n \"z_04_authentication\": new_parameter_4,\n },\n )\n\n return build_config\n\n def build_vectorize_options(self, **kwargs):\n for attribute in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if not hasattr(self, attribute):\n setattr(self, attribute, None)\n\n # Fetch values from kwargs if any self.* attributes are None\n provider_value = self.VECTORIZE_PROVIDERS_MAPPING.get(self.provider, [None])[0] or kwargs.get(\"provider\")\n authentication = {**(self.z_04_authentication or kwargs.get(\"z_04_authentication\", {}))}\n\n api_key_name = self.z_02_api_key_name or kwargs.get(\"z_02_api_key_name\")\n provider_key = self.z_03_provider_api_key or kwargs.get(\"z_03_provider_api_key\")\n if api_key_name:\n authentication[\"providerKey\"] = api_key_name\n\n return {\n # must match astrapy.info.CollectionVectorServiceOptions\n \"collection_vector_service_options\": {\n \"provider\": provider_value,\n \"modelName\": self.z_00_model_name or kwargs.get(\"z_00_model_name\"),\n \"authentication\": authentication,\n \"parameters\": self.z_01_model_parameters or kwargs.get(\"z_01_model_parameters\", {}),\n },\n \"collection_embedding_api_key\": provider_key,\n }\n\n @check_cached_vector_store\n def build_vector_store(self, vectorize_options=None):\n try:\n from langchain_astradb import AstraDBVectorStore\n from langchain_astradb.utils.astradb import SetupMode\n except ImportError:\n msg = (\n \"Could not import langchain Astra DB integration package. \"\n \"Please install it with `pip install langchain-astradb`.\"\n )\n raise ImportError(msg)\n\n try:\n if not self.setup_mode:\n self.setup_mode = self._inputs[\"setup_mode\"].options[0]\n\n setup_mode_value = SetupMode[self.setup_mode.upper()]\n except KeyError:\n msg = f\"Invalid setup mode: {self.setup_mode}\"\n raise ValueError(msg)\n\n if self.embedding:\n embedding_dict = {\"embedding\": self.embedding}\n else:\n from astrapy.info import CollectionVectorServiceOptions\n\n dict_options = vectorize_options or self.build_vectorize_options()\n dict_options[\"authentication\"] = {\n k: v for k, v in dict_options.get(\"authentication\", {}).items() if k and v\n }\n dict_options[\"parameters\"] = {k: v for k, v in dict_options.get(\"parameters\", {}).items() if k and v}\n\n embedding_dict = {\n \"collection_vector_service_options\": CollectionVectorServiceOptions.from_dict(\n dict_options.get(\"collection_vector_service_options\", {})\n ),\n }\n\n vector_store_kwargs = {\n **embedding_dict,\n \"collection_name\": self.collection_name,\n \"token\": self.token,\n \"api_endpoint\": self.api_endpoint,\n \"namespace\": self.namespace or None,\n \"environment\": parse_api_endpoint(self.api_endpoint).environment,\n \"metric\": self.metric or None,\n \"batch_size\": self.batch_size or None,\n \"bulk_insert_batch_concurrency\": self.bulk_insert_batch_concurrency or None,\n \"bulk_insert_overwrite_concurrency\": self.bulk_insert_overwrite_concurrency or None,\n \"bulk_delete_concurrency\": self.bulk_delete_concurrency or None,\n \"setup_mode\": setup_mode_value,\n \"pre_delete_collection\": self.pre_delete_collection or False,\n }\n\n if self.metadata_indexing_include:\n vector_store_kwargs[\"metadata_indexing_include\"] = self.metadata_indexing_include\n elif self.metadata_indexing_exclude:\n vector_store_kwargs[\"metadata_indexing_exclude\"] = self.metadata_indexing_exclude\n elif self.collection_indexing_policy:\n vector_store_kwargs[\"collection_indexing_policy\"] = self.collection_indexing_policy\n\n try:\n vector_store = AstraDBVectorStore(**vector_store_kwargs)\n except Exception as e:\n msg = f\"Error initializing AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n\n self._add_documents_to_vector_store(vector_store)\n\n return vector_store\n\n def _add_documents_to_vector_store(self, vector_store):\n documents = []\n for _input in self.ingest_data or []:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n msg = \"Vector Store Inputs must be Data objects.\"\n raise ValueError(msg)\n\n if documents:\n logger.debug(f\"Adding {len(documents)} documents to the Vector Store.\")\n try:\n vector_store.add_documents(documents)\n except Exception as e:\n msg = f\"Error adding documents to AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n else:\n logger.debug(\"No documents to add to the Vector Store.\")\n\n def _map_search_type(self):\n if self.search_type == \"Similarity with score threshold\":\n return \"similarity_score_threshold\"\n if self.search_type == \"MMR (Max Marginal Relevance)\":\n return \"mmr\"\n return \"similarity\"\n\n def _build_search_args(self):\n args = {\n \"k\": self.number_of_results,\n \"score_threshold\": self.search_score_threshold,\n }\n\n if self.search_filter:\n clean_filter = {k: v for k, v in self.search_filter.items() if k and v}\n if len(clean_filter) > 0:\n args[\"filter\"] = clean_filter\n return args\n\n def search_documents(self, vector_store=None) -> list[Data]:\n if not vector_store:\n vector_store = self.build_vector_store()\n\n logger.debug(f\"Search input: {self.search_input}\")\n logger.debug(f\"Search type: {self.search_type}\")\n logger.debug(f\"Number of results: {self.number_of_results}\")\n\n if self.search_input and isinstance(self.search_input, str) and self.search_input.strip():\n try:\n search_type = self._map_search_type()\n search_args = self._build_search_args()\n\n docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)\n except Exception as e:\n msg = f\"Error performing search in AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n\n logger.debug(f\"Retrieved documents: {len(docs)}\")\n\n data = docs_to_data(docs)\n logger.debug(f\"Converted documents to data: {len(data)}\")\n self.status = data\n return data\n logger.debug(\"No search input provided. Skipping search.\")\n return []\n\n def get_retriever_kwargs(self):\n search_args = self._build_search_args()\n return {\n \"search_type\": self._map_search_type(),\n \"search_kwargs\": search_args,\n }\n" }, "collection_indexing_policy": { "advanced": true, @@ -1030,7 +1055,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" + "value": "from langflow.custom import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.io import DataInput, MultilineInput, Output, StrInput\nfrom langflow.schema.message import Message\n\n\nclass ParseDataComponent(Component):\n display_name = \"Parse Data\"\n description = \"Convert Data into plain text following a specified template.\"\n icon = \"braces\"\n name = \"ParseData\"\n\n inputs = [\n DataInput(name=\"data\", display_name=\"Data\", info=\"The data to convert to text.\"),\n MultilineInput(\n name=\"template\",\n display_name=\"Template\",\n info=\"The template to use for formatting the data. \"\n \"It can contain the keys {text}, {data} or any other key in the Data.\",\n value=\"{text}\",\n ),\n StrInput(name=\"sep\", display_name=\"Separator\", advanced=True, value=\"\\n\"),\n ]\n\n outputs = [\n Output(display_name=\"Text\", name=\"text\", method=\"parse_data\"),\n ]\n\n def parse_data(self) -> Message:\n data = self.data if isinstance(self.data, list) else [self.data]\n template = self.template\n\n result_string = data_to_text(template, data, sep=self.sep)\n self.status = result_string\n return Message(text=result_string)\n" }, "data": { "advanced": false, @@ -1649,7 +1674,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from pathlib import Path\n\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parse_text_file_to_data\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, FileInput, Output\nfrom langflow.schema import Data\n\n\nclass FileComponent(Component):\n display_name = \"File\"\n description = \"A generic file loader.\"\n icon = \"file-text\"\n name = \"File\"\n\n inputs = [\n FileInput(\n name=\"path\",\n display_name=\"Path\",\n file_types=TEXT_FILE_TYPES,\n info=f\"Supported file types: {', '.join(TEXT_FILE_TYPES)}\",\n ),\n BoolInput(\n name=\"silent_errors\",\n display_name=\"Silent Errors\",\n advanced=True,\n info=\"If true, errors will not raise an exception.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"load_file\"),\n ]\n\n def load_file(self) -> Data:\n if not self.path:\n raise ValueError(\"Please, upload a file to use this component.\")\n resolved_path = self.resolve_path(self.path)\n silent_errors = self.silent_errors\n\n extension = Path(resolved_path).suffix[1:].lower()\n\n if extension == \"doc\":\n raise ValueError(\"doc files are not supported. Please save as .docx\")\n if extension not in TEXT_FILE_TYPES:\n raise ValueError(f\"Unsupported file type: {extension}\")\n\n data = parse_text_file_to_data(resolved_path, silent_errors)\n self.status = data if data else \"No data\"\n return data or Data()\n" + "value": "from pathlib import Path\n\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parse_text_file_to_data\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, FileInput, Output\nfrom langflow.schema import Data\n\n\nclass FileComponent(Component):\n display_name = \"File\"\n description = \"A generic file loader.\"\n icon = \"file-text\"\n name = \"File\"\n\n inputs = [\n FileInput(\n name=\"path\",\n display_name=\"Path\",\n file_types=TEXT_FILE_TYPES,\n info=f\"Supported file types: {', '.join(TEXT_FILE_TYPES)}\",\n ),\n BoolInput(\n name=\"silent_errors\",\n display_name=\"Silent Errors\",\n advanced=True,\n info=\"If true, errors will not raise an exception.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"load_file\"),\n ]\n\n def load_file(self) -> Data:\n if not self.path:\n msg = \"Please, upload a file to use this component.\"\n raise ValueError(msg)\n resolved_path = self.resolve_path(self.path)\n silent_errors = self.silent_errors\n\n extension = Path(resolved_path).suffix[1:].lower()\n\n if extension == \"doc\":\n msg = \"doc files are not supported. Please save as .docx\"\n raise ValueError(msg)\n if extension not in TEXT_FILE_TYPES:\n msg = f\"Unsupported file type: {extension}\"\n raise ValueError(msg)\n\n data = parse_text_file_to_data(resolved_path, silent_errors)\n self.status = data if data else \"No data\"\n return data or Data()\n" }, "path": { "advanced": false, @@ -1772,6 +1797,7 @@ "display_name": "Retriever", "method": "build_base_retriever", "name": "base_retriever", + "required_inputs": [], "selected": "Retriever", "types": [ "Retriever" @@ -1783,6 +1809,29 @@ "display_name": "Search Results", "method": "search_documents", "name": "search_results", + "required_inputs": [ + "api_endpoint", + "batch_size", + "bulk_delete_concurrency", + "bulk_insert_batch_concurrency", + "bulk_insert_overwrite_concurrency", + "collection_indexing_policy", + "collection_name", + "embedding", + "ingest_data", + "metadata_indexing_exclude", + "metadata_indexing_include", + "metric", + "namespace", + "number_of_results", + "pre_delete_collection", + "search_filter", + "search_input", + "search_score_threshold", + "search_type", + "setup_mode", + "token" + ], "selected": "Data", "types": [ "Data" @@ -1794,6 +1843,7 @@ "display_name": "Vector Store", "method": "cast_vector_store", "name": "vector_store", + "required_inputs": [], "selected": "VectorStore", "types": [ "VectorStore" @@ -1898,7 +1948,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import os\n\nfrom astrapy.admin import parse_api_endpoint\nfrom loguru import logger\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.helpers import docs_to_data\nfrom langflow.inputs import DictInput, FloatInput, MessageTextInput\nfrom langflow.io import (\n BoolInput,\n DataInput,\n DropdownInput,\n HandleInput,\n IntInput,\n MultilineInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.schema import Data\n\n\nclass AstraVectorStoreComponent(LCVectorStoreComponent):\n display_name: str = \"Astra DB\"\n description: str = \"Implementation of Vector Store using Astra DB with search capabilities\"\n documentation: str = \"https://docs.langflow.org/starter-projects-vector-store-rag\"\n name = \"AstraDB\"\n icon: str = \"AstraDB\"\n\n VECTORIZE_PROVIDERS_MAPPING = {\n \"Azure OpenAI\": [\"azureOpenAI\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Hugging Face - Dedicated\": [\"huggingfaceDedicated\", [\"endpoint-defined-model\"]],\n \"Hugging Face - Serverless\": [\n \"huggingface\",\n [\n \"sentence-transformers/all-MiniLM-L6-v2\",\n \"intfloat/multilingual-e5-large\",\n \"intfloat/multilingual-e5-large-instruct\",\n \"BAAI/bge-small-en-v1.5\",\n \"BAAI/bge-base-en-v1.5\",\n \"BAAI/bge-large-en-v1.5\",\n ],\n ],\n \"Jina AI\": [\n \"jinaAI\",\n [\n \"jina-embeddings-v2-base-en\",\n \"jina-embeddings-v2-base-de\",\n \"jina-embeddings-v2-base-es\",\n \"jina-embeddings-v2-base-code\",\n \"jina-embeddings-v2-base-zh\",\n ],\n ],\n \"Mistral AI\": [\"mistral\", [\"mistral-embed\"]],\n \"NVIDIA\": [\"nvidia\", [\"NV-Embed-QA\"]],\n \"OpenAI\": [\"openai\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Upstage\": [\"upstageAI\", [\"solar-embedding-1-large\"]],\n \"Voyage AI\": [\n \"voyageAI\",\n [\"voyage-large-2-instruct\", \"voyage-law-2\", \"voyage-code-2\", \"voyage-large-2\", \"voyage-2\"],\n ],\n }\n\n inputs = [\n SecretStrInput(\n name=\"token\",\n display_name=\"Astra DB Application Token\",\n info=\"Authentication token for accessing Astra DB.\",\n value=\"ASTRA_DB_APPLICATION_TOKEN\",\n required=True,\n advanced=os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\",\n ),\n SecretStrInput(\n name=\"api_endpoint\",\n display_name=\"Database\" if os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\" else \"API Endpoint\",\n info=\"API endpoint URL for the Astra DB service.\",\n value=\"ASTRA_DB_API_ENDPOINT\",\n required=True,\n ),\n StrInput(\n name=\"collection_name\",\n display_name=\"Collection Name\",\n info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n required=True,\n ),\n MultilineInput(\n name=\"search_input\",\n display_name=\"Search Input\",\n ),\n DataInput(\n name=\"ingest_data\",\n display_name=\"Ingest Data\",\n is_list=True,\n ),\n StrInput(\n name=\"namespace\",\n display_name=\"Namespace\",\n info=\"Optional namespace within Astra DB to use for the collection.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"embedding_service\",\n display_name=\"Embedding Model or Astra Vectorize\",\n info=\"Determines whether to use Astra Vectorize for the collection.\",\n options=[\"Embedding Model\", \"Astra Vectorize\"],\n real_time_refresh=True,\n value=\"Embedding Model\",\n ),\n HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ),\n DropdownInput(\n name=\"metric\",\n display_name=\"Metric\",\n info=\"Optional distance metric for vector comparisons in the vector store.\",\n options=[\"cosine\", \"dot_product\", \"euclidean\"],\n advanced=True,\n ),\n IntInput(\n name=\"batch_size\",\n display_name=\"Batch Size\",\n info=\"Optional number of data to process in a single batch.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_batch_concurrency\",\n display_name=\"Bulk Insert Batch Concurrency\",\n info=\"Optional concurrency level for bulk insert operations.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_overwrite_concurrency\",\n display_name=\"Bulk Insert Overwrite Concurrency\",\n info=\"Optional concurrency level for bulk insert operations that overwrite existing data.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_delete_concurrency\",\n display_name=\"Bulk Delete Concurrency\",\n info=\"Optional concurrency level for bulk delete operations.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"setup_mode\",\n display_name=\"Setup Mode\",\n info=\"Configuration mode for setting up the vector store, with options like 'Sync', 'Async', or 'Off'.\",\n options=[\"Sync\", \"Async\", \"Off\"],\n advanced=True,\n value=\"Sync\",\n ),\n BoolInput(\n name=\"pre_delete_collection\",\n display_name=\"Pre Delete Collection\",\n info=\"Boolean flag to determine whether to delete the collection before creating a new one.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_include\",\n display_name=\"Metadata Indexing Include\",\n info=\"Optional list of metadata fields to include in the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_exclude\",\n display_name=\"Metadata Indexing Exclude\",\n info=\"Optional list of metadata fields to exclude from the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"collection_indexing_policy\",\n display_name=\"Collection Indexing Policy\",\n info=\"Optional dictionary defining the indexing policy for the collection.\",\n advanced=True,\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Number of Results\",\n info=\"Number of results to return.\",\n advanced=True,\n value=4,\n ),\n DropdownInput(\n name=\"search_type\",\n display_name=\"Search Type\",\n info=\"Search type to use\",\n options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n value=\"Similarity\",\n advanced=True,\n ),\n FloatInput(\n name=\"search_score_threshold\",\n display_name=\"Search Score Threshold\",\n info=\"Minimum similarity score threshold for search results. (when using 'Similarity with score threshold')\",\n value=0,\n advanced=True,\n ),\n DictInput(\n name=\"search_filter\",\n display_name=\"Search Metadata Filter\",\n info=\"Optional dictionary of filters to apply to the search query.\",\n advanced=True,\n is_list=True,\n ),\n ]\n\n def insert_in_dict(self, build_config, field_name, new_parameters):\n # Insert the new key-value pair after the found key\n for new_field_name, new_parameter in new_parameters.items():\n # Get all the items as a list of tuples (key, value)\n items = list(build_config.items())\n\n # Find the index of the key to insert after\n for i, (key, value) in enumerate(items):\n if key == field_name:\n break\n\n items.insert(i + 1, (new_field_name, new_parameter))\n\n # Clear the original dictionary and update with the modified items\n build_config.clear()\n build_config.update(items)\n\n return build_config\n\n def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n if field_name == \"embedding_service\":\n if field_value == \"Astra Vectorize\":\n for field in [\"embedding\"]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = DropdownInput(\n name=\"provider\",\n display_name=\"Vectorize Provider\",\n options=self.VECTORIZE_PROVIDERS_MAPPING.keys(),\n value=\"\",\n required=True,\n real_time_refresh=True,\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"provider\": new_parameter})\n else:\n for field in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"embedding\": new_parameter})\n\n elif field_name == \"provider\":\n for field in [\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n model_options = self.VECTORIZE_PROVIDERS_MAPPING[field_value][1]\n\n new_parameter_0 = DropdownInput(\n name=\"z_00_model_name\",\n display_name=\"Model Name\",\n info=f\"The embedding model to use for the selected provider. Each provider has a different set of models \"\n f\"available (full list at https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html):\\n\\n{', '.join(model_options)}\",\n options=model_options,\n required=True,\n ).to_dict()\n\n new_parameter_1 = DictInput(\n name=\"z_01_model_parameters\",\n display_name=\"Model Parameters\",\n is_list=True,\n ).to_dict()\n\n new_parameter_2 = MessageTextInput(\n name=\"z_02_api_key_name\",\n display_name=\"API Key name\",\n info=\"The name of the embeddings provider API key stored on Astra. If set, it will override the 'ProviderKey' in the authentication parameters.\",\n ).to_dict()\n\n new_parameter_3 = SecretStrInput(\n name=\"z_03_provider_api_key\",\n display_name=\"Provider API Key\",\n info=\"An alternative to the Astra Authentication that passes an API key for the provider with each request to Astra DB. This may be used when Vectorize is configured for the collection, but no corresponding provider secret is stored within Astra's key management system.\",\n ).to_dict()\n\n new_parameter_4 = DictInput(\n name=\"z_04_authentication\",\n display_name=\"Authentication parameters\",\n is_list=True,\n ).to_dict()\n\n self.insert_in_dict(\n build_config,\n \"provider\",\n {\n \"z_00_model_name\": new_parameter_0,\n \"z_01_model_parameters\": new_parameter_1,\n \"z_02_api_key_name\": new_parameter_2,\n \"z_03_provider_api_key\": new_parameter_3,\n \"z_04_authentication\": new_parameter_4,\n },\n )\n\n return build_config\n\n def build_vectorize_options(self, **kwargs):\n for attribute in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if not hasattr(self, attribute):\n setattr(self, attribute, None)\n\n # Fetch values from kwargs if any self.* attributes are None\n provider_value = self.VECTORIZE_PROVIDERS_MAPPING.get(self.provider, [None])[0] or kwargs.get(\"provider\")\n authentication = {**(self.z_04_authentication or kwargs.get(\"z_04_authentication\", {}))}\n\n api_key_name = self.z_02_api_key_name or kwargs.get(\"z_02_api_key_name\")\n provider_key = self.z_03_provider_api_key or kwargs.get(\"z_03_provider_api_key\")\n if api_key_name:\n authentication[\"providerKey\"] = api_key_name\n\n return {\n # must match astrapy.info.CollectionVectorServiceOptions\n \"collection_vector_service_options\": {\n \"provider\": provider_value,\n \"modelName\": self.z_00_model_name or kwargs.get(\"z_00_model_name\"),\n \"authentication\": authentication,\n \"parameters\": self.z_01_model_parameters or kwargs.get(\"z_01_model_parameters\", {}),\n },\n \"collection_embedding_api_key\": provider_key,\n }\n\n @check_cached_vector_store\n def build_vector_store(self, vectorize_options=None):\n try:\n from langchain_astradb import AstraDBVectorStore\n from langchain_astradb.utils.astradb import SetupMode\n except ImportError:\n raise ImportError(\n \"Could not import langchain Astra DB integration package. \"\n \"Please install it with `pip install langchain-astradb`.\"\n )\n\n try:\n if not self.setup_mode:\n self.setup_mode = self._inputs[\"setup_mode\"].options[0]\n\n setup_mode_value = SetupMode[self.setup_mode.upper()]\n except KeyError:\n raise ValueError(f\"Invalid setup mode: {self.setup_mode}\")\n\n if self.embedding:\n embedding_dict = {\"embedding\": self.embedding}\n else:\n from astrapy.info import CollectionVectorServiceOptions\n\n dict_options = vectorize_options or self.build_vectorize_options()\n dict_options[\"authentication\"] = {\n k: v for k, v in dict_options.get(\"authentication\", {}).items() if k and v\n }\n dict_options[\"parameters\"] = {k: v for k, v in dict_options.get(\"parameters\", {}).items() if k and v}\n\n embedding_dict = {\n \"collection_vector_service_options\": CollectionVectorServiceOptions.from_dict(\n dict_options.get(\"collection_vector_service_options\", {})\n ),\n }\n\n vector_store_kwargs = {\n **embedding_dict,\n \"collection_name\": self.collection_name,\n \"token\": self.token,\n \"api_endpoint\": self.api_endpoint,\n \"namespace\": self.namespace or None,\n \"environment\": parse_api_endpoint(self.api_endpoint).environment,\n \"metric\": self.metric or None,\n \"batch_size\": self.batch_size or None,\n \"bulk_insert_batch_concurrency\": self.bulk_insert_batch_concurrency or None,\n \"bulk_insert_overwrite_concurrency\": self.bulk_insert_overwrite_concurrency or None,\n \"bulk_delete_concurrency\": self.bulk_delete_concurrency or None,\n \"setup_mode\": setup_mode_value,\n \"pre_delete_collection\": self.pre_delete_collection or False,\n }\n\n if self.metadata_indexing_include:\n vector_store_kwargs[\"metadata_indexing_include\"] = self.metadata_indexing_include\n elif self.metadata_indexing_exclude:\n vector_store_kwargs[\"metadata_indexing_exclude\"] = self.metadata_indexing_exclude\n elif self.collection_indexing_policy:\n vector_store_kwargs[\"collection_indexing_policy\"] = self.collection_indexing_policy\n\n try:\n vector_store = AstraDBVectorStore(**vector_store_kwargs)\n except Exception as e:\n raise ValueError(f\"Error initializing AstraDBVectorStore: {str(e)}\") from e\n\n self._add_documents_to_vector_store(vector_store)\n\n return vector_store\n\n def _add_documents_to_vector_store(self, vector_store):\n documents = []\n for _input in self.ingest_data or []:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n raise ValueError(\"Vector Store Inputs must be Data objects.\")\n\n if documents:\n logger.debug(f\"Adding {len(documents)} documents to the Vector Store.\")\n try:\n vector_store.add_documents(documents)\n except Exception as e:\n raise ValueError(f\"Error adding documents to AstraDBVectorStore: {str(e)}\") from e\n else:\n logger.debug(\"No documents to add to the Vector Store.\")\n\n def _map_search_type(self):\n if self.search_type == \"Similarity with score threshold\":\n return \"similarity_score_threshold\"\n elif self.search_type == \"MMR (Max Marginal Relevance)\":\n return \"mmr\"\n else:\n return \"similarity\"\n\n def _build_search_args(self):\n args = {\n \"k\": self.number_of_results,\n \"score_threshold\": self.search_score_threshold,\n }\n\n if self.search_filter:\n clean_filter = {k: v for k, v in self.search_filter.items() if k and v}\n if len(clean_filter) > 0:\n args[\"filter\"] = clean_filter\n return args\n\n def search_documents(self, vector_store=None) -> list[Data]:\n if not vector_store:\n vector_store = self.build_vector_store()\n\n logger.debug(f\"Search input: {self.search_input}\")\n logger.debug(f\"Search type: {self.search_type}\")\n logger.debug(f\"Number of results: {self.number_of_results}\")\n\n if self.search_input and isinstance(self.search_input, str) and self.search_input.strip():\n try:\n search_type = self._map_search_type()\n search_args = self._build_search_args()\n\n docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)\n except Exception as e:\n raise ValueError(f\"Error performing search in AstraDBVectorStore: {str(e)}\") from e\n\n logger.debug(f\"Retrieved documents: {len(docs)}\")\n\n data = docs_to_data(docs)\n logger.debug(f\"Converted documents to data: {len(data)}\")\n self.status = data\n return data\n else:\n logger.debug(\"No search input provided. Skipping search.\")\n return []\n\n def get_retriever_kwargs(self):\n search_args = self._build_search_args()\n return {\n \"search_type\": self._map_search_type(),\n \"search_kwargs\": search_args,\n }\n" + "value": "import os\n\nfrom astrapy.admin import parse_api_endpoint\nfrom loguru import logger\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.helpers import docs_to_data\nfrom langflow.inputs import DictInput, FloatInput, MessageTextInput\nfrom langflow.io import (\n BoolInput,\n DataInput,\n DropdownInput,\n HandleInput,\n IntInput,\n MultilineInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.schema import Data\n\n\nclass AstraVectorStoreComponent(LCVectorStoreComponent):\n display_name: str = \"Astra DB\"\n description: str = \"Implementation of Vector Store using Astra DB with search capabilities\"\n documentation: str = \"https://docs.langflow.org/starter-projects-vector-store-rag\"\n name = \"AstraDB\"\n icon: str = \"AstraDB\"\n\n VECTORIZE_PROVIDERS_MAPPING = {\n \"Azure OpenAI\": [\"azureOpenAI\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Hugging Face - Dedicated\": [\"huggingfaceDedicated\", [\"endpoint-defined-model\"]],\n \"Hugging Face - Serverless\": [\n \"huggingface\",\n [\n \"sentence-transformers/all-MiniLM-L6-v2\",\n \"intfloat/multilingual-e5-large\",\n \"intfloat/multilingual-e5-large-instruct\",\n \"BAAI/bge-small-en-v1.5\",\n \"BAAI/bge-base-en-v1.5\",\n \"BAAI/bge-large-en-v1.5\",\n ],\n ],\n \"Jina AI\": [\n \"jinaAI\",\n [\n \"jina-embeddings-v2-base-en\",\n \"jina-embeddings-v2-base-de\",\n \"jina-embeddings-v2-base-es\",\n \"jina-embeddings-v2-base-code\",\n \"jina-embeddings-v2-base-zh\",\n ],\n ],\n \"Mistral AI\": [\"mistral\", [\"mistral-embed\"]],\n \"NVIDIA\": [\"nvidia\", [\"NV-Embed-QA\"]],\n \"OpenAI\": [\"openai\", [\"text-embedding-3-small\", \"text-embedding-3-large\", \"text-embedding-ada-002\"]],\n \"Upstage\": [\"upstageAI\", [\"solar-embedding-1-large\"]],\n \"Voyage AI\": [\n \"voyageAI\",\n [\"voyage-large-2-instruct\", \"voyage-law-2\", \"voyage-code-2\", \"voyage-large-2\", \"voyage-2\"],\n ],\n }\n\n inputs = [\n SecretStrInput(\n name=\"token\",\n display_name=\"Astra DB Application Token\",\n info=\"Authentication token for accessing Astra DB.\",\n value=\"ASTRA_DB_APPLICATION_TOKEN\",\n required=True,\n advanced=os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\",\n ),\n SecretStrInput(\n name=\"api_endpoint\",\n display_name=\"Database\" if os.getenv(\"ASTRA_ENHANCED\", \"false\").lower() == \"true\" else \"API Endpoint\",\n info=\"API endpoint URL for the Astra DB service.\",\n value=\"ASTRA_DB_API_ENDPOINT\",\n required=True,\n ),\n StrInput(\n name=\"collection_name\",\n display_name=\"Collection Name\",\n info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n required=True,\n ),\n MultilineInput(\n name=\"search_input\",\n display_name=\"Search Input\",\n ),\n DataInput(\n name=\"ingest_data\",\n display_name=\"Ingest Data\",\n is_list=True,\n ),\n StrInput(\n name=\"namespace\",\n display_name=\"Namespace\",\n info=\"Optional namespace within Astra DB to use for the collection.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"embedding_service\",\n display_name=\"Embedding Model or Astra Vectorize\",\n info=\"Determines whether to use Astra Vectorize for the collection.\",\n options=[\"Embedding Model\", \"Astra Vectorize\"],\n real_time_refresh=True,\n value=\"Embedding Model\",\n ),\n HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ),\n DropdownInput(\n name=\"metric\",\n display_name=\"Metric\",\n info=\"Optional distance metric for vector comparisons in the vector store.\",\n options=[\"cosine\", \"dot_product\", \"euclidean\"],\n advanced=True,\n ),\n IntInput(\n name=\"batch_size\",\n display_name=\"Batch Size\",\n info=\"Optional number of data to process in a single batch.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_batch_concurrency\",\n display_name=\"Bulk Insert Batch Concurrency\",\n info=\"Optional concurrency level for bulk insert operations.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_insert_overwrite_concurrency\",\n display_name=\"Bulk Insert Overwrite Concurrency\",\n info=\"Optional concurrency level for bulk insert operations that overwrite existing data.\",\n advanced=True,\n ),\n IntInput(\n name=\"bulk_delete_concurrency\",\n display_name=\"Bulk Delete Concurrency\",\n info=\"Optional concurrency level for bulk delete operations.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"setup_mode\",\n display_name=\"Setup Mode\",\n info=\"Configuration mode for setting up the vector store, with options like 'Sync', 'Async', or 'Off'.\",\n options=[\"Sync\", \"Async\", \"Off\"],\n advanced=True,\n value=\"Sync\",\n ),\n BoolInput(\n name=\"pre_delete_collection\",\n display_name=\"Pre Delete Collection\",\n info=\"Boolean flag to determine whether to delete the collection before creating a new one.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_include\",\n display_name=\"Metadata Indexing Include\",\n info=\"Optional list of metadata fields to include in the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"metadata_indexing_exclude\",\n display_name=\"Metadata Indexing Exclude\",\n info=\"Optional list of metadata fields to exclude from the indexing.\",\n advanced=True,\n ),\n StrInput(\n name=\"collection_indexing_policy\",\n display_name=\"Collection Indexing Policy\",\n info=\"Optional dictionary defining the indexing policy for the collection.\",\n advanced=True,\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Number of Results\",\n info=\"Number of results to return.\",\n advanced=True,\n value=4,\n ),\n DropdownInput(\n name=\"search_type\",\n display_name=\"Search Type\",\n info=\"Search type to use\",\n options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n value=\"Similarity\",\n advanced=True,\n ),\n FloatInput(\n name=\"search_score_threshold\",\n display_name=\"Search Score Threshold\",\n info=\"Minimum similarity score threshold for search results. \"\n \"(when using 'Similarity with score threshold')\",\n value=0,\n advanced=True,\n ),\n DictInput(\n name=\"search_filter\",\n display_name=\"Search Metadata Filter\",\n info=\"Optional dictionary of filters to apply to the search query.\",\n advanced=True,\n is_list=True,\n ),\n ]\n\n def insert_in_dict(self, build_config, field_name, new_parameters):\n # Insert the new key-value pair after the found key\n for new_field_name, new_parameter in new_parameters.items():\n # Get all the items as a list of tuples (key, value)\n items = list(build_config.items())\n\n # Find the index of the key to insert after\n for i, (key, value) in enumerate(items):\n if key == field_name:\n break\n\n items.insert(i + 1, (new_field_name, new_parameter))\n\n # Clear the original dictionary and update with the modified items\n build_config.clear()\n build_config.update(items)\n\n return build_config\n\n def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n if field_name == \"embedding_service\":\n if field_value == \"Astra Vectorize\":\n for field in [\"embedding\"]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = DropdownInput(\n name=\"provider\",\n display_name=\"Vectorize Provider\",\n options=self.VECTORIZE_PROVIDERS_MAPPING.keys(),\n value=\"\",\n required=True,\n real_time_refresh=True,\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"provider\": new_parameter})\n else:\n for field in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n new_parameter = HandleInput(\n name=\"embedding\",\n display_name=\"Embedding Model\",\n input_types=[\"Embeddings\"],\n info=\"Allows an embedding model configuration.\",\n ).to_dict()\n\n self.insert_in_dict(build_config, \"embedding_service\", {\"embedding\": new_parameter})\n\n elif field_name == \"provider\":\n for field in [\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if field in build_config:\n del build_config[field]\n\n model_options = self.VECTORIZE_PROVIDERS_MAPPING[field_value][1]\n\n new_parameter_0 = DropdownInput(\n name=\"z_00_model_name\",\n display_name=\"Model Name\",\n info=\"The embedding model to use for the selected provider. Each provider has a different set of \"\n \"models available (full list at \"\n \"https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html):\\n\\n\"\n f\"{', '.join(model_options)}\",\n options=model_options,\n required=True,\n ).to_dict()\n\n new_parameter_1 = DictInput(\n name=\"z_01_model_parameters\",\n display_name=\"Model Parameters\",\n is_list=True,\n ).to_dict()\n\n new_parameter_2 = MessageTextInput(\n name=\"z_02_api_key_name\",\n display_name=\"API Key name\",\n info=\"The name of the embeddings provider API key stored on Astra. \"\n \"If set, it will override the 'ProviderKey' in the authentication parameters.\",\n ).to_dict()\n\n new_parameter_3 = SecretStrInput(\n name=\"z_03_provider_api_key\",\n display_name=\"Provider API Key\",\n info=\"An alternative to the Astra Authentication that passes an API key for the provider \"\n \"with each request to Astra DB. \"\n \"This may be used when Vectorize is configured for the collection, \"\n \"but no corresponding provider secret is stored within Astra's key management system.\",\n ).to_dict()\n\n new_parameter_4 = DictInput(\n name=\"z_04_authentication\",\n display_name=\"Authentication parameters\",\n is_list=True,\n ).to_dict()\n\n self.insert_in_dict(\n build_config,\n \"provider\",\n {\n \"z_00_model_name\": new_parameter_0,\n \"z_01_model_parameters\": new_parameter_1,\n \"z_02_api_key_name\": new_parameter_2,\n \"z_03_provider_api_key\": new_parameter_3,\n \"z_04_authentication\": new_parameter_4,\n },\n )\n\n return build_config\n\n def build_vectorize_options(self, **kwargs):\n for attribute in [\n \"provider\",\n \"z_00_model_name\",\n \"z_01_model_parameters\",\n \"z_02_api_key_name\",\n \"z_03_provider_api_key\",\n \"z_04_authentication\",\n ]:\n if not hasattr(self, attribute):\n setattr(self, attribute, None)\n\n # Fetch values from kwargs if any self.* attributes are None\n provider_value = self.VECTORIZE_PROVIDERS_MAPPING.get(self.provider, [None])[0] or kwargs.get(\"provider\")\n authentication = {**(self.z_04_authentication or kwargs.get(\"z_04_authentication\", {}))}\n\n api_key_name = self.z_02_api_key_name or kwargs.get(\"z_02_api_key_name\")\n provider_key = self.z_03_provider_api_key or kwargs.get(\"z_03_provider_api_key\")\n if api_key_name:\n authentication[\"providerKey\"] = api_key_name\n\n return {\n # must match astrapy.info.CollectionVectorServiceOptions\n \"collection_vector_service_options\": {\n \"provider\": provider_value,\n \"modelName\": self.z_00_model_name or kwargs.get(\"z_00_model_name\"),\n \"authentication\": authentication,\n \"parameters\": self.z_01_model_parameters or kwargs.get(\"z_01_model_parameters\", {}),\n },\n \"collection_embedding_api_key\": provider_key,\n }\n\n @check_cached_vector_store\n def build_vector_store(self, vectorize_options=None):\n try:\n from langchain_astradb import AstraDBVectorStore\n from langchain_astradb.utils.astradb import SetupMode\n except ImportError:\n msg = (\n \"Could not import langchain Astra DB integration package. \"\n \"Please install it with `pip install langchain-astradb`.\"\n )\n raise ImportError(msg)\n\n try:\n if not self.setup_mode:\n self.setup_mode = self._inputs[\"setup_mode\"].options[0]\n\n setup_mode_value = SetupMode[self.setup_mode.upper()]\n except KeyError:\n msg = f\"Invalid setup mode: {self.setup_mode}\"\n raise ValueError(msg)\n\n if self.embedding:\n embedding_dict = {\"embedding\": self.embedding}\n else:\n from astrapy.info import CollectionVectorServiceOptions\n\n dict_options = vectorize_options or self.build_vectorize_options()\n dict_options[\"authentication\"] = {\n k: v for k, v in dict_options.get(\"authentication\", {}).items() if k and v\n }\n dict_options[\"parameters\"] = {k: v for k, v in dict_options.get(\"parameters\", {}).items() if k and v}\n\n embedding_dict = {\n \"collection_vector_service_options\": CollectionVectorServiceOptions.from_dict(\n dict_options.get(\"collection_vector_service_options\", {})\n ),\n }\n\n vector_store_kwargs = {\n **embedding_dict,\n \"collection_name\": self.collection_name,\n \"token\": self.token,\n \"api_endpoint\": self.api_endpoint,\n \"namespace\": self.namespace or None,\n \"environment\": parse_api_endpoint(self.api_endpoint).environment,\n \"metric\": self.metric or None,\n \"batch_size\": self.batch_size or None,\n \"bulk_insert_batch_concurrency\": self.bulk_insert_batch_concurrency or None,\n \"bulk_insert_overwrite_concurrency\": self.bulk_insert_overwrite_concurrency or None,\n \"bulk_delete_concurrency\": self.bulk_delete_concurrency or None,\n \"setup_mode\": setup_mode_value,\n \"pre_delete_collection\": self.pre_delete_collection or False,\n }\n\n if self.metadata_indexing_include:\n vector_store_kwargs[\"metadata_indexing_include\"] = self.metadata_indexing_include\n elif self.metadata_indexing_exclude:\n vector_store_kwargs[\"metadata_indexing_exclude\"] = self.metadata_indexing_exclude\n elif self.collection_indexing_policy:\n vector_store_kwargs[\"collection_indexing_policy\"] = self.collection_indexing_policy\n\n try:\n vector_store = AstraDBVectorStore(**vector_store_kwargs)\n except Exception as e:\n msg = f\"Error initializing AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n\n self._add_documents_to_vector_store(vector_store)\n\n return vector_store\n\n def _add_documents_to_vector_store(self, vector_store):\n documents = []\n for _input in self.ingest_data or []:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n msg = \"Vector Store Inputs must be Data objects.\"\n raise ValueError(msg)\n\n if documents:\n logger.debug(f\"Adding {len(documents)} documents to the Vector Store.\")\n try:\n vector_store.add_documents(documents)\n except Exception as e:\n msg = f\"Error adding documents to AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n else:\n logger.debug(\"No documents to add to the Vector Store.\")\n\n def _map_search_type(self):\n if self.search_type == \"Similarity with score threshold\":\n return \"similarity_score_threshold\"\n if self.search_type == \"MMR (Max Marginal Relevance)\":\n return \"mmr\"\n return \"similarity\"\n\n def _build_search_args(self):\n args = {\n \"k\": self.number_of_results,\n \"score_threshold\": self.search_score_threshold,\n }\n\n if self.search_filter:\n clean_filter = {k: v for k, v in self.search_filter.items() if k and v}\n if len(clean_filter) > 0:\n args[\"filter\"] = clean_filter\n return args\n\n def search_documents(self, vector_store=None) -> list[Data]:\n if not vector_store:\n vector_store = self.build_vector_store()\n\n logger.debug(f\"Search input: {self.search_input}\")\n logger.debug(f\"Search type: {self.search_type}\")\n logger.debug(f\"Number of results: {self.number_of_results}\")\n\n if self.search_input and isinstance(self.search_input, str) and self.search_input.strip():\n try:\n search_type = self._map_search_type()\n search_args = self._build_search_args()\n\n docs = vector_store.search(query=self.search_input, search_type=search_type, **search_args)\n except Exception as e:\n msg = f\"Error performing search in AstraDBVectorStore: {str(e)}\"\n raise ValueError(msg) from e\n\n logger.debug(f\"Retrieved documents: {len(docs)}\")\n\n data = docs_to_data(docs)\n logger.debug(f\"Converted documents to data: {len(data)}\")\n self.status = data\n return data\n logger.debug(\"No search input provided. Skipping search.\")\n return []\n\n def get_retriever_kwargs(self):\n search_args = self._build_search_args()\n return {\n \"search_type\": self._map_search_type(),\n \"search_kwargs\": search_args,\n }\n" }, "collection_indexing_policy": { "advanced": true, @@ -2262,6 +2312,28 @@ "display_name": "Embeddings", "method": "build_embeddings", "name": "embeddings", + "required_inputs": [ + "chunk_size", + "default_headers", + "default_query", + "deployment", + "dimensions", + "embedding_ctx_length", + "max_retries", + "model", + "model_kwargs", + "openai_api_base", + "openai_api_key", + "openai_api_type", + "openai_api_version", + "openai_organization", + "openai_proxy", + "request_timeout", + "show_progress_bar", + "skip_empty", + "tiktoken_enable", + "tiktoken_model_name" + ], "selected": "Embeddings", "types": [ "Embeddings" @@ -2323,7 +2395,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n name = \"OpenAIEmbeddings\"\n\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\", value=\"OPENAI_API_KEY\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. Only supported by certain models.\",\n advanced=True,\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n dimensions=self.dimensions or None,\n )\n" + "value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n name = \"OpenAIEmbeddings\"\n\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\", value=\"OPENAI_API_KEY\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. \"\n \"Only supported by certain models.\",\n advanced=True,\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n dimensions=self.dimensions or None,\n )\n" }, "default_headers": { "advanced": true, @@ -2716,6 +2788,28 @@ "display_name": "Embeddings", "method": "build_embeddings", "name": "embeddings", + "required_inputs": [ + "chunk_size", + "default_headers", + "default_query", + "deployment", + "dimensions", + "embedding_ctx_length", + "max_retries", + "model", + "model_kwargs", + "openai_api_base", + "openai_api_key", + "openai_api_type", + "openai_api_version", + "openai_organization", + "openai_proxy", + "request_timeout", + "show_progress_bar", + "skip_empty", + "tiktoken_enable", + "tiktoken_model_name" + ], "selected": "Embeddings", "types": [ "Embeddings" @@ -2777,7 +2871,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n name = \"OpenAIEmbeddings\"\n\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\", value=\"OPENAI_API_KEY\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. Only supported by certain models.\",\n advanced=True,\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n dimensions=self.dimensions or None,\n )\n" + "value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n name = \"OpenAIEmbeddings\"\n\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\", value=\"OPENAI_API_KEY\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. \"\n \"Only supported by certain models.\",\n advanced=True,\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n dimensions=self.dimensions or None,\n )\n" }, "default_headers": { "advanced": true, @@ -3162,6 +3256,11 @@ "display_name": "Text", "method": "text_response", "name": "text_output", + "required_inputs": [ + "input_value", + "stream", + "system_message" + ], "selected": "Message", "types": [ "Message" @@ -3173,6 +3272,17 @@ "display_name": "Language Model", "method": "build_model", "name": "model_output", + "required_inputs": [ + "api_key", + "json_mode", + "max_tokens", + "model_kwargs", + "model_name", + "openai_api_base", + "output_schema", + "seed", + "temperature" + ], "selected": "LanguageModel", "types": [ "LanguageModel" @@ -3217,7 +3327,7 @@ "show": true, "title_case": false, "type": "code", - "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return\n" + "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import OPENAI_MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.inputs import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n SecretStrInput,\n StrInput,\n)\nfrom langflow.inputs.inputs import HandleInput\n\n\nclass OpenAIModelComponent(LCModelComponent):\n display_name = \"OpenAI\"\n description = \"Generates text using OpenAI LLMs.\"\n icon = \"OpenAI\"\n name = \"OpenAIModel\"\n\n inputs = LCModelComponent._base_inputs + [\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n range_spec=RangeSpec(min=0, max=128000),\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n BoolInput(\n name=\"json_mode\",\n display_name=\"JSON Mode\",\n advanced=True,\n info=\"If True, it will output JSON regardless of passing a schema.\",\n ),\n DictInput(\n name=\"output_schema\",\n is_list=True,\n display_name=\"Schema\",\n advanced=True,\n info=\"The schema for the Output of the model. \"\n \"You must pass the word JSON in the prompt. \"\n \"If left blank, JSON mode will be disabled.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n advanced=False,\n options=OPENAI_MODEL_NAMES,\n value=OPENAI_MODEL_NAMES[0],\n ),\n StrInput(\n name=\"openai_api_base\",\n display_name=\"OpenAI API Base\",\n advanced=True,\n info=\"The base URL of the OpenAI API. \"\n \"Defaults to https://api.openai.com/v1. \"\n \"You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"The OpenAI API Key to use for the OpenAI model.\",\n advanced=False,\n value=\"OPENAI_API_KEY\",\n ),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n IntInput(\n name=\"seed\",\n display_name=\"Seed\",\n info=\"The seed controls the reproducibility of the job.\",\n advanced=True,\n value=1,\n ),\n HandleInput(\n name=\"output_parser\",\n display_name=\"Output Parser\",\n info=\"The parser to use to parse the output of the model\",\n advanced=True,\n input_types=[\"OutputParser\"],\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n # self.output_schema is a list of dictionaries\n # let's convert it to a dictionary\n output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n openai_api_key = self.api_key\n temperature = self.temperature\n model_name: str = self.model_name\n max_tokens = self.max_tokens\n model_kwargs = self.model_kwargs or {}\n openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n json_mode = bool(output_schema_dict) or self.json_mode\n seed = self.seed\n\n if openai_api_key:\n api_key = SecretStr(openai_api_key)\n else:\n api_key = None\n output = ChatOpenAI(\n max_tokens=max_tokens or None,\n model_kwargs=model_kwargs,\n model=model_name,\n base_url=openai_api_base,\n api_key=api_key,\n temperature=temperature if temperature is not None else 0.1,\n seed=seed,\n )\n if json_mode:\n if output_schema_dict:\n output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\") # type: ignore\n else:\n output = output.bind(response_format={\"type\": \"json_object\"}) # type: ignore\n\n return output # type: ignore\n\n def _get_exception_message(self, e: Exception):\n \"\"\"\n Get a message from an OpenAI exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n\n try:\n from openai import BadRequestError\n except ImportError:\n return None\n if isinstance(e, BadRequestError):\n message = e.body.get(\"message\") # type: ignore\n if message:\n return message\n return None\n" }, "input_value": { "advanced": false, diff --git a/src/backend/base/langflow/inputs/utils.py b/src/backend/base/langflow/inputs/utils.py new file mode 100644 index 000000000..e725f38d8 --- /dev/null +++ b/src/backend/base/langflow/inputs/utils.py @@ -0,0 +1,32 @@ +from typing import TYPE_CHECKING, Any + +if TYPE_CHECKING: + from langflow.inputs.inputs import InputTypes, InputTypesMap +else: + InputTypes = Any + InputTypesMap = Any + +# Lazy import for InputTypesMap +_InputTypesMap: dict[str, type["InputTypes"]] | None = None + + +def get_InputTypesMap(): + global _InputTypesMap + if _InputTypesMap is None: + from langflow.inputs.inputs import InputTypesMap + + _InputTypesMap = InputTypesMap + return _InputTypesMap + + +def instantiate_input(input_type: str, data: dict) -> InputTypes: + InputTypesMap = get_InputTypesMap() + + input_type_class = InputTypesMap.get(input_type) + if "type" in data: + # Replace with field_type + data["field_type"] = data.pop("type") + if input_type_class: + return input_type_class(**data) + msg = f"Invalid input type: {input_type}" + raise ValueError(msg) diff --git a/src/backend/base/langflow/io/schema.py b/src/backend/base/langflow/io/schema.py index 72342dccc..037cb3978 100644 --- a/src/backend/base/langflow/io/schema.py +++ b/src/backend/base/langflow/io/schema.py @@ -14,6 +14,7 @@ _convert_field_type_to_type: dict[FieldTypes, type] = { FieldTypes.TABLE: dict, FieldTypes.FILE: str, FieldTypes.PROMPT: str, + FieldTypes.OTHER: str, } if TYPE_CHECKING: @@ -30,6 +31,9 @@ def create_input_schema(inputs: list["InputTypes"]) -> type[BaseModel]: field_type = input_model.field_type if isinstance(field_type, FieldTypes): field_type = _convert_field_type_to_type[field_type] + else: + msg = f"Invalid field type: {field_type}" + raise ValueError(msg) if hasattr(input_model, "options") and isinstance(input_model.options, list) and input_model.options: literal_string = f"Literal{input_model.options}" # validate that the literal_string is a valid literal diff --git a/src/backend/base/langflow/services/settings/feature_flags.py b/src/backend/base/langflow/services/settings/feature_flags.py new file mode 100644 index 000000000..1a8dc0f7a --- /dev/null +++ b/src/backend/base/langflow/services/settings/feature_flags.py @@ -0,0 +1,11 @@ +from pydantic_settings import BaseSettings + + +class FeatureFlags(BaseSettings): + add_toolkit_output: bool = False + + class Config: + env_prefix = "LANGFLOW_FEATURE_" + + +FEATURE_FLAGS = FeatureFlags() diff --git a/src/backend/base/langflow/template/field/base.py b/src/backend/base/langflow/template/field/base.py index 904524b8a..869ea1a4e 100644 --- a/src/backend/base/langflow/template/field/base.py +++ b/src/backend/base/langflow/template/field/base.py @@ -1,16 +1,11 @@ -from collections.abc import Callable +from collections.abc import Callable # noqa: I001 from enum import Enum -from typing import Any, GenericAlias, _GenericAlias, _UnionGenericAlias # type: ignore +from typing import Any # noqa +from typing import GenericAlias # type: ignore +from typing import _GenericAlias # type: ignore +from typing import _UnionGenericAlias # type: ignore -from pydantic import ( - BaseModel, - ConfigDict, - Field, - field_serializer, - field_validator, - model_serializer, - model_validator, -) +from pydantic import BaseModel, ConfigDict, Field, field_serializer, field_validator, model_serializer, model_validator from langflow.field_typing import Text from langflow.field_typing.range_spec import RangeSpec @@ -189,6 +184,9 @@ class Output(BaseModel): cache: bool = Field(default=True) + required_inputs: list[str] | None = Field(default=None) + """List of required inputs for this output.""" + def to_dict(self): return self.model_dump(by_alias=True, exclude_none=True) diff --git a/src/backend/base/langflow/template/template/base.py b/src/backend/base/langflow/template/template/base.py index dab6aa94f..76004bd99 100644 --- a/src/backend/base/langflow/template/template/base.py +++ b/src/backend/base/langflow/template/template/base.py @@ -3,7 +3,8 @@ from typing import cast from pydantic import BaseModel, Field, model_serializer -from langflow.inputs.inputs import InputTypes, instantiate_input +from langflow.inputs.inputs import InputTypes +from langflow.inputs.utils import instantiate_input from langflow.template.field.base import Input from langflow.utils.constants import DIRECT_TYPES diff --git a/src/backend/tests/conftest.py b/src/backend/tests/conftest.py index b632d4935..ced3f5e6d 100644 --- a/src/backend/tests/conftest.py +++ b/src/backend/tests/conftest.py @@ -367,7 +367,8 @@ def added_flow_with_prompt_and_history(client, json_flow_with_prompt_and_history assert response.status_code == 201 assert response.json()["name"] == flow.name assert response.json()["data"] == flow.data - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture @@ -379,7 +380,8 @@ def added_flow_chat_input(client, json_chat_input, logged_in_headers): assert response.status_code == 201 assert response.json()["name"] == flow.name assert response.json()["data"] == flow.data - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture @@ -391,7 +393,8 @@ def added_flow_two_outputs(client, json_two_outputs, logged_in_headers): assert response.status_code == 201 assert response.json()["name"] == flow.name assert response.json()["data"] == flow.data - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture @@ -403,7 +406,8 @@ def added_vector_store(client, json_vector_store, logged_in_headers): assert response.status_code == 201 assert response.json()["name"] == vector_store.name assert response.json()["data"] == vector_store.data - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture @@ -429,7 +433,8 @@ def flow_component(client: TestClient, logged_in_headers): flow = FlowCreate(**graph_dict) response = client.post("api/v1/flows/", json=flow.model_dump(), headers=logged_in_headers) assert response.status_code == 201 - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture @@ -460,7 +465,8 @@ def get_simple_api_test(client, logged_in_headers, json_simple_api_test): flow = FlowCreate(name="Simple API Test", data=data, description="Simple API Test") response = client.post("api/v1/flows/", json=flow.model_dump(), headers=logged_in_headers) assert response.status_code == 201 - return response.json() + yield response.json() + client.delete(f"api/v1/flows/{response.json()['id']}", headers=logged_in_headers) @pytest.fixture(name="starter_project") diff --git a/src/backend/tests/unit/base/tools/test_component_tool.py b/src/backend/tests/unit/base/tools/test_component_tool.py deleted file mode 100644 index 25c547099..000000000 --- a/src/backend/tests/unit/base/tools/test_component_tool.py +++ /dev/null @@ -1,62 +0,0 @@ -import pytest - -from langflow.base.tools.component_tool import ComponentTool -from langflow.components.inputs.ChatInput import ChatInput - - -@pytest.fixture -def client(): - pass - - -def test_component_tool(): - chat_input = ChatInput() - component_tool = ComponentTool(component=chat_input) - assert component_tool.name == "ChatInput" - assert component_tool.description == chat_input.description - assert component_tool.args == { - "input_value": { - "default": "", - "description": "Message to be passed as input.", - "title": "Input Value", - "type": "string", - }, - "should_store_message": { - "default": True, - "description": "Store the message in the history.", - "title": "Should Store Message", - "type": "boolean", - }, - "sender": { - "default": "User", - "description": "Type of sender.", - "enum": ["Machine", "User"], - "title": "Sender", - "type": "string", - }, - "sender_name": { - "default": "User", - "description": "Name of the sender.", - "title": "Sender Name", - "type": "string", - }, - "session_id": { - "default": "", - "description": "The session ID of the chat. If empty, the current session ID parameter will be used.", - "title": "Session Id", - "type": "string", - }, - "files": { - "default": "", - "description": "Files to be sent with the message.", - "items": {"type": "string"}, - "title": "Files", - "type": "array", - }, - } - assert component_tool.component == chat_input - - result = component_tool.invoke(input=dict(input_value="test")) - assert isinstance(result, dict) - assert hasattr(result["message"], "get_text") - assert result["message"].get_text() == "test" diff --git a/src/backend/tests/unit/base/tools/test_component_toolkit.py b/src/backend/tests/unit/base/tools/test_component_toolkit.py new file mode 100644 index 000000000..d471355b8 --- /dev/null +++ b/src/backend/tests/unit/base/tools/test_component_toolkit.py @@ -0,0 +1,103 @@ +import os + +import pytest + +from langflow.base.tools.component_tool import ComponentToolkit +from langflow.components.agents.ToolCallingAgent import ToolCallingAgentComponent +from langflow.components.inputs.ChatInput import ChatInput +from langflow.components.models.OpenAIModel import OpenAIModelComponent +from langflow.components.outputs import ChatOutput +from langflow.graph.graph.base import Graph +from langflow.schema.message import Message +from langflow.services.settings.feature_flags import FEATURE_FLAGS + + +@pytest.fixture +def client(): + pass + + +@pytest.fixture +def add_toolkit_output(): + FEATURE_FLAGS.add_toolkit_output = True + yield + FEATURE_FLAGS.add_toolkit_output = False + + +def test_component_tool(): + chat_input = ChatInput() + component_toolkit = ComponentToolkit(component=chat_input) + component_tool = component_toolkit.get_tools()[0] + assert component_tool.name == "ChatInput-message_response" + terms = [ + "message_response", + "files", + "input_value", + "sender", + "sender_name", + "session_id", + "should_store_message", + ] + assert all(term in component_tool.description for term in terms) + assert component_tool.args == { + "input_value": { + "default": "", + "description": "Message to be passed as input.", + "title": "Input Value", + "type": "string", + }, + "should_store_message": { + "default": True, + "description": "Store the message in the history.", + "title": "Should Store Message", + "type": "boolean", + }, + "sender": { + "default": "User", + "description": "Type of sender.", + "enum": ["Machine", "User"], + "title": "Sender", + "type": "string", + }, + "sender_name": { + "default": "User", + "description": "Name of the sender.", + "title": "Sender Name", + "type": "string", + }, + "session_id": { + "default": "", + "description": "The session ID of the chat. If empty, the current session ID parameter will be used.", + "title": "Session Id", + "type": "string", + }, + "files": { + "default": "", + "description": "Files to be sent with the message.", + "items": {"type": "string"}, + "title": "Files", + "type": "array", + }, + } + assert component_toolkit.component == chat_input + + result = component_tool.invoke(input=dict(input_value="test")) + assert isinstance(result, Message) + assert result.get_text() == "test" + + +@pytest.mark.api_key_required +def test_component_tool_with_api_key(client, add_toolkit_output): + chat_output = ChatOutput() + openai_llm = OpenAIModelComponent() + openai_llm.set(api_key=os.environ["OPENAI_API_KEY"]) + tool_calling_agent = ToolCallingAgentComponent() + tool_calling_agent.set( + llm=openai_llm.build_model, tools=[chat_output], input_value="Which tools are available? Please tell its name." + ) + + g = Graph(start=tool_calling_agent, end=tool_calling_agent) + assert g is not None + results = list(g.start()) + assert len(results) == 4 + assert "message_response" in tool_calling_agent._outputs_map["response"].value.get_text() diff --git a/src/backend/tests/unit/custom/component/test_component_to_tool.py b/src/backend/tests/unit/custom/component/test_component_to_tool.py index 076240a4d..df8e7cbf7 100644 --- a/src/backend/tests/unit/custom/component/test_component_to_tool.py +++ b/src/backend/tests/unit/custom/component/test_component_to_tool.py @@ -1,3 +1,5 @@ +from collections.abc import Callable + import pytest from langflow.components.inputs.ChatInput import ChatInput @@ -8,9 +10,29 @@ def client(): pass -def test_component_to_tool(): +def test_component_to_toolkit(): chat_input = ChatInput() - tool = chat_input.to_tool() - assert tool.name == "ChatInput" - assert tool.description == "Get chat inputs from the Playground." - assert tool.component._id == chat_input._id + tools = chat_input.to_toolkit() + assert len(tools) == 1 + tool = tools[0] + + assert tool.name == "ChatInput-message_response" + terms = [ + "message_response", + "files", + "input_value", + "sender", + "sender_name", + "session_id", + "should_store_message", + ] + assert all(term in tool.description for term in terms) + + assert isinstance(tool.func, Callable) + assert tool.args_schema is not None + + +def test_component_to_tool_has_no_component_as_tool(): + chat_input = ChatInput() + tools = chat_input.to_toolkit() + assert len(tools) == 1 diff --git a/src/backend/tests/unit/custom/custom_component/test_component.py b/src/backend/tests/unit/custom/custom_component/test_component.py index d5d1821ec..be67c774d 100644 --- a/src/backend/tests/unit/custom/custom_component/test_component.py +++ b/src/backend/tests/unit/custom/custom_component/test_component.py @@ -1,9 +1,12 @@ import pytest from langflow.components.agents.CrewAIAgent import CrewAIAgentComponent +from langflow.components.agents.ToolCallingAgent import ToolCallingAgentComponent from langflow.components.helpers.SequentialTask import SequentialTaskComponent from langflow.components.inputs.ChatInput import ChatInput +from langflow.components.models.OpenAIModel import OpenAIModelComponent from langflow.components.outputs import ChatOutput +from langflow.template.field.base import Output @pytest.fixture @@ -24,3 +27,45 @@ def test_set_component(): task.set(agent=crewai_agent) assert task._edges[0]["source"] == crewai_agent._id assert crewai_agent in task._components + + +def _output_required_inputs_are_in_inputs(output: Output, inputs: list[str]): + return all(input_type in inputs for input_type in output.required_inputs) + + +def _assert_all_outputs_have_different_required_inputs(outputs: list[Output]): + required_inputs = [tuple(output.required_inputs) for output in outputs] + assert len(required_inputs) == len(set(required_inputs)), "All outputs must have different required inputs" + return True + + +def test_set_required_inputs(): + chatinput = ChatInput() + + assert all(_output_required_inputs_are_in_inputs(output, chatinput._inputs) for output in chatinput.outputs) + assert _assert_all_outputs_have_different_required_inputs(chatinput.outputs) + + +def test_set_required_inputs_various_components(): + chatinput = ChatInput() + chatoutput = ChatOutput() + task = SequentialTaskComponent() + tool_calling_agent = ToolCallingAgentComponent() + openai_component = OpenAIModelComponent() + + assert all(_output_required_inputs_are_in_inputs(output, chatinput._inputs) for output in chatinput.outputs) + assert all(_output_required_inputs_are_in_inputs(output, chatoutput._inputs) for output in chatoutput.outputs) + assert all(_output_required_inputs_are_in_inputs(output, task._inputs) for output in task.outputs) + assert all( + _output_required_inputs_are_in_inputs(output, tool_calling_agent._inputs) + for output in tool_calling_agent.outputs + ) + assert all( + _output_required_inputs_are_in_inputs(output, openai_component._inputs) for output in openai_component.outputs + ) + + assert _assert_all_outputs_have_different_required_inputs(chatinput.outputs) + assert _assert_all_outputs_have_different_required_inputs(chatoutput.outputs) + assert _assert_all_outputs_have_different_required_inputs(task.outputs) + assert _assert_all_outputs_have_different_required_inputs(tool_calling_agent.outputs) + assert _assert_all_outputs_have_different_required_inputs(openai_component.outputs) diff --git a/src/backend/tests/unit/graph/graph/test_base.py b/src/backend/tests/unit/graph/graph/test_base.py index 37dfcd401..9ca9df5bc 100644 --- a/src/backend/tests/unit/graph/graph/test_base.py +++ b/src/backend/tests/unit/graph/graph/test_base.py @@ -145,13 +145,6 @@ def test_graph_functional_start_end(): assert results[-1] == Finish() -def test_graph_set_with_invalid_component(): - chat_input = ChatInput(_id="chat_input") - chat_output = ChatOutput(input_value="test", _id="chat_output") - with pytest.raises(ValueError, match="There are multiple outputs"): - chat_output.set(sender_name=chat_input) - - @pytest.mark.skip(reason="Temporarily disabled") def test_graph_set_with_valid_component(): tool = YfinanceToolComponent() diff --git a/src/backend/tests/unit/inputs/test_inputs.py b/src/backend/tests/unit/inputs/test_inputs.py index f4057a54b..f8b7c7796 100644 --- a/src/backend/tests/unit/inputs/test_inputs.py +++ b/src/backend/tests/unit/inputs/test_inputs.py @@ -21,8 +21,8 @@ from langflow.inputs.inputs import ( SecretStrInput, StrInput, TableInput, - instantiate_input, ) +from langflow.inputs.utils import instantiate_input from langflow.schema.message import Message diff --git a/src/backend/tests/unit/io/test_io_schema.py b/src/backend/tests/unit/io/test_io_schema.py index 0a518ce43..97caead0b 100644 --- a/src/backend/tests/unit/io/test_io_schema.py +++ b/src/backend/tests/unit/io/test_io_schema.py @@ -218,18 +218,6 @@ class TestCreateInputSchema: assert field_info.description == "" # Handling invalid field types - def test_invalid_field_types_handling(self): - from langflow.inputs.inputs import StrInput - from langflow.io.schema import create_input_schema - - class InvalidFieldType: - pass - - input_instance = StrInput(name="test_field") - input_instance.field_type = InvalidFieldType() - - with pytest.raises(KeyError): - create_input_schema([input_instance]) # Handling input types with None as default value def test_none_default_value_handling(self): diff --git a/src/backend/tests/unit/test_custom_component.py b/src/backend/tests/unit/test_custom_component.py index 24eb37eec..d96f2acee 100644 --- a/src/backend/tests/unit/test_custom_component.py +++ b/src/backend/tests/unit/test_custom_component.py @@ -11,6 +11,7 @@ from langflow.custom.code_parser.code_parser import CodeParser, CodeSyntaxError from langflow.custom.custom_component.base_component import BaseComponent, ComponentCodeNullError from langflow.custom.utils import build_custom_component_template from langflow.services.database.models.flow import FlowCreate +from langflow.services.settings.feature_flags import FEATURE_FLAGS @pytest.fixture @@ -543,6 +544,14 @@ def test_custom_component_multiple_outputs(code_component_with_multiple_outputs, assert frontnd_node_dict["outputs"][0]["types"] == ["Text"] +def test_feature_flags_add_toolkit_output(active_user, code_component_with_multiple_outputs): + frontnd_node_dict, _ = build_custom_component_template(code_component_with_multiple_outputs, active_user.id) + len_outputs = len(frontnd_node_dict["outputs"]) + FEATURE_FLAGS.add_toolkit_output = True + frontnd_node_dict, _ = build_custom_component_template(code_component_with_multiple_outputs, active_user.id) + assert len(frontnd_node_dict["outputs"]) == len_outputs + 1 + + def test_custom_component_subclass_from_lctoolcomponent(): # Import LCToolComponent and create a subclass code = dedent("""