From 040a84ed521975a15f90ce83d54fa4e2a81e1578 Mon Sep 17 00:00:00 2001 From: Edwin Jose Date: Fri, 17 Jan 2025 18:12:56 -0500 Subject: [PATCH] feat: run flow component with tool mode option to run a flow as a tool (#5518) * Update calculator.py * Update json_cleaner.py * [autofix.ci] apply automated fixes * updated init * updated format format * update component sample component update * Update flow_orchestrator.py * test files tests * update in flow Orchestrator * Update flow_orchestrator.py solves issues with agents and session ids * Update flow_orchestrator.py * update to FlowOrchetstor update to FlowOrchetstor * draft Commit * updated to run_flow * updates * refactor code * [autofix.ci] apply automated fixes * default_name of tool to be the name of the flow * add tool_mode default activation * [autofix.ci] apply automated fixes * updates to build schema * [autofix.ci] apply automated fixes * update to schema and run flow * cleanup * Update run_flow.py * [autofix.ci] apply automated fixes * fix(run_flow.py): update condition to check if field_order exists in field_template for improved input validation * Update run_flow.py * [autofix.ci] apply automated fixes * debug updates * updates in flow tool outputs and tool mode * code cleanup * Update component_tool.py * Update run_flow.py * updated description added beta tag as per Simons Suggestion * [autofix.ci] apply automated fixes * Update component_tool.py * Update schema.py * [autofix.ci] apply automated fixes * feat: Add ToolModeMixin to CodeInput class * Update component.py * updated tests * [autofix.ci] apply automated fixes --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida --- src/backend/base/langflow/api/v1/endpoints.py | 2 +- .../base/langflow/base/agents/agent.py | 2 +- .../langflow/base/tools/component_tool.py | 26 ++- .../base/langflow/base/tools/run_flow.py | 216 ++++++++++++++++++ .../base/langflow/components/agents/agent.py | 3 +- .../langflow/components/logic/run_flow.py | 115 +++++----- .../custom/custom_component/component.py | 11 +- .../Instagram Copywriter.json | 2 +- .../starter_projects/Market Research.json | 2 +- .../starter_projects/Research Agent.json | 2 +- .../starter_projects/SaaS Pricing.json | 2 +- .../Sequential Tasks Agents .json | 6 +- .../starter_projects/Simple Agent.json | 2 +- .../Travel Planning Agents.json | 6 +- src/backend/base/langflow/inputs/inputs.py | 2 +- src/backend/base/langflow/io/schema.py | 49 ++++ .../base/langflow/services/tracing/schema.py | 32 +-- .../unit/base/tools/test_create_schema.py | 33 +++ .../component/test_component_to_tool.py | 4 +- .../custom_component/test_update_outputs.py | 34 +-- 20 files changed, 437 insertions(+), 114 deletions(-) create mode 100644 src/backend/base/langflow/base/tools/run_flow.py create mode 100644 src/backend/tests/unit/base/tools/test_create_schema.py diff --git a/src/backend/base/langflow/api/v1/endpoints.py b/src/backend/base/langflow/api/v1/endpoints.py index 573684dd7..4a04d8223 100644 --- a/src/backend/base/langflow/api/v1/endpoints.py +++ b/src/backend/base/langflow/api/v1/endpoints.py @@ -748,7 +748,7 @@ async def custom_component_update( ) component_node["template"] = updated_build_config if isinstance(cc_instance, Component): - cc_instance.run_and_validate_update_outputs( + await cc_instance.run_and_validate_update_outputs( frontend_node=component_node, field_name=code_request.field, field_value=code_request.field_value, diff --git a/src/backend/base/langflow/base/agents/agent.py b/src/backend/base/langflow/base/agents/agent.py index 61cf3ef9f..1d8fdc20c 100644 --- a/src/backend/base/langflow/base/agents/agent.py +++ b/src/backend/base/langflow/base/agents/agent.py @@ -233,7 +233,7 @@ class LCToolsAgentComponent(LCAgentComponent): tools_names = ", ".join([tool.name for tool in self.tools]) return tools_names - def to_toolkit(self) -> list[Tool]: + async def to_toolkit(self) -> list[Tool]: component_toolkit = _get_component_toolkit() tools_names = self._build_tools_names() agent_description = self.get_tool_description() diff --git a/src/backend/base/langflow/base/tools/component_tool.py b/src/backend/base/langflow/base/tools/component_tool.py index baba33773..bc3664e0b 100644 --- a/src/backend/base/langflow/base/tools/component_tool.py +++ b/src/backend/base/langflow/base/tools/component_tool.py @@ -11,7 +11,7 @@ from loguru import logger from pydantic import BaseModel from langflow.base.tools.constants import TOOL_OUTPUT_NAME -from langflow.io.schema import create_input_schema +from langflow.io.schema import create_input_schema, create_input_schema_from_dict from langflow.schema.data import Data from langflow.schema.message import Message @@ -25,6 +25,7 @@ if TYPE_CHECKING: from langflow.inputs.inputs import InputTypes from langflow.io import Output from langflow.schema.content_block import ContentBlock + from langflow.schema.dotdict import dotdict TOOL_TYPES_SET = {"Tool", "BaseTool", "StructuredTool"} @@ -169,7 +170,11 @@ class ComponentToolkit: self.metadata = metadata def get_tools( - self, tool_name: str | None = None, tool_description: str | None = None, callbacks: Callbacks | None = None + self, + tool_name: str | None = None, + tool_description: str | None = None, + callbacks: Callbacks | None = None, + flow_mode_inputs: list[dotdict] | None = None, ) -> list[BaseTool]: tools = [] for output in self.component.outputs: @@ -183,7 +188,12 @@ class ComponentToolkit: output_method: Callable = getattr(self.component, output.method) args_schema = None tool_mode_inputs = [_input for _input in self.component.inputs if getattr(_input, "tool_mode", False)] - if output.required_inputs: + if flow_mode_inputs: + args_schema = create_input_schema_from_dict( + inputs=flow_mode_inputs, + param_key="flow_tweak_data", + ) + elif output.required_inputs: inputs = [ self.component._inputs[input_name] for input_name in output.required_inputs @@ -239,8 +249,16 @@ class ComponentToolkit: ) if len(tools) == 1 and (tool_name or tool_description): tool = tools[0] - tool.name = tool_name or tool.name + tool.name = _format_tool_name(str(tool_name)) or tool.name tool.description = tool_description or tool.description + tool.tags = [tool.name] + elif flow_mode_inputs and (tool_name or tool_description): + for tool in tools: + tool.name = _format_tool_name(str(tool_name) + "_" + str(tool.name)) or tool.name + tool.description = ( + str(tool_description) + " Output details: " + str(tool.description) + ) or tool.description + tool.tags = [tool.name] elif tool_name or tool_description: msg = ( "When passing a tool name or description, there must be only one tool, " diff --git a/src/backend/base/langflow/base/tools/run_flow.py b/src/backend/base/langflow/base/tools/run_flow.py new file mode 100644 index 000000000..5360eedab --- /dev/null +++ b/src/backend/base/langflow/base/tools/run_flow.py @@ -0,0 +1,216 @@ +from abc import abstractmethod + +from loguru import logger + +from langflow.base.tools.constants import TOOLS_METADATA_INPUT_NAME +from langflow.custom import Component +from langflow.custom.custom_component.component import _get_component_toolkit +from langflow.field_typing import Tool +from langflow.graph.graph.base import Graph +from langflow.graph.vertex.base import Vertex +from langflow.helpers.flow import get_flow_inputs +from langflow.inputs.inputs import ( + DropdownInput, + InputTypes, + MessageInput, +) +from langflow.schema import Data, dotdict +from langflow.schema.dataframe import DataFrame +from langflow.schema.message import Message +from langflow.template import Output + + +class RunFlowBaseComponent(Component): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + self.add_tool_output = True + + _base_inputs: list[InputTypes] = [ + DropdownInput( + name="flow_name_selected", + display_name="Flow Name", + info="The name of the flow to run.", + options=[], + real_time_refresh=True, + refresh_button=True, + value=None, + ), + MessageInput( + name="session_id", + display_name="Session ID", + info="The session ID to run the flow in.", + value="", + advanced=True, + ), + ] + _base_outputs: list[Output] = [ + Output(name="flow_outputs_data", display_name="Flow Data Output", method="data_output", hidden=True), + Output( + name="flow_outputs_dataframe", display_name="Flow Dataframe Output", method="dataframe_output", hidden=True + ), + Output(name="flow_outputs_message", display_name="Flow Message Output", method="message_output"), + ] + default_keys = ["code", "_type", "flow_name_selected", "session_id"] + FLOW_INPUTS: list[dotdict] = [] + flow_tweak_data: dict = {} + + @abstractmethod + async def run_flow_with_tweaks(self) -> list[Data]: + """Run the flow with tweaks.""" + + async def data_output(self) -> Data: + """Return the data output.""" + run_outputs = await self.run_flow_with_tweaks() + first_output = run_outputs[0] + + if isinstance(first_output, Data): + return first_output + + message_data = first_output.outputs[0].results["message"].data + return Data(data=message_data) + + async def dataframe_output(self) -> DataFrame: + """Return the dataframe output.""" + run_outputs = await self.run_flow_with_tweaks() + first_output = run_outputs[0] + + if isinstance(first_output, DataFrame): + return first_output + + message_data = first_output.outputs[0].results["message"].data + return DataFrame(data=message_data if isinstance(message_data, list) else [message_data]) + + async def message_output(self) -> Message: + """Return the message output.""" + run_outputs = await self.run_flow_with_tweaks() + message_result = run_outputs[0].outputs[0].results["message"] + + if isinstance(message_result, Message): + return message_result + + if isinstance(message_result, str): + return Message(content=message_result) + + return Message(content=message_result.data["text"]) + + async def get_flow_names(self) -> list[str]: + # TODO: get flfow ID with flow name + flow_data = await self.alist_flows() + return [flow_data.data["name"] for flow_data in flow_data] + + async def get_flow(self, flow_name_selected: str) -> Data | None: + # get flow from flow id + flow_datas = await self.alist_flows() + for flow_data in flow_datas: + if flow_data.data["name"] == flow_name_selected: + return flow_data + return None + + async def get_graph(self, flow_name_selected: str | None = None) -> Graph: + if flow_name_selected: + flow_data = await self.get_flow(flow_name_selected) + if flow_data: + return Graph.from_payload(flow_data.data["data"]) + msg = "Flow not found" + raise ValueError(msg) + # Ensure a Graph is always returned or an exception is raised + msg = "No valid flow JSON or flow name selected." + raise ValueError(msg) + + def get_new_fields_from_graph(self, graph: Graph) -> list[dotdict]: + inputs = get_flow_inputs(graph) + return self.get_new_fields(inputs) + + def update_build_config_from_graph(self, build_config: dotdict, graph: Graph): + try: + # Get all inputs from the graph + new_fields = self.get_new_fields_from_graph(graph) + old_fields = self.get_old_fields(build_config, new_fields) + self.delete_fields(build_config, old_fields) + build_config = self.add_new_fields(build_config, new_fields) + + except Exception as e: + msg = "Error updating build config from graph" + logger.exception(msg) + raise RuntimeError(msg) from e + + def get_new_fields(self, inputs_vertex: list[Vertex]) -> list[dotdict]: + new_fields: list[dotdict] = [] + + for vertex in inputs_vertex: + field_template = vertex.data.get("node", {}).get("template", {}) + field_order = vertex.data.get("node", {}).get("field_order", []) + if field_order and field_template: + new_vertex_inputs = [ + dotdict( + { + **field_template[input_name], + "display_name": vertex.display_name + " - " + field_template[input_name]["display_name"], + "name": f"{vertex.id}~{input_name}", + "tool_mode": not (field_template[input_name].get("advanced", False)), + } + ) + for input_name in field_order + if input_name in field_template + ] + new_fields += new_vertex_inputs + return new_fields + + def add_new_fields(self, build_config: dotdict, new_fields: list[dotdict]) -> dotdict: + """Add new fields to the build_config.""" + for field in new_fields: + build_config[field["name"]] = field + return build_config + + def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None: + """Delete specified fields from build_config.""" + if isinstance(fields, dict): + fields = list(fields.keys()) + for field in fields: + build_config.pop(field, None) + + def get_old_fields(self, build_config: dotdict, new_fields: list[dotdict]) -> list[str]: + """Get fields that are in build_config but not in new_fields.""" + return [ + field + for field in build_config + if field not in [new_field["name"] for new_field in new_fields] + self.default_keys + ] + + async def get_required_data(self, flow_name_selected): + self.flow_data = await self.alist_flows() + for flow_data in self.flow_data: + if flow_data.data["name"] == flow_name_selected: + graph = Graph.from_payload(flow_data.data["data"]) + new_fields = self.get_new_fields_from_graph(graph) + new_fields = self.update_input_types(new_fields) + + return flow_data.data["description"], [field for field in new_fields if field.get("tool_mode") is True] + return None + + def update_input_types(self, fields: list[dotdict]) -> list[dotdict]: + for field in fields: + if isinstance(field, dict): + if field.get("input_types") is None: + field["input_types"] = [] + elif hasattr(field, "input_types") and field.input_types is None: + field.input_types = [] + return fields + + async def to_toolkit(self) -> list[Tool]: + component_toolkit = _get_component_toolkit() + flow_description, tool_mode_inputs = await self.get_required_data(self.flow_name_selected) + # # convert list of dicts to list of dotdicts + tool_mode_inputs = [dotdict(field) for field in tool_mode_inputs] + tools = component_toolkit(component=self).get_tools( + tool_name=f"{self.flow_name_selected}_tool", + tool_description=( + f"Tool designed to execute the flow '{self.flow_name_selected}'. Flow details: {flow_description}." + ), + callbacks=self.get_langchain_callbacks(), + flow_mode_inputs=tool_mode_inputs, + ) + if hasattr(self, TOOLS_METADATA_INPUT_NAME): + tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools) + # self.status = tools + return tools diff --git a/src/backend/base/langflow/components/agents/agent.py b/src/backend/base/langflow/components/agents/agent.py index 288861eab..059285800 100644 --- a/src/backend/base/langflow/components/agents/agent.py +++ b/src/backend/base/langflow/components/agents/agent.py @@ -86,7 +86,8 @@ class AgentComponent(ToolCallingAgentComponent): if not isinstance(self.tools, list): # type: ignore[has-type] self.tools = [] # Convert CurrentDateComponent to a StructuredTool - current_date_tool = CurrentDateComponent().to_toolkit()[0] + current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0) + # current_date_tool = CurrentDateComponent().to_toolkit()[0] if isinstance(current_date_tool, StructuredTool): self.tools.append(current_date_tool) else: diff --git a/src/backend/base/langflow/components/logic/run_flow.py b/src/backend/base/langflow/components/logic/run_flow.py index 02d2d1674..6e61f213a 100644 --- a/src/backend/base/langflow/components/logic/run_flow.py +++ b/src/backend/base/langflow/components/logic/run_flow.py @@ -1,74 +1,69 @@ -from typing import TYPE_CHECKING, Any +from typing import Any -from typing_extensions import override +from loguru import logger -from langflow.base.flow_processing.utils import build_data_from_run_outputs -from langflow.custom import Component -from langflow.io import DropdownInput, MessageTextInput, NestedDictInput, Output -from langflow.schema import Data, dotdict - -if TYPE_CHECKING: - from langflow.graph.schema import RunOutputs +from langflow.base.tools.run_flow import RunFlowBaseComponent +from langflow.helpers.flow import run_flow +from langflow.schema import dotdict -class RunFlowComponent(Component): +class RunFlowComponent(RunFlowBaseComponent): display_name = "Run Flow" - description = "A component to run a flow." + description = "Creates a tool component from a Flow that takes all its inputs and runs it." + beta = True name = "RunFlow" - legacy: bool = True - icon = "workflow" + icon = "Workflow" - async def get_flow_names(self) -> list[str]: - flow_data = await self.alist_flows() - return [flow_data.data["name"] for flow_data in flow_data] + inputs = RunFlowBaseComponent._base_inputs + outputs = RunFlowBaseComponent._base_outputs - @override async def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None): - if field_name == "flow_name": - build_config["flow_name"]["options"] = await self.get_flow_names() - + if field_name == "flow_name_selected": + build_config["flow_name_selected"]["options"] = await self.get_flow_names() + missing_keys = [key for key in self.default_keys if key not in build_config] + if missing_keys: + msg = f"Missing required keys in build_config: {missing_keys}" + raise ValueError(msg) + if field_value is not None: + try: + graph = await self.get_graph(field_value) + build_config = self.update_build_config_from_graph(build_config, graph) + except Exception as e: + msg = f"Error building graph for flow {field_value}" + logger.exception(msg) + raise RuntimeError(msg) from e return build_config - inputs = [ - MessageTextInput( - name="input_value", - display_name="Input Value", - info="The input value to be processed by the flow.", - ), - DropdownInput( - name="flow_name", - display_name="Flow Name", - info="The name of the flow to run.", - options=[], - refresh_button=True, - ), - NestedDictInput( - name="tweaks", - display_name="Tweaks", - info="Tweaks to apply to the flow.", - ), - ] + async def run_flow_with_tweaks(self): + tweaks: dict = {} - outputs = [ - Output(display_name="Run Outputs", name="run_outputs", method="generate_results"), - ] + flow_name_selected = self._attributes.get("flow_name_selected") + parsed_flow_tweak_data = self._attributes.get("flow_tweak_data", {}) + if not isinstance(parsed_flow_tweak_data, dict): + parsed_flow_tweak_data = parsed_flow_tweak_data.dict() - async def generate_results(self) -> list[Data]: - if "flow_name" not in self._attributes or not self._attributes["flow_name"]: - msg = "Flow name is required" - raise ValueError(msg) - flow_name = self._attributes["flow_name"] - - results: list[RunOutputs | None] = await self.run_flow( - inputs={"input_value": self.input_value}, flow_name=flow_name, tweaks=self.tweaks - ) - if isinstance(results, list): - data = [] - for result in results: - if result: - data.extend(build_data_from_run_outputs(result)) + if parsed_flow_tweak_data != {}: + for field in parsed_flow_tweak_data: + if "~" in field: + [node, name] = field.split("~") + if node not in tweaks: + tweaks[node] = {} + tweaks[node][name] = parsed_flow_tweak_data[field] else: - data = build_data_from_run_outputs()(results) - - self.status = data - return data + for field in self._attributes: + if field not in self.default_keys and "~" in field: + [node, name] = field.split("~") + if node not in tweaks: + tweaks[node] = {} + tweaks[node][name] = self._attributes[field] + # import pdb; pdb.set_trace() + return await run_flow( + inputs=None, + output_type="all", + flow_id=None, + flow_name=flow_name_selected, + tweaks=tweaks, + user_id=str(self.user_id), + # run_id=self.graph.run_id, + session_id=self.graph.session_id or self.session_id, + ) diff --git a/src/backend/base/langflow/custom/custom_component/component.py b/src/backend/base/langflow/custom/custom_component/component.py index 20e09ed4c..3d5bfc064 100644 --- a/src/backend/base/langflow/custom/custom_component/component.py +++ b/src/backend/base/langflow/custom/custom_component/component.py @@ -406,14 +406,15 @@ class Component(CustomComponent): self._validate_inputs(params) self._validate_outputs() - def run_and_validate_update_outputs(self, frontend_node: dict, field_name: str, field_value: Any): + async def run_and_validate_update_outputs(self, frontend_node: dict, field_name: str, field_value: Any): frontend_node = self.update_outputs(frontend_node, field_name, field_value) if field_name == "tool_mode" or frontend_node.get("tool_mode"): is_tool_mode = field_value or frontend_node.get("tool_mode") frontend_node["outputs"] = [self._build_tool_output()] if is_tool_mode else frontend_node["outputs"] if is_tool_mode: frontend_node.setdefault("template", {}) - frontend_node["template"][TOOLS_METADATA_INPUT_NAME] = self._build_tools_metadata_input().to_dict() + tools_metadata_input = await self._build_tools_metadata_input() + frontend_node["template"][TOOLS_METADATA_INPUT_NAME] = tools_metadata_input.to_dict() elif "template" in frontend_node: frontend_node["template"].pop(TOOLS_METADATA_INPUT_NAME, None) self.tools_metadata = frontend_node.get("template", {}).get(TOOLS_METADATA_INPUT_NAME, {}).get("value") @@ -994,7 +995,7 @@ class Component(CustomComponent): def _get_fallback_input(self, **kwargs): return Input(**kwargs) - def to_toolkit(self) -> list[Tool]: + async def to_toolkit(self) -> list[Tool]: component_toolkit = _get_component_toolkit() tools = component_toolkit(component=self).get_tools(callbacks=self.get_langchain_callbacks()) if hasattr(self, TOOLS_METADATA_INPUT_NAME): @@ -1212,8 +1213,8 @@ class Component(CustomComponent): def _build_tool_output(self) -> Output: return Output(name=TOOL_OUTPUT_NAME, display_name=TOOL_OUTPUT_DISPLAY_NAME, method="to_toolkit", types=["Tool"]) - def _build_tools_metadata_input(self): - tools = self.to_toolkit() + async def _build_tools_metadata_input(self): + tools = await self.to_toolkit() tool_data = ( self.tools_metadata if hasattr(self, TOOLS_METADATA_INPUT_NAME) diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json b/src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json index ef39a5a99..dd415970b 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json @@ -1735,7 +1735,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Market Research.json b/src/backend/base/langflow/initial_setup/starter_projects/Market Research.json index 4fd9ee2e2..b0b6f63c6 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Market Research.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Market Research.json @@ -1979,7 +1979,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json b/src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json index a7fa3864e..5cff34753 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json @@ -2226,7 +2226,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json b/src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json index daa608ebf..c316b4968 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json @@ -802,7 +802,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents .json b/src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents .json index 9c488c410..5398ac42d 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents .json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents .json @@ -747,7 +747,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", @@ -1323,7 +1323,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", @@ -3212,7 +3212,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json b/src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json index 6cff25a01..a9850b934 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json @@ -275,7 +275,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", 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 a1119bdf1..64959cfc2 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 @@ -1374,7 +1374,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", @@ -1950,7 +1950,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", @@ -2526,7 +2526,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" + "value": "from langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.io import BoolInput, DropdownInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n display_name: str = \"Agent\"\n description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n icon = \"bot\"\n beta = False\n name = \"Agent\"\n\n memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n inputs = [\n DropdownInput(\n name=\"agent_llm\",\n display_name=\"Model Provider\",\n info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"OpenAI\",\n real_time_refresh=True,\n input_types=[],\n ),\n *MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"],\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n advanced=False,\n ),\n *LCToolsAgentComponent._base_inputs,\n *memory_inputs,\n BoolInput(\n name=\"add_current_date_tool\",\n display_name=\"Current Date\",\n advanced=True,\n info=\"If true, will add a tool to the agent that returns the current date.\",\n value=True,\n ),\n ]\n outputs = [Output(name=\"response\", display_name=\"Response\", method=\"message_response\")]\n\n async def message_response(self) -> Message:\n try:\n llm_model, display_name = self.get_llm()\n if llm_model is None:\n msg = \"No language model selected\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n except Exception as e:\n # Log the error for debugging purposes\n logger.error(f\"Error retrieving language model: {e}\")\n raise\n\n try:\n self.chat_history = await self.get_memory_data()\n except Exception as e:\n logger.error(f\"Error retrieving chat history: {e}\")\n raise\n\n if self.add_current_date_tool:\n try:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n # Convert CurrentDateComponent to a StructuredTool\n current_date_tool = (await CurrentDateComponent().to_toolkit()).pop(0)\n # current_date_tool = CurrentDateComponent().to_toolkit()[0]\n if isinstance(current_date_tool, StructuredTool):\n self.tools.append(current_date_tool)\n else:\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n except Exception as e:\n logger.error(f\"Error adding current date tool: {e}\")\n raise\n\n if not self.tools:\n msg = \"Tools are required to run the agent.\"\n logger.error(msg)\n raise ValueError(msg)\n\n try:\n self.set(\n llm=llm_model,\n tools=self.tools,\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=self.system_prompt,\n )\n agent = self.create_agent_runnable()\n except Exception as e:\n logger.error(f\"Error setting up the agent: {e}\")\n raise\n\n return await self.run_agent(agent)\n\n async def get_memory_data(self):\n memory_kwargs = {\n component_input.name: getattr(self, f\"{component_input.name}\") for component_input in self.memory_inputs\n }\n\n return await MemoryComponent().set(**memory_kwargs).retrieve_messages()\n\n def get_llm(self):\n if isinstance(self.agent_llm, str):\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n display_name = component_class.display_name\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\", \"\")\n return (\n self._build_llm_model(component_class, inputs, prefix),\n display_name,\n )\n except Exception as e:\n msg = f\"Error building {self.agent_llm} language model\"\n raise ValueError(msg) from e\n return self.agent_llm, None\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n return component.set(**model_kwargs).build_model()\n\n def set_component_params(self, component):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n inputs = provider_info.get(\"inputs\")\n prefix = provider_info.get(\"prefix\")\n model_kwargs = {input_.name: getattr(self, f\"{prefix}{input_.name}\") for input_ in inputs}\n\n return component.set(**model_kwargs)\n return component\n\n def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n \"\"\"Delete specified fields from build_config.\"\"\"\n for field in fields:\n build_config.pop(field, None)\n\n def update_input_types(self, build_config: dotdict) -> dotdict:\n \"\"\"Update input types for all fields in build_config.\"\"\"\n for key, value in build_config.items():\n if isinstance(value, dict):\n if value.get(\"input_types\") is None:\n build_config[key][\"input_types\"] = []\n elif hasattr(value, \"input_types\") and value.input_types is None:\n value.input_types = []\n return build_config\n\n async def update_build_config(\n self, build_config: dotdict, field_value: str, field_name: str | None = None\n ) -> dotdict:\n # Iterate over all providers in the MODEL_PROVIDERS_DICT\n # Existing logic for updating build_config\n if field_name in (\"agent_llm\",):\n provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call the component class's update_build_config method\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n\n provider_configs: dict[str, tuple[dict, list[dict]]] = {\n provider: (\n MODEL_PROVIDERS_DICT[provider][\"fields\"],\n [\n MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n for other_provider in MODEL_PROVIDERS_DICT\n if other_provider != provider\n ],\n )\n for provider in MODEL_PROVIDERS_DICT\n }\n if field_value in provider_configs:\n fields_to_add, fields_to_delete = provider_configs[field_value]\n\n # Delete fields from other providers\n for fields in fields_to_delete:\n self.delete_fields(build_config, fields)\n\n # Add provider-specific fields\n if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n build_config.update(fields_to_add)\n else:\n build_config.update(fields_to_add)\n # Reset input types for agent_llm\n build_config[\"agent_llm\"][\"input_types\"] = []\n elif field_value == \"Custom\":\n # Delete all provider fields\n self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n # Update with custom component\n custom_component = DropdownInput(\n name=\"agent_llm\",\n display_name=\"Language Model\",\n options=[*sorted(MODEL_PROVIDERS_DICT.keys()), \"Custom\"],\n value=\"Custom\",\n real_time_refresh=True,\n input_types=[\"LanguageModel\"],\n )\n build_config.update({\"agent_llm\": custom_component.to_dict()})\n # Update input types for all fields\n build_config = self.update_input_types(build_config)\n\n # Validate required keys\n default_keys = [\n \"code\",\n \"_type\",\n \"agent_llm\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"system_prompt\",\n \"agent_description\",\n \"max_iterations\",\n \"handle_parsing_errors\",\n \"verbose\",\n ]\n missing_keys = [key for key in default_keys if key not in build_config]\n if missing_keys:\n msg = f\"Missing required keys in build_config: {missing_keys}\"\n raise ValueError(msg)\n if (\n isinstance(self.agent_llm, str)\n and self.agent_llm in MODEL_PROVIDERS_DICT\n and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n ):\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"component_class\")\n component_class = self.set_component_params(component_class)\n prefix = provider_info.get(\"prefix\")\n if component_class and hasattr(component_class, \"update_build_config\"):\n # Call each component class's update_build_config method\n # remove the prefix from the field_name\n if isinstance(field_name, str) and isinstance(prefix, str):\n field_name = field_name.replace(prefix, \"\")\n build_config = await update_component_build_config(\n component_class, build_config, field_value, field_name\n )\n return build_config\n" }, "handle_parsing_errors": { "_input_type": "BoolInput", diff --git a/src/backend/base/langflow/inputs/inputs.py b/src/backend/base/langflow/inputs/inputs.py index cc932d52a..f3f1744ab 100644 --- a/src/backend/base/langflow/inputs/inputs.py +++ b/src/backend/base/langflow/inputs/inputs.py @@ -86,7 +86,7 @@ class PromptInput(BaseInputMixin, ListableInputMixin, InputTraceMixin, ToolModeM field_type: SerializableFieldTypes = FieldTypes.PROMPT -class CodeInput(BaseInputMixin, ListableInputMixin, InputTraceMixin): +class CodeInput(BaseInputMixin, ListableInputMixin, InputTraceMixin, ToolModeMixin): field_type: SerializableFieldTypes = FieldTypes.CODE diff --git a/src/backend/base/langflow/io/schema.py b/src/backend/base/langflow/io/schema.py index 8672d9789..b92c6fe2e 100644 --- a/src/backend/base/langflow/io/schema.py +++ b/src/backend/base/langflow/io/schema.py @@ -3,6 +3,7 @@ from typing import TYPE_CHECKING, Literal from pydantic import BaseModel, Field, create_model from langflow.inputs.inputs import FieldTypes +from langflow.schema.dotdict import dotdict _convert_field_type_to_type: dict[FieldTypes, type] = { FieldTypes.TEXT: str, @@ -62,3 +63,51 @@ def create_input_schema(inputs: list["InputTypes"]) -> type[BaseModel]: model = create_model("InputSchema", **fields) model.model_rebuild() return model + + +def create_input_schema_from_dict(inputs: list[dotdict], param_key: str | None = None) -> type[BaseModel]: + if not isinstance(inputs, list): + msg = "inputs must be a list of Inputs" + raise TypeError(msg) + fields = {} + for input_model in inputs: + # Create a Pydantic Field for each input field + field_type = input_model.type + 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 + + field_type = eval(literal_string, {"Literal": Literal}) # noqa: S307 + if hasattr(input_model, "is_list") and input_model.is_list: + field_type = list[field_type] # type: ignore[valid-type] + if input_model.name: + name = input_model.name.replace("_", " ").title() + elif input_model.display_name: + name = input_model.display_name + else: + msg = "Input name or display_name is required" + raise ValueError(msg) + field_dict = { + "title": name, + "description": input_model.info or "", + } + if input_model.required is False: + field_dict["default"] = input_model.value # type: ignore[assignment] + pydantic_field = Field(**field_dict) + + fields[input_model.name] = (field_type, pydantic_field) + + # Wrap fields in a dictionary with the key as param_key + if param_key is not None: + # Create an inner model with the fields + inner_model = create_model("InnerModel", **fields) + + # Ensure the model is wrapped correctly in a dictionary + # model = create_model("InputSchema", **{param_key: (inner_model, Field(default=..., description=description))}) + model = create_model("InputSchema", **{param_key: (inner_model, ...)}) + else: + # Create and return the InputSchema model + model = create_model("InputSchema", **fields) + + model.model_rebuild() + return model diff --git a/src/backend/base/langflow/services/tracing/schema.py b/src/backend/base/langflow/services/tracing/schema.py index 30a0bc73f..4485f578c 100644 --- a/src/backend/base/langflow/services/tracing/schema.py +++ b/src/backend/base/langflow/services/tracing/schema.py @@ -1,3 +1,5 @@ +import logging + from fastapi.encoders import jsonable_encoder from pydantic import BaseModel, field_serializer from pydantic.v1 import BaseModel as V1BaseModel @@ -5,6 +7,8 @@ from pydantic_core import PydanticSerializationError from langflow.schema.log import LoggableType +logger = logging.getLogger(__name__) + class Log(BaseModel): name: str @@ -13,21 +17,23 @@ class Log(BaseModel): @field_serializer("message") def serialize_message(self, value): - # We need to make sure everything inside the message has been serialized - if isinstance(value, dict): - return {key: self.serialize_message(value[key]) for key in value} - if isinstance(value, list): - return [self.serialize_message(item) for item in value] - # To json is for LangChain Serializable objects - if hasattr(value, "dict") and isinstance(value, V1BaseModel): - # This is for Pydantic V1 models - return value.dict() - if hasattr(value, "to_json"): - return value.to_json() - if isinstance(value, BaseModel): - return value.model_dump(exclude_none=True) try: + # We need to make sure everything inside the message has been serialized + if isinstance(value, dict): + return {key: self.serialize_message(value[key]) for key in value} + if isinstance(value, list): + return [self.serialize_message(item) for item in value] + # To json is for LangChain Serializable objects + if hasattr(value, "dict") and isinstance(value, V1BaseModel): + # This is for Pydantic V1 models + return value.dict() + if hasattr(value, "to_json"): + return value.to_json() + if isinstance(value, BaseModel): + return value.model_dump(exclude_none=True) value = jsonable_encoder(value) + except UnicodeDecodeError: + return str(value) # Fallback to string representation except PydanticSerializationError: return str(value) return value diff --git a/src/backend/tests/unit/base/tools/test_create_schema.py b/src/backend/tests/unit/base/tools/test_create_schema.py new file mode 100644 index 000000000..ed421079f --- /dev/null +++ b/src/backend/tests/unit/base/tools/test_create_schema.py @@ -0,0 +1,33 @@ +from langflow.io.schema import create_input_schema_from_dict +from langflow.schema.dotdict import dotdict + + +def test_create_schema(): + sample_input = [ + { + "_input_type": "MultilineInput", + "advanced": False, + "display_name": "Chat Input - Text", + "dynamic": False, + "info": "Message to be passed as input.", + "input_types": ["Message"], + "list": False, + "load_from_db": False, + "multiline": True, + "name": "ChatInput-xNZ0a|input_value", + "placeholder": "", + "required": False, + "show": True, + "title_case": False, + "tool_mode": True, + "trace_as_input": True, + "trace_as_metadata": True, + "type": "str", + "value": "add 1+1", + } + ] + # convert to dotdict + # change the key type + sample_input = [dotdict(field) for field in sample_input] + schema = create_input_schema_from_dict(sample_input) + assert schema is not None 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 4b4caec45..ce5001c49 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 @@ -5,11 +5,11 @@ from langflow.components.agents.agent import AgentComponent from langflow.components.tools.calculator import CalculatorToolComponent -def test_component_to_toolkit(): +async def test_component_to_toolkit(): calculator_component = CalculatorToolComponent() agent_component = AgentComponent().set(tools=[calculator_component]) - tools = agent_component.to_toolkit() + tools = await agent_component.to_toolkit() assert len(tools) == 1 tool = tools[0] diff --git a/src/backend/tests/unit/custom/custom_component/test_update_outputs.py b/src/backend/tests/unit/custom/custom_component/test_update_outputs.py index 0de0de5cc..a1a7c39c3 100644 --- a/src/backend/tests/unit/custom/custom_component/test_update_outputs.py +++ b/src/backend/tests/unit/custom/custom_component/test_update_outputs.py @@ -4,7 +4,7 @@ from langflow.custom.custom_component.component import Component class TestComponentOutputs: - def test_run_and_validate_update_outputs_tool_mode(self): + async def test_run_and_validate_update_outputs_tool_mode(self): """Test run_and_validate_update_outputs with tool_mode field.""" class TestComponent(Component): @@ -33,7 +33,7 @@ class TestComponentOutputs: } # Test enabling tool mode - updated_node = component.run_and_validate_update_outputs( + updated_node = await component.run_and_validate_update_outputs( frontend_node=frontend_node.copy(), # Use a copy to avoid modifying original field_name="tool_mode", field_value=True, @@ -45,7 +45,7 @@ class TestComponentOutputs: assert updated_node["outputs"][0]["display_name"] == TOOL_OUTPUT_DISPLAY_NAME # Test disabling tool mode - use the original frontend node - updated_node = component.run_and_validate_update_outputs( + updated_node = await component.run_and_validate_update_outputs( frontend_node={"outputs": original_outputs.copy()}, # Use original outputs field_name="tool_mode", field_value=False, @@ -60,7 +60,7 @@ class TestComponentOutputs: assert "types" in updated_node["outputs"][0] assert "selected" in updated_node["outputs"][0] - def test_run_and_validate_update_outputs_invalid_output(self): + async def test_run_and_validate_update_outputs_invalid_output(self): """Test run_and_validate_update_outputs with invalid output structure.""" class TestComponent(Component): @@ -74,11 +74,11 @@ class TestComponentOutputs: # Test validation fails for invalid output with pytest.raises(ValueError, match="Invalid output: 1 validation error for Output"): - component.run_and_validate_update_outputs( + await component.run_and_validate_update_outputs( frontend_node=frontend_node, field_name="some_field", field_value="some_value" ) - def test_run_and_validate_update_outputs_custom_update(self): + async def test_run_and_validate_update_outputs_custom_update(self): """Test run_and_validate_update_outputs with custom update logic.""" class CustomComponent(Component): @@ -111,7 +111,7 @@ class TestComponentOutputs: frontend_node = {"outputs": []} # Test custom update logic - updated_node = component.run_and_validate_update_outputs( + updated_node = await component.run_and_validate_update_outputs( frontend_node=frontend_node, field_name="custom_field", field_value="custom_value" ) @@ -122,14 +122,14 @@ class TestComponentOutputs: assert "types" in updated_node["outputs"][0] assert "selected" in updated_node["outputs"][0] - def test_run_and_validate_update_outputs_with_existing_tool_output(self): + async def test_run_and_validate_update_outputs_with_existing_tool_output(self): """Test run_and_validate_update_outputs when tool output already exists.""" class TestComponent(Component): def build(self) -> None: pass - def to_toolkit(self) -> list: + async def to_toolkit(self) -> list: """Method that returns a list of tools.""" return [] @@ -154,7 +154,7 @@ class TestComponentOutputs: } # Test enabling tool mode doesn't duplicate tool output - updated_node = component.run_and_validate_update_outputs( + updated_node = await component.run_and_validate_update_outputs( frontend_node=frontend_node, field_name="tool_mode", field_value=True ) @@ -164,7 +164,7 @@ class TestComponentOutputs: assert "types" in updated_node["outputs"][0] assert "selected" in updated_node["outputs"][0] - def test_run_and_validate_update_outputs_with_multiple_outputs(self): + async def test_run_and_validate_update_outputs_with_multiple_outputs(self): """Test run_and_validate_update_outputs with multiple outputs.""" class TestComponent(Component): @@ -203,7 +203,7 @@ class TestComponentOutputs: frontend_node = {"outputs": []} # Test adding multiple outputs - updated_node = component.run_and_validate_update_outputs( + updated_node = await component.run_and_validate_update_outputs( frontend_node=frontend_node, field_name="add_output", field_value=True ) @@ -217,7 +217,7 @@ class TestComponentOutputs: assert set(output["types"]) == {"Text"} assert output["selected"] == "Text" - def test_run_and_validate_update_outputs_output_validation(self): + async def test_run_and_validate_update_outputs_output_validation(self): """Test output validation in run_and_validate_update_outputs.""" class TestComponent(Component): @@ -236,10 +236,14 @@ class TestComponentOutputs: } with pytest.raises(AttributeError, match="nonexistent_method not found in TestComponent"): - component.run_and_validate_update_outputs(frontend_node=invalid_node, field_name="test", field_value=True) + await component.run_and_validate_update_outputs( + frontend_node=invalid_node, field_name="test", field_value=True + ) # Test missing method case invalid_node = {"outputs": [{"name": "test", "type": "str", "display_name": "Test"}]} with pytest.raises(ValueError, match="Output test does not have a method"): - component.run_and_validate_update_outputs(frontend_node=invalid_node, field_name="test", field_value=True) + await component.run_and_validate_update_outputs( + frontend_node=invalid_node, field_name="test", field_value=True + )