diff --git a/src/backend/base/langflow/base/models/model.py b/src/backend/base/langflow/base/models/model.py index b9afe335a..a6bfdff05 100644 --- a/src/backend/base/langflow/base/models/model.py +++ b/src/backend/base/langflow/base/models/model.py @@ -3,6 +3,7 @@ import json import warnings from abc import abstractmethod +from langchain_core.language_models import BaseChatModel from langchain_core.language_models.llms import LLM from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, SystemMessage from langchain_core.output_parsers import BaseOutputParser @@ -43,6 +44,20 @@ class LCModelComponent(Component): def _get_exception_message(self, e: Exception): return str(e) + def supports_tool_calling(self, model: LanguageModel) -> bool: + try: + # Check if the bind_tools method is the same as the base class's method + if model.bind_tools is BaseChatModel.bind_tools: + return False + + def test_tool(x: int) -> int: + return x + + model_with_tool = model.bind_tools([test_tool]) + return hasattr(model_with_tool, "tools") and len(model_with_tool.tools) > 0 + except (AttributeError, TypeError, ValueError): + return False + def _validate_outputs(self) -> None: # At least these two outputs must be defined required_output_methods = ["text_response", "build_model"] diff --git a/src/backend/base/langflow/base/models/model_input_constants.py b/src/backend/base/langflow/base/models/model_input_constants.py index dcb7bbcd6..b11eb91c8 100644 --- a/src/backend/base/langflow/base/models/model_input_constants.py +++ b/src/backend/base/langflow/base/models/model_input_constants.py @@ -28,7 +28,7 @@ def process_inputs(component_data): if isinstance(component_data, SecretStrInput): component_data.value = "" component_data.load_from_db = False - elif component_data.name == "temperature": + elif component_data.name in {"temperature", "tool_model_enabled", "base_url"}: component_data = set_advanced_true(component_data) return component_data @@ -180,3 +180,11 @@ except ImportError: MODEL_PROVIDERS = list(MODEL_PROVIDERS_DICT.keys()) ALL_PROVIDER_FIELDS: list[str] = [field for provider in MODEL_PROVIDERS_DICT.values() for field in provider["fields"]] + +MODEL_DYNAMIC_UPDATE_FIELDS = [ + "api_key", + "model", + "tool_model_enabled", + "base_url", + "model_name", +] diff --git a/src/backend/base/langflow/components/agents/agent.py b/src/backend/base/langflow/components/agents/agent.py index 8705a04a7..288861eab 100644 --- a/src/backend/base/langflow/components/agents/agent.py +++ b/src/backend/base/langflow/components/agents/agent.py @@ -3,6 +3,7 @@ from langchain_core.tools import StructuredTool from langflow.base.agents.agent import LCToolsAgentComponent from langflow.base.models.model_input_constants import ( ALL_PROVIDER_FIELDS, + MODEL_DYNAMIC_UPDATE_FIELDS, MODEL_PROVIDERS_DICT, ) from langflow.base.models.model_utils import get_model_name @@ -144,6 +145,16 @@ class AgentComponent(ToolCallingAgentComponent): model_kwargs = {input_.name: getattr(self, f"{prefix}{input_.name}") for input_ in inputs} return component.set(**model_kwargs).build_model() + def set_component_params(self, component): + provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm) + if provider_info: + inputs = provider_info.get("inputs") + prefix = provider_info.get("prefix") + model_kwargs = {input_.name: getattr(self, f"{prefix}{input_.name}") for input_ in inputs} + + return component.set(**model_kwargs) + return component + def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None: """Delete specified fields from build_config.""" for field in fields: @@ -164,7 +175,7 @@ class AgentComponent(ToolCallingAgentComponent): ) -> dotdict: # Iterate over all providers in the MODEL_PROVIDERS_DICT # Existing logic for updating build_config - if field_name == "agent_llm": + if field_name in ("agent_llm",): provider_info = MODEL_PROVIDERS_DICT.get(field_value) if provider_info: component_class = provider_info.get("component_class") @@ -233,10 +244,15 @@ class AgentComponent(ToolCallingAgentComponent): if missing_keys: msg = f"Missing required keys in build_config: {missing_keys}" raise ValueError(msg) - if isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT: + if ( + isinstance(self.agent_llm, str) + and self.agent_llm in MODEL_PROVIDERS_DICT + and field_name in MODEL_DYNAMIC_UPDATE_FIELDS + ): provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm) if provider_info: component_class = provider_info.get("component_class") + component_class = self.set_component_params(component_class) prefix = provider_info.get("prefix") if component_class and hasattr(component_class, "update_build_config"): # Call each component class's update_build_config method @@ -246,5 +262,4 @@ class AgentComponent(ToolCallingAgentComponent): build_config = await update_component_build_config( component_class, build_config, field_value, field_name ) - return build_config diff --git a/src/backend/base/langflow/components/models/anthropic.py b/src/backend/base/langflow/components/models/anthropic.py index 66886b792..b1f0a1b24 100644 --- a/src/backend/base/langflow/components/models/anthropic.py +++ b/src/backend/base/langflow/components/models/anthropic.py @@ -1,9 +1,14 @@ -from pydantic.v1 import SecretStr +from typing import Any + +import requests +from loguru import logger from langflow.base.models.anthropic_constants import ANTHROPIC_MODELS from langflow.base.models.model import LCModelComponent from langflow.field_typing import LanguageModel -from langflow.io import DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput +from langflow.field_typing.range_spec import RangeSpec +from langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput, SliderInput +from langflow.schema.dotdict import dotdict class AnthropicModelComponent(LCModelComponent): @@ -22,19 +27,42 @@ class AnthropicModelComponent(LCModelComponent): info="The maximum number of tokens to generate. Set to 0 for unlimited tokens.", ), DropdownInput( - name="model", + name="model_name", display_name="Model Name", - options=ANTHROPIC_MODELS, - info="https://python.langchain.com/docs/integrations/chat/anthropic", - value="claude-3-5-sonnet-latest", + options=[], + refresh_button=True, + real_time_refresh=True, + ), + SecretStrInput( + name="api_key", + display_name="Anthropic API Key", + info="Your Anthropic API key.", + value=None, + real_time_refresh=True, + ), + SliderInput( + name="temperature", + display_name="Temperature", + value=0.1, + info="Run inference with this temperature. Must by in the closed interval [0.0, 1.0].", + range_spec=RangeSpec(min=0, max=1, step=0.01), ), - SecretStrInput(name="anthropic_api_key", display_name="Anthropic API Key", info="Your Anthropic API key."), - FloatInput(name="temperature", display_name="Temperature", value=0.1), MessageTextInput( - name="anthropic_api_url", + name="base_url", display_name="Anthropic API URL", - advanced=True, info="Endpoint of the Anthropic API. Defaults to 'https://api.anthropic.com' if not specified.", + value="https://api.anthropic.com", + real_time_refresh=True, + ), + BoolInput( + name="tool_model_enabled", + display_name="Enable Tool Models", + info=( + "Select if you want to use models that can work with tools. If yes, only those models will be shown." + ), + advanced=False, + value=True, + real_time_refresh=True, ), MessageTextInput( name="prefill", display_name="Prefill", info="Prefill text to guide the model's response.", advanced=True @@ -47,19 +75,13 @@ class AnthropicModelComponent(LCModelComponent): except ImportError as e: msg = "langchain_anthropic is not installed. Please install it with `pip install langchain_anthropic`." raise ImportError(msg) from e - model = self.model - anthropic_api_key = self.anthropic_api_key - max_tokens = self.max_tokens - temperature = self.temperature - anthropic_api_url = self.anthropic_api_url or "https://api.anthropic.com" - try: output = ChatAnthropic( - model=model, - anthropic_api_key=(SecretStr(anthropic_api_key).get_secret_value() if anthropic_api_key else None), - max_tokens_to_sample=max_tokens, - temperature=temperature, - anthropic_api_url=anthropic_api_url, + model=self.model_name, + anthropic_api_key=self.api_key, + max_tokens_to_sample=self.max_tokens, + temperature=self.temperature, + anthropic_api_url=self.base_url, streaming=self.stream, ) except Exception as e: @@ -68,6 +90,32 @@ class AnthropicModelComponent(LCModelComponent): return output + def get_models(self, tool_model_enabled: bool | None = None) -> list[str]: + try: + import anthropic + + client = anthropic.Anthropic(api_key=self.api_key) + models = client.models.list(limit=20).data + model_ids = [model.id for model in models] + except (ImportError, ValueError, requests.exceptions.RequestException) as e: + logger.exception(f"Error getting model names: {e}") + model_ids = ANTHROPIC_MODELS + if tool_model_enabled: + try: + from langchain_anthropic.chat_models import ChatAnthropic + except ImportError as e: + msg = "langchain_anthropic is not installed. Please install it with `pip install langchain_anthropic`." + raise ImportError(msg) from e + for model in model_ids: + model_with_tool = ChatAnthropic( + model=self.model_name, + anthropic_api_key=self.api_key, + anthropic_api_url=self.base_url, + ) + if not self.supports_tool_calling(model_with_tool): + model_ids.remove(model) + return model_ids + def _get_exception_message(self, exception: Exception) -> str | None: """Get a message from an Anthropic exception. @@ -86,3 +134,19 @@ class AnthropicModelComponent(LCModelComponent): if message: return message return None + + def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None): + if field_name in ("base_url", "model_name", "tool_model_enabled", "api_key") and field_value: + try: + if len(self.api_key) != 0: + try: + ids = self.get_models(tool_model_enabled=self.tool_model_enabled) + except (ImportError, ValueError, requests.exceptions.RequestException) as e: + logger.exception(f"Error getting model names: {e}") + ids = ANTHROPIC_MODELS + build_config["model_name"]["options"] = ids + build_config["model_name"]["value"] = ids[0] + except Exception as e: + msg = f"Error getting model names: {e}" + raise ValueError(msg) from e + return build_config diff --git a/src/backend/base/langflow/components/models/groq.py b/src/backend/base/langflow/components/models/groq.py index 010221144..30fc0c078 100644 --- a/src/backend/base/langflow/components/models/groq.py +++ b/src/backend/base/langflow/components/models/groq.py @@ -1,11 +1,12 @@ import requests +from loguru import logger from pydantic.v1 import SecretStr -from typing_extensions import override from langflow.base.models.groq_constants import GROQ_MODELS from langflow.base.models.model import LCModelComponent from langflow.field_typing import LanguageModel -from langflow.io import DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput +from langflow.field_typing.range_spec import RangeSpec +from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput, SliderInput class GroqModel(LCModelComponent): @@ -16,13 +17,16 @@ class GroqModel(LCModelComponent): inputs = [ *LCModelComponent._base_inputs, - SecretStrInput(name="groq_api_key", display_name="Groq API Key", info="API key for the Groq API."), + SecretStrInput( + name="api_key", display_name="Groq API Key", info="API key for the Groq API.", real_time_refresh=True + ), MessageTextInput( - name="groq_api_base", + name="base_url", display_name="Groq API Base", info="Base URL path for API requests, leave blank if not using a proxy or service emulator.", advanced=True, value="https://api.groq.com", + real_time_refresh=True, ), IntInput( name="max_tokens", @@ -36,6 +40,13 @@ class GroqModel(LCModelComponent): info="Run inference with this temperature. Must by in the closed interval [0.0, 1.0].", value=0.1, ), + SliderInput( + name="temperature", + display_name="Temperature", + value=0.1, + info="Run inference with this temperature. Must by in the closed interval [0.0, 1.0].", + range_spec=RangeSpec(min=0, max=1, step=0.01), + ), IntInput( name="n", display_name="N", @@ -47,33 +58,65 @@ class GroqModel(LCModelComponent): name="model_name", display_name="Model", info="The name of the model to use.", - options=GROQ_MODELS, - value="llama-3.1-8b-instant", + options=[], refresh_button=True, + real_time_refresh=True, + ), + BoolInput( + name="tool_model_enabled", + display_name="Enable Tool Models", + info=( + "Select if you want to use models that can work with tools. If yes, only those models will be shown." + ), + advanced=False, + value=True, + real_time_refresh=True, ), ] - def get_models(self) -> list[str]: - api_key = self.groq_api_key - base_url = self.groq_api_base or "https://api.groq.com" - url = f"{base_url}/openai/v1/models" - - headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"} - + def get_models(self, tool_model_enabled: bool | None = None) -> list[str]: try: + url = f"{self.base_url}/openai/v1/models" + headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"} + response = requests.get(url, headers=headers, timeout=10) response.raise_for_status() model_list = response.json() - return [model["id"] for model in model_list.get("data", [])] - except requests.RequestException as e: - self.status = f"Error fetching models: {e}" - return GROQ_MODELS + model_ids = [model["id"] for model in model_list.get("data", [])] + except (ImportError, ValueError, requests.exceptions.RequestException) as e: + logger.exception(f"Error getting model names: {e}") + model_ids = GROQ_MODELS + if tool_model_enabled: + try: + from langchain_groq import ChatGroq + except ImportError as e: + msg = "langchain_groq is not installed. Please install it with `pip install langchain_groq`." + raise ImportError(msg) from e + for model in model_ids: + model_with_tool = ChatGroq( + model=model, + api_key=self.api_key, + base_url=self.base_url, + ) + if not self.supports_tool_calling(model_with_tool): + model_ids.remove(model) + return model_ids + return model_ids - @override def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None): - if field_name in {"groq_api_key", "groq_api_base", "model_name"}: - models = self.get_models() - build_config["model_name"]["options"] = models + if field_name in ("base_url", "model_name", "tool_model_enabled", "api_key") and field_value: + try: + if len(self.api_key) != 0: + try: + ids = self.get_models(tool_model_enabled=self.tool_model_enabled) + except (ImportError, ValueError, requests.exceptions.RequestException) as e: + logger.exception(f"Error getting model names: {e}") + ids = GROQ_MODELS + build_config["model_name"]["options"] = ids + build_config["model_name"]["value"] = ids[0] + except Exception as e: + msg = f"Error getting model names: {e}" + raise ValueError(msg) from e return build_config def build_model(self) -> LanguageModel: # type: ignore[type-var] @@ -83,20 +126,12 @@ class GroqModel(LCModelComponent): msg = "langchain-groq is not installed. Please install it with `pip install langchain-groq`." raise ImportError(msg) from e - groq_api_key = self.groq_api_key - model_name = self.model_name - max_tokens = self.max_tokens - temperature = self.temperature - groq_api_base = self.groq_api_base - n = self.n - stream = self.stream - return ChatGroq( - model=model_name, - max_tokens=max_tokens or None, - temperature=temperature, - base_url=groq_api_base, - n=n or 1, - api_key=SecretStr(groq_api_key).get_secret_value(), - streaming=stream, + model=self.model_name, + max_tokens=self.max_tokens or None, + temperature=self.temperature, + base_url=self.base_url, + n=self.n or 1, + api_key=SecretStr(self.api_key).get_secret_value(), + streaming=self.stream, ) diff --git a/src/backend/base/langflow/components/models/nvidia.py b/src/backend/base/langflow/components/models/nvidia.py index 89132d3c6..92b0b6043 100644 --- a/src/backend/base/langflow/components/models/nvidia.py +++ b/src/backend/base/langflow/components/models/nvidia.py @@ -2,7 +2,8 @@ from typing import Any from langflow.base.models.model import LCModelComponent from langflow.field_typing import LanguageModel -from langflow.inputs import BoolInput, DropdownInput, FloatInput, IntInput, SecretStrInput, StrInput +from langflow.field_typing.range_spec import RangeSpec +from langflow.inputs import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput, SliderInput from langflow.schema.dotdict import dotdict @@ -23,15 +24,17 @@ class NVIDIAModelComponent(LCModelComponent): name="model_name", display_name="Model Name", advanced=False, - options=["mistralai/mixtral-8x7b-instruct-v0.1"], - value="mistralai/mixtral-8x7b-instruct-v0.1", + options=[], + real_time_refresh=True, + refresh_button=True, ), - StrInput( + MessageTextInput( name="base_url", display_name="NVIDIA Base URL", value="https://integrate.api.nvidia.com/v1", refresh_button=True, info="The base URL of the NVIDIA API. Defaults to https://integrate.api.nvidia.com/v1.", + real_time_refresh=True, ), BoolInput( name="tool_model_enabled", @@ -41,15 +44,23 @@ class NVIDIAModelComponent(LCModelComponent): ), advanced=False, value=True, + real_time_refresh=True, ), SecretStrInput( - name="nvidia_api_key", + name="api_key", display_name="NVIDIA API Key", info="The NVIDIA API Key.", advanced=False, value="NVIDIA_API_KEY", + real_time_refresh=True, + ), + SliderInput( + name="temperature", + display_name="Temperature", + value=0.1, + info="Run inference with this temperature. Must by in the closed interval [0.0, 1.0].", + range_spec=RangeSpec(min=0, max=1, step=0.01), ), - FloatInput(name="temperature", display_name="Temperature", value=0.1), IntInput( name="seed", display_name="Seed", @@ -67,7 +78,7 @@ class NVIDIAModelComponent(LCModelComponent): return [model.id for model in build_model.available_models] def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None): - if field_name == "base_url" and field_value: + if field_name in ("base_url", "model_name", "tool_model_enabled", "api_key") and field_value: try: ids = self.get_models(self.tool_model_enabled) build_config["model_name"]["options"] = ids @@ -83,7 +94,7 @@ class NVIDIAModelComponent(LCModelComponent): except ImportError as e: msg = "Please install langchain-nvidia-ai-endpoints to use the NVIDIA model." raise ImportError(msg) from e - nvidia_api_key = self.nvidia_api_key + api_key = self.api_key temperature = self.temperature model_name: str = self.model_name max_tokens = self.max_tokens @@ -92,7 +103,7 @@ class NVIDIAModelComponent(LCModelComponent): max_tokens=max_tokens or None, model=model_name, base_url=self.base_url, - api_key=nvidia_api_key, + api_key=api_key, temperature=temperature or 0.1, seed=seed, ) diff --git a/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json b/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json index 7e3a27758..0171edfaf 100644 --- a/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Custom Component Maker.json @@ -1375,7 +1375,7 @@ "pinned": false, "template": { "_type": "Component", - "anthropic_api_key": { + "api_key": { "_input_type": "SecretStrInput", "advanced": false, "display_name": "Anthropic API Key", @@ -1384,19 +1384,19 @@ "input_types": [ "Message" ], - "load_from_db": false, - "name": "anthropic_api_key", + "load_from_db": true, + "name": "api_key", "password": true, "placeholder": "", + "real_time_refresh": true, "required": false, "show": true, "title_case": false, - "type": "str", - "value": "" + "type": "str" }, - "anthropic_api_url": { + "base_url": { "_input_type": "MessageTextInput", - "advanced": true, + "advanced": false, "display_name": "Anthropic API URL", "dynamic": false, "info": "Endpoint of the Anthropic API. Defaults to 'https://api.anthropic.com' if not specified.", @@ -1404,16 +1404,19 @@ "Message" ], "list": false, + "list_add_label": "Add More", "load_from_db": false, - "name": "anthropic_api_url", + "name": "base_url", "placeholder": "", + "real_time_refresh": true, "required": false, "show": true, "title_case": false, + "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", - "value": "" + "value": "https://api.anthropic.com" }, "code": { "advanced": true, @@ -1431,7 +1434,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from pydantic.v1 import SecretStr\n\nfrom langflow.base.models.anthropic_constants import ANTHROPIC_MODELS\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import LanguageModel\nfrom langflow.io import DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass AnthropicModelComponent(LCModelComponent):\n display_name = \"Anthropic\"\n description = \"Generate text using Anthropic Chat&Completion LLMs with prefill support.\"\n icon = \"Anthropic\"\n name = \"AnthropicModel\"\n\n inputs = [\n *LCModelComponent._base_inputs,\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n value=4096,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n ),\n DropdownInput(\n name=\"model\",\n display_name=\"Model Name\",\n options=ANTHROPIC_MODELS,\n info=\"https://python.langchain.com/docs/integrations/chat/anthropic\",\n value=\"claude-3-5-sonnet-latest\",\n ),\n SecretStrInput(name=\"anthropic_api_key\", display_name=\"Anthropic API Key\", info=\"Your Anthropic API key.\"),\n FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n MessageTextInput(\n name=\"anthropic_api_url\",\n display_name=\"Anthropic API URL\",\n advanced=True,\n info=\"Endpoint of the Anthropic API. Defaults to 'https://api.anthropic.com' if not specified.\",\n ),\n MessageTextInput(\n name=\"prefill\", display_name=\"Prefill\", info=\"Prefill text to guide the model's response.\", advanced=True\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n try:\n from langchain_anthropic.chat_models import ChatAnthropic\n except ImportError as e:\n msg = \"langchain_anthropic is not installed. Please install it with `pip install langchain_anthropic`.\"\n raise ImportError(msg) from e\n model = self.model\n anthropic_api_key = self.anthropic_api_key\n max_tokens = self.max_tokens\n temperature = self.temperature\n anthropic_api_url = self.anthropic_api_url or \"https://api.anthropic.com\"\n\n try:\n output = ChatAnthropic(\n model=model,\n anthropic_api_key=(SecretStr(anthropic_api_key).get_secret_value() if anthropic_api_key else None),\n max_tokens_to_sample=max_tokens,\n temperature=temperature,\n anthropic_api_url=anthropic_api_url,\n streaming=self.stream,\n )\n except Exception as e:\n msg = \"Could not connect to Anthropic API.\"\n raise ValueError(msg) from e\n\n return output\n\n def _get_exception_message(self, exception: Exception) -> str | None:\n \"\"\"Get a message from an Anthropic exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n try:\n from anthropic import BadRequestError\n except ImportError:\n return None\n if isinstance(exception, BadRequestError):\n message = exception.body.get(\"error\", {}).get(\"message\")\n if message:\n return message\n return None\n" + "value": "from typing import Any\n\nimport requests\nfrom loguru import logger\n\nfrom langflow.base.models.anthropic_constants import ANTHROPIC_MODELS\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import LanguageModel\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput, SliderInput\nfrom langflow.schema.dotdict import dotdict\n\n\nclass AnthropicModelComponent(LCModelComponent):\n display_name = \"Anthropic\"\n description = \"Generate text using Anthropic Chat&Completion LLMs with prefill support.\"\n icon = \"Anthropic\"\n name = \"AnthropicModel\"\n\n inputs = [\n *LCModelComponent._base_inputs,\n IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n advanced=True,\n value=4096,\n info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n options=[],\n refresh_button=True,\n real_time_refresh=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"Anthropic API Key\",\n info=\"Your Anthropic API key.\",\n value=None,\n real_time_refresh=True,\n ),\n SliderInput(\n name=\"temperature\",\n display_name=\"Temperature\",\n value=0.1,\n info=\"Run inference with this temperature. Must by in the closed interval [0.0, 1.0].\",\n range_spec=RangeSpec(min=0, max=1, step=0.01),\n ),\n MessageTextInput(\n name=\"base_url\",\n display_name=\"Anthropic API URL\",\n info=\"Endpoint of the Anthropic API. Defaults to 'https://api.anthropic.com' if not specified.\",\n value=\"https://api.anthropic.com\",\n real_time_refresh=True,\n ),\n BoolInput(\n name=\"tool_model_enabled\",\n display_name=\"Enable Tool Models\",\n info=(\n \"Select if you want to use models that can work with tools. If yes, only those models will be shown.\"\n ),\n advanced=False,\n value=True,\n real_time_refresh=True,\n ),\n MessageTextInput(\n name=\"prefill\", display_name=\"Prefill\", info=\"Prefill text to guide the model's response.\", advanced=True\n ),\n ]\n\n def build_model(self) -> LanguageModel: # type: ignore[type-var]\n try:\n from langchain_anthropic.chat_models import ChatAnthropic\n except ImportError as e:\n msg = \"langchain_anthropic is not installed. Please install it with `pip install langchain_anthropic`.\"\n raise ImportError(msg) from e\n try:\n output = ChatAnthropic(\n model=self.model_name,\n anthropic_api_key=self.api_key,\n max_tokens_to_sample=self.max_tokens,\n temperature=self.temperature,\n anthropic_api_url=self.base_url,\n streaming=self.stream,\n )\n except Exception as e:\n msg = \"Could not connect to Anthropic API.\"\n raise ValueError(msg) from e\n\n return output\n\n def get_models(self, tool_model_enabled: bool | None = None) -> list[str]:\n try:\n import anthropic\n\n client = anthropic.Anthropic(api_key=self.api_key)\n models = client.models.list(limit=20).data\n model_ids = [model.id for model in models]\n except (ImportError, ValueError, requests.exceptions.RequestException) as e:\n logger.exception(f\"Error getting model names: {e}\")\n model_ids = ANTHROPIC_MODELS\n if tool_model_enabled:\n try:\n from langchain_anthropic.chat_models import ChatAnthropic\n except ImportError as e:\n msg = \"langchain_anthropic is not installed. Please install it with `pip install langchain_anthropic`.\"\n raise ImportError(msg) from e\n for model in model_ids:\n model_with_tool = ChatAnthropic(\n model=self.model_name,\n anthropic_api_key=self.api_key,\n anthropic_api_url=self.base_url,\n )\n if not self.supports_tool_calling(model_with_tool):\n model_ids.remove(model)\n return model_ids\n\n def _get_exception_message(self, exception: Exception) -> str | None:\n \"\"\"Get a message from an Anthropic exception.\n\n Args:\n exception (Exception): The exception to get the message from.\n\n Returns:\n str: The message from the exception.\n \"\"\"\n try:\n from anthropic import BadRequestError\n except ImportError:\n return None\n if isinstance(exception, BadRequestError):\n message = exception.body.get(\"error\", {}).get(\"message\")\n if message:\n return message\n return None\n\n def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):\n if field_name in (\"base_url\", \"model_name\", \"tool_model_enabled\", \"api_key\") and field_value:\n try:\n if len(self.api_key) != 0:\n try:\n ids = self.get_models(tool_model_enabled=self.tool_model_enabled)\n except (ImportError, ValueError, requests.exceptions.RequestException) as e:\n logger.exception(f\"Error getting model names: {e}\")\n ids = ANTHROPIC_MODELS\n build_config[\"model_name\"][\"options\"] = ids\n build_config[\"model_name\"][\"value\"] = ids[0]\n except Exception as e:\n msg = f\"Error getting model names: {e}\"\n raise ValueError(msg) from e\n return build_config\n" }, "input_value": { "_input_type": "MessageInput", @@ -1470,31 +1473,25 @@ "type": "int", "value": 4096 }, - "model": { + "model_name": { "_input_type": "DropdownInput", "advanced": false, "combobox": false, "display_name": "Model Name", "dynamic": false, - "info": "https://python.langchain.com/docs/integrations/chat/anthropic", - "name": "model", - "options": [ - "claude-3-5-sonnet-latest", - "claude-3-5-haiku-latest", - "claude-3-opus-latest", - "claude-3-5-sonnet-20240620", - "claude-3-5-sonnet-20241022", - "claude-3-5-haiku-20241022", - "claude-3-sonnet-20240229", - "claude-3-haiku-20240307" - ], + "info": "", + "name": "model_name", + "options": [], "placeholder": "", + "real_time_refresh": true, + "refresh_button": true, "required": false, "show": true, "title_case": false, + "tool_mode": false, "trace_as_metadata": true, "type": "str", - "value": "claude-3-5-sonnet-20240620" + "value": "" }, "prefill": { "_input_type": "MessageTextInput", @@ -1559,7 +1556,7 @@ "advanced": false, "display_name": "Temperature", "dynamic": false, - "info": "", + "info": "Run inference with this temperature. Must by in the closed interval [0.0, 1.0].", "list": false, "name": "temperature", "placeholder": "", @@ -1569,6 +1566,25 @@ "trace_as_metadata": true, "type": "float", "value": 0.1 + }, + "tool_model_enabled": { + "_input_type": "BoolInput", + "advanced": false, + "display_name": "Enable Tool Models", + "dynamic": false, + "info": "Select if you want to use models that can work with tools. If yes, only those models will be shown.", + "list": false, + "list_add_label": "Add More", + "name": "tool_model_enabled", + "placeholder": "", + "real_time_refresh": true, + "required": false, + "show": true, + "title_case": false, + "tool_mode": false, + "trace_as_metadata": true, + "type": "bool", + "value": true } } }, 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 9fb42cde6..ef39a5a99 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 b4df2d8b1..4fd9ee2e2 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 35466095a..a7fa3864e 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 7f56612f3..daa608ebf 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 41b5cc28e..9c488c410 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 596ad8c38..6cff25a01 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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 428d50439..a1119bdf1 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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_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 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 == \"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 isinstance(self.agent_llm, str) and self.agent_llm in MODEL_PROVIDERS_DICT:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if provider_info:\n component_class = provider_info.get(\"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\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 = 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",