{ "data": { "edges": [ { "animated": false, "className": "", "data": { "sourceHandle": { "dataType": "ApifyActors", "id": "ApifyActors-Zrjnz", "name": "tool", "output_types": [ "Tool" ] }, "targetHandle": { "fieldName": "tools", "id": "Agent-0vMrI", "inputTypes": [ "Tool" ], "type": "other" } }, "id": "reactflow__edge-ApifyActors-Zrjnz{œdataTypeœ:œApifyActorsœ,œidœ:œApifyActors-Zrjnzœ,œnameœ:œtoolœ,œoutput_typesœ:[œToolœ]}-Agent-0vMrI{œfieldNameœ:œtoolsœ,œidœ:œAgent-0vMrIœ,œinputTypesœ:[œToolœ],œtypeœ:œotherœ}", "selected": false, "source": "ApifyActors-Zrjnz", "sourceHandle": "{œdataTypeœ: œApifyActorsœ, œidœ: œApifyActors-Zrjnzœ, œnameœ: œtoolœ, œoutput_typesœ: [œToolœ]}", "target": "Agent-0vMrI", "targetHandle": "{œfieldNameœ: œtoolsœ, œidœ: œAgent-0vMrIœ, œinputTypesœ: [œToolœ], œtypeœ: œotherœ}" }, { "animated": false, "className": "", "data": { "sourceHandle": { "dataType": "ApifyActors", "id": "ApifyActors-8WoKJ", "name": "tool", "output_types": [ "Tool" ] }, "targetHandle": { "fieldName": "tools", "id": "Agent-0vMrI", "inputTypes": [ "Tool" ], "type": "other" } }, "id": "reactflow__edge-ApifyActors-8WoKJ{œdataTypeœ:œApifyActorsœ,œidœ:œApifyActors-8WoKJœ,œnameœ:œtoolœ,œoutput_typesœ:[œToolœ]}-Agent-0vMrI{œfieldNameœ:œtoolsœ,œidœ:œAgent-0vMrIœ,œinputTypesœ:[œToolœ],œtypeœ:œotherœ}", "selected": false, "source": "ApifyActors-8WoKJ", "sourceHandle": "{œdataTypeœ: œApifyActorsœ, œidœ: œApifyActors-8WoKJœ, œnameœ: œtoolœ, œoutput_typesœ: [œToolœ]}", "target": "Agent-0vMrI", "targetHandle": "{œfieldNameœ: œtoolsœ, œidœ: œAgent-0vMrIœ, œinputTypesœ: [œToolœ], œtypeœ: œotherœ}" }, { "animated": false, "className": "", "data": { "sourceHandle": { "dataType": "ChatInput", "id": "ChatInput-RBrnT", "name": "message", "output_types": [ "Message" ] }, "targetHandle": { "fieldName": "input_value", "id": "Agent-0vMrI", "inputTypes": [ "Message" ], "type": "str" } }, "id": "reactflow__edge-ChatInput-RBrnT{œdataTypeœ:œChatInputœ,œidœ:œChatInput-RBrnTœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-Agent-0vMrI{œfieldNameœ:œinput_valueœ,œidœ:œAgent-0vMrIœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}", "selected": false, "source": "ChatInput-RBrnT", "sourceHandle": "{œdataTypeœ: œChatInputœ, œidœ: œChatInput-RBrnTœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}", "target": "Agent-0vMrI", "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œAgent-0vMrIœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}" }, { "animated": false, "className": "", "data": { "sourceHandle": { "dataType": "Agent", "id": "Agent-0vMrI", "name": "response", "output_types": [ "Message" ] }, "targetHandle": { "fieldName": "input_value", "id": "ChatOutput-Lgpwq", "inputTypes": [ "Data", "DataFrame", "Message" ], "type": "other" } }, "id": "reactflow__edge-Agent-0vMrI{œdataTypeœ:œAgentœ,œidœ:œAgent-0vMrIœ,œnameœ:œresponseœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-Lgpwq{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-Lgpwqœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}", "selected": false, "source": "Agent-0vMrI", "sourceHandle": "{œdataTypeœ: œAgentœ, œidœ: œAgent-0vMrIœ, œnameœ: œresponseœ, œoutput_typesœ: [œMessageœ]}", "target": "ChatOutput-Lgpwq", "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-Lgpwqœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}" } ], "nodes": [ { "data": { "id": "ApifyActors-8WoKJ", "node": { "base_classes": [ "Data", "Tool" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Use Apify Actors to extract data from hundreds of places fast. This component can be used in a flow to retrieve data or as a tool with an agent.", "display_name": "Apify Actors", "documentation": "http://docs.langflow.org/integrations-apify", "edited": false, "field_order": [ "apify_token", "actor_id", "run_input", "dataset_fields", "flatten_dataset" ], "frozen": false, "icon": "Apify", "legacy": false, "lf_version": "1.4.2", "metadata": {}, "minimized": false, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Output", "hidden": null, "method": "run_model", "name": "output", "required_inputs": null, "tool_mode": true, "types": [ "Data" ], "value": "__UNDEFINED__" }, { "allows_loop": false, "cache": true, "display_name": "Tool", "hidden": null, "method": "build_tool", "name": "tool", "required_inputs": null, "selected": "Tool", "tool_mode": true, "types": [ "Tool" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "actor_id": { "_input_type": "StrInput", "advanced": false, "display_name": "Actor", "dynamic": false, "info": "Actor name from Apify store to run. For example 'apify/website-content-crawler' to use the Website Content Crawler Actor.", "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "actor_id", "placeholder": "", "required": true, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "clockworks/free-tiktok-scraper" }, "apify_token": { "_input_type": "SecretStrInput", "advanced": false, "display_name": "Apify Token", "dynamic": false, "info": "The API token for the Apify account.", "input_types": [], "load_from_db": false, "name": "apify_token", "password": true, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "str", "value": "" }, "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "import json\nimport string\nfrom typing import Any, cast\n\nfrom apify_client import ApifyClient\nfrom langchain_community.document_loaders.apify_dataset import ApifyDatasetLoader\nfrom langchain_core.tools import BaseTool\nfrom pydantic import BaseModel, Field, field_serializer\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing import Tool\nfrom langflow.inputs.inputs import BoolInput\nfrom langflow.io import MultilineInput, Output, SecretStrInput, StrInput\nfrom langflow.schema.data import Data\n\nMAX_DESCRIPTION_LEN = 250\n\n\nclass ApifyActorsComponent(Component):\n display_name = \"Apify Actors\"\n description = (\n \"Use Apify Actors to extract data from hundreds of places fast. \"\n \"This component can be used in a flow to retrieve data or as a tool with an agent.\"\n )\n documentation: str = \"http://docs.langflow.org/integrations-apify\"\n icon = \"Apify\"\n name = \"ApifyActors\"\n\n inputs = [\n SecretStrInput(\n name=\"apify_token\",\n display_name=\"Apify Token\",\n info=\"The API token for the Apify account.\",\n required=True,\n password=True,\n ),\n StrInput(\n name=\"actor_id\",\n display_name=\"Actor\",\n info=(\n \"Actor name from Apify store to run. For example 'apify/website-content-crawler' \"\n \"to use the Website Content Crawler Actor.\"\n ),\n value=\"apify/website-content-crawler\",\n required=True,\n ),\n # multiline input is more pleasant to use than the nested dict input\n MultilineInput(\n name=\"run_input\",\n display_name=\"Run input\",\n info=(\n 'The JSON input for the Actor run. For example for the \"apify/website-content-crawler\" Actor: '\n '{\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}'\n ),\n value='{\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}',\n required=True,\n ),\n MultilineInput(\n name=\"dataset_fields\",\n display_name=\"Output fields\",\n info=(\n \"Fields to extract from the dataset, split by commas. \"\n \"Other fields will be ignored. Dots in nested structures will be replaced by underscores. \"\n \"Sample input: 'text, metadata.title'. \"\n \"Sample output: {'text': 'page content here', 'metadata_title': 'page title here'}. \"\n \"For example, for the 'apify/website-content-crawler' Actor, you can extract the 'markdown' field, \"\n \"which is the content of the website in markdown format.\"\n ),\n ),\n BoolInput(\n name=\"flatten_dataset\",\n display_name=\"Flatten output\",\n info=(\n \"The output dataset will be converted from a nested format to a flat structure. \"\n \"Dots in nested structure will be replaced by underscores. \"\n \"This is useful for further processing of the Data object. \"\n \"For example, {'a': {'b': 1}} will be flattened to {'a_b': 1}.\"\n ),\n ),\n ]\n\n outputs = [\n Output(display_name=\"Output\", name=\"output\", type_=list[Data], method=\"run_model\"),\n Output(display_name=\"Tool\", name=\"tool\", type_=Tool, method=\"build_tool\"),\n ]\n\n def __init__(self, *args, **kwargs) -> None:\n super().__init__(*args, **kwargs)\n self._apify_client: ApifyClient | None = None\n\n def run_model(self) -> list[Data]:\n \"\"\"Run the Actor and return node output.\"\"\"\n input_ = json.loads(self.run_input)\n fields = ApifyActorsComponent.parse_dataset_fields(self.dataset_fields) if self.dataset_fields else None\n res = self._run_actor(self.actor_id, input_, fields=fields)\n if self.flatten_dataset:\n res = [ApifyActorsComponent.flatten(item) for item in res]\n data = [Data(data=item) for item in res]\n\n self.status = data\n return data\n\n def build_tool(self) -> Tool:\n \"\"\"Build a tool for an agent that runs the Apify Actor.\"\"\"\n actor_id = self.actor_id\n\n build = self._get_actor_latest_build(actor_id)\n readme = build.get(\"readme\", \"\")[:250] + \"...\"\n if not (input_schema_str := build.get(\"inputSchema\")):\n msg = \"Input schema not found\"\n raise ValueError(msg)\n input_schema = json.loads(input_schema_str)\n properties, required = ApifyActorsComponent.get_actor_input_schema_from_build(input_schema)\n properties = {\"run_input\": properties}\n\n # works from input schema\n info_ = [\n (\n \"JSON encoded as a string with input schema (STRICTLY FOLLOW JSON FORMAT AND SCHEMA):\\n\\n\"\n f\"{json.dumps(properties, separators=(',', ':'))}\"\n )\n ]\n if required:\n info_.append(\"\\n\\nRequired fields:\\n\" + \"\\n\".join(required))\n\n info = \"\".join(info_)\n\n input_model_cls = ApifyActorsComponent.create_input_model_class(info)\n tool_cls = ApifyActorsComponent.create_tool_class(self, readme, input_model_cls, actor_id)\n\n return cast(\"Tool\", tool_cls())\n\n @staticmethod\n def create_tool_class(\n parent: \"ApifyActorsComponent\", readme: str, input_model: type[BaseModel], actor_id: str\n ) -> type[BaseTool]:\n \"\"\"Create a tool class that runs an Apify Actor.\"\"\"\n\n class ApifyActorRun(BaseTool):\n \"\"\"Tool that runs Apify Actors.\"\"\"\n\n name: str = f\"apify_actor_{ApifyActorsComponent.actor_id_to_tool_name(actor_id)}\"\n description: str = (\n \"Run an Apify Actor with the given input. \"\n \"Here is a part of the currently loaded Actor README:\\n\\n\"\n f\"{readme}\\n\\n\"\n )\n\n args_schema: type[BaseModel] = input_model\n\n @field_serializer(\"args_schema\")\n def serialize_args_schema(self, args_schema):\n return args_schema.schema()\n\n def _run(self, run_input: str | dict) -> str:\n \"\"\"Use the Apify Actor.\"\"\"\n input_dict = json.loads(run_input) if isinstance(run_input, str) else run_input\n\n # retrieve if nested, just in case\n input_dict = input_dict.get(\"run_input\", input_dict)\n\n res = parent._run_actor(actor_id, input_dict)\n return \"\\n\\n\".join([ApifyActorsComponent.dict_to_json_str(item) for item in res])\n\n return ApifyActorRun\n\n @staticmethod\n def create_input_model_class(description: str) -> type[BaseModel]:\n \"\"\"Create a Pydantic model class for the Actor input.\"\"\"\n\n class ActorInput(BaseModel):\n \"\"\"Input for the Apify Actor tool.\"\"\"\n\n run_input: str = Field(..., description=description)\n\n return ActorInput\n\n def _get_apify_client(self) -> ApifyClient:\n \"\"\"Get the Apify client.\n\n Is created if not exists or token changes.\n \"\"\"\n if not self.apify_token:\n msg = \"API token is required.\"\n raise ValueError(msg)\n # when token changes, create a new client\n if self._apify_client is None or self._apify_client.token != self.apify_token:\n self._apify_client = ApifyClient(self.apify_token)\n if httpx_client := self._apify_client.http_client.httpx_client:\n httpx_client.headers[\"user-agent\"] += \"; Origin/langflow\"\n return self._apify_client\n\n def _get_actor_latest_build(self, actor_id: str) -> dict:\n \"\"\"Get the latest build of an Actor from the default build tag.\"\"\"\n client = self._get_apify_client()\n actor = client.actor(actor_id=actor_id)\n if not (actor_info := actor.get()):\n msg = f\"Actor {actor_id} not found.\"\n raise ValueError(msg)\n\n default_build_tag = actor_info.get(\"defaultRunOptions\", {}).get(\"build\")\n latest_build_id = actor_info.get(\"taggedBuilds\", {}).get(default_build_tag, {}).get(\"buildId\")\n\n if (build := client.build(latest_build_id).get()) is None:\n msg = f\"Build {latest_build_id} not found.\"\n raise ValueError(msg)\n\n return build\n\n @staticmethod\n def get_actor_input_schema_from_build(input_schema: dict) -> tuple[dict, list[str]]:\n \"\"\"Get the input schema from the Actor build.\n\n Trim the description to 250 characters.\n \"\"\"\n properties = input_schema.get(\"properties\", {})\n required = input_schema.get(\"required\", [])\n\n properties_out: dict = {}\n for item, meta in properties.items():\n properties_out[item] = {}\n if desc := meta.get(\"description\"):\n properties_out[item][\"description\"] = (\n desc[:MAX_DESCRIPTION_LEN] + \"...\" if len(desc) > MAX_DESCRIPTION_LEN else desc\n )\n for key_name in (\"type\", \"default\", \"prefill\", \"enum\"):\n if value := meta.get(key_name):\n properties_out[item][key_name] = value\n\n return properties_out, required\n\n def _get_run_dataset_id(self, run_id: str) -> str:\n \"\"\"Get the dataset id from the run id.\"\"\"\n client = self._get_apify_client()\n run = client.run(run_id=run_id)\n if (dataset := run.dataset().get()) is None:\n msg = \"Dataset not found\"\n raise ValueError(msg)\n if (did := dataset.get(\"id\")) is None:\n msg = \"Dataset id not found\"\n raise ValueError(msg)\n return did\n\n @staticmethod\n def dict_to_json_str(d: dict) -> str:\n \"\"\"Convert a dictionary to a JSON string.\"\"\"\n return json.dumps(d, separators=(\",\", \":\"), default=lambda _: \"\")\n\n @staticmethod\n def actor_id_to_tool_name(actor_id: str) -> str:\n \"\"\"Turn actor_id into a valid tool name.\n\n Tool name must only contain letters, numbers, underscores, dashes,\n and cannot contain spaces.\n \"\"\"\n valid_chars = string.ascii_letters + string.digits + \"_-\"\n return \"\".join(char if char in valid_chars else \"_\" for char in actor_id)\n\n def _run_actor(self, actor_id: str, run_input: dict, fields: list[str] | None = None) -> list[dict]:\n \"\"\"Run an Apify Actor and return the output dataset.\n\n Args:\n actor_id: Actor name from Apify store to run.\n run_input: JSON input for the Actor.\n fields: List of fields to extract from the dataset. Other fields will be ignored.\n \"\"\"\n client = self._get_apify_client()\n if (details := client.actor(actor_id=actor_id).call(run_input=run_input, wait_secs=1)) is None:\n msg = \"Actor run details not found\"\n raise ValueError(msg)\n if (run_id := details.get(\"id\")) is None:\n msg = \"Run id not found\"\n raise ValueError(msg)\n\n if (run_client := client.run(run_id)) is None:\n msg = \"Run client not found\"\n raise ValueError(msg)\n\n # stream logs\n with run_client.log().stream() as response:\n if response:\n for line in response.iter_lines():\n self.log(line)\n run_client.wait_for_finish()\n\n dataset_id = self._get_run_dataset_id(run_id)\n\n loader = ApifyDatasetLoader(\n dataset_id=dataset_id,\n dataset_mapping_function=lambda item: item\n if not fields\n else {k.replace(\".\", \"_\"): ApifyActorsComponent.get_nested_value(item, k) for k in fields},\n )\n return loader.load()\n\n @staticmethod\n def get_nested_value(data: dict[str, Any], key: str) -> Any:\n \"\"\"Get a nested value from a dictionary.\"\"\"\n keys = key.split(\".\")\n value = data\n for k in keys:\n if not isinstance(value, dict) or k not in value:\n return None\n value = value[k]\n return value\n\n @staticmethod\n def parse_dataset_fields(dataset_fields: str) -> list[str]:\n \"\"\"Convert a string of comma-separated fields into a list of fields.\"\"\"\n dataset_fields = dataset_fields.replace(\"'\", \"\").replace('\"', \"\").replace(\"`\", \"\")\n return [field.strip() for field in dataset_fields.split(\",\")]\n\n @staticmethod\n def flatten(d: dict) -> dict:\n \"\"\"Flatten a nested dictionary.\"\"\"\n\n def items():\n for key, value in d.items():\n if isinstance(value, dict):\n for subkey, subvalue in ApifyActorsComponent.flatten(value).items():\n yield key + \"_\" + subkey, subvalue\n else:\n yield key, value\n\n return dict(items())\n" }, "dataset_fields": { "_input_type": "MultilineInput", "advanced": false, "display_name": "Output fields", "dynamic": false, "info": "Fields to extract from the dataset, split by commas. Other fields will be ignored. Dots in nested structures will be replaced by underscores. Sample input: 'text, metadata.title'. Sample output: {'text': 'page content here', 'metadata_title': 'page title here'}. For example, for the 'apify/website-content-crawler' Actor, you can extract the 'markdown' field, which is the content of the website in markdown format.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "dataset_fields", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "flatten_dataset": { "_input_type": "BoolInput", "advanced": false, "display_name": "Flatten output", "dynamic": false, "info": "The output dataset will be converted from a nested format to a flat structure. Dots in nested structure will be replaced by underscores. This is useful for further processing of the Data object. For example, {'a': {'b': 1}} will be flattened to {'a_b': 1}.", "list": false, "list_add_label": "Add More", "name": "flatten_dataset", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": false }, "run_input": { "_input_type": "MultilineInput", "advanced": false, "display_name": "Run input", "dynamic": false, "info": "The JSON input for the Actor run. For example for the \"apify/website-content-crawler\" Actor: {\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "run_input", "placeholder": "", "required": true, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "{}" } }, "tool_mode": false }, "selected_output": "tool", "showNode": true, "type": "ApifyActors" }, "dragging": false, "id": "ApifyActors-8WoKJ", "measured": { "height": 526, "width": 320 }, "position": { "x": 283.15772574454707, "y": 39.657725744547065 }, "selected": false, "type": "genericNode" }, { "data": { "id": "ApifyActors-Zrjnz", "node": { "base_classes": [ "Data", "Tool" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Use Apify Actors to extract data from hundreds of places fast. This component can be used in a flow to retrieve data or as a tool with an agent.", "display_name": "Apify Actors", "documentation": "http://docs.langflow.org/integrations-apify", "edited": false, "field_order": [ "apify_token", "actor_id", "run_input", "dataset_fields", "flatten_dataset" ], "frozen": false, "icon": "Apify", "legacy": false, "lf_version": "1.4.2", "metadata": {}, "minimized": false, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Output", "hidden": null, "method": "run_model", "name": "output", "required_inputs": null, "tool_mode": true, "types": [ "Data" ], "value": "__UNDEFINED__" }, { "allows_loop": false, "cache": true, "display_name": "Tool", "hidden": null, "method": "build_tool", "name": "tool", "required_inputs": null, "selected": "Tool", "tool_mode": true, "types": [ "Tool" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "actor_id": { "_input_type": "StrInput", "advanced": false, "display_name": "Actor", "dynamic": false, "info": "Actor name from Apify store to run. For example 'apify/website-content-crawler' to use the Website Content Crawler Actor.", "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "actor_id", "placeholder": "", "required": true, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "apify/google-search-scraper" }, "apify_token": { "_input_type": "SecretStrInput", "advanced": false, "display_name": "Apify Token", "dynamic": false, "info": "The API token for the Apify account.", "input_types": [], "load_from_db": false, "name": "apify_token", "password": true, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "str", "value": "" }, "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "import json\nimport string\nfrom typing import Any, cast\n\nfrom apify_client import ApifyClient\nfrom langchain_community.document_loaders.apify_dataset import ApifyDatasetLoader\nfrom langchain_core.tools import BaseTool\nfrom pydantic import BaseModel, Field, field_serializer\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing import Tool\nfrom langflow.inputs.inputs import BoolInput\nfrom langflow.io import MultilineInput, Output, SecretStrInput, StrInput\nfrom langflow.schema.data import Data\n\nMAX_DESCRIPTION_LEN = 250\n\n\nclass ApifyActorsComponent(Component):\n display_name = \"Apify Actors\"\n description = (\n \"Use Apify Actors to extract data from hundreds of places fast. \"\n \"This component can be used in a flow to retrieve data or as a tool with an agent.\"\n )\n documentation: str = \"http://docs.langflow.org/integrations-apify\"\n icon = \"Apify\"\n name = \"ApifyActors\"\n\n inputs = [\n SecretStrInput(\n name=\"apify_token\",\n display_name=\"Apify Token\",\n info=\"The API token for the Apify account.\",\n required=True,\n password=True,\n ),\n StrInput(\n name=\"actor_id\",\n display_name=\"Actor\",\n info=(\n \"Actor name from Apify store to run. For example 'apify/website-content-crawler' \"\n \"to use the Website Content Crawler Actor.\"\n ),\n value=\"apify/website-content-crawler\",\n required=True,\n ),\n # multiline input is more pleasant to use than the nested dict input\n MultilineInput(\n name=\"run_input\",\n display_name=\"Run input\",\n info=(\n 'The JSON input for the Actor run. For example for the \"apify/website-content-crawler\" Actor: '\n '{\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}'\n ),\n value='{\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}',\n required=True,\n ),\n MultilineInput(\n name=\"dataset_fields\",\n display_name=\"Output fields\",\n info=(\n \"Fields to extract from the dataset, split by commas. \"\n \"Other fields will be ignored. Dots in nested structures will be replaced by underscores. \"\n \"Sample input: 'text, metadata.title'. \"\n \"Sample output: {'text': 'page content here', 'metadata_title': 'page title here'}. \"\n \"For example, for the 'apify/website-content-crawler' Actor, you can extract the 'markdown' field, \"\n \"which is the content of the website in markdown format.\"\n ),\n ),\n BoolInput(\n name=\"flatten_dataset\",\n display_name=\"Flatten output\",\n info=(\n \"The output dataset will be converted from a nested format to a flat structure. \"\n \"Dots in nested structure will be replaced by underscores. \"\n \"This is useful for further processing of the Data object. \"\n \"For example, {'a': {'b': 1}} will be flattened to {'a_b': 1}.\"\n ),\n ),\n ]\n\n outputs = [\n Output(display_name=\"Output\", name=\"output\", type_=list[Data], method=\"run_model\"),\n Output(display_name=\"Tool\", name=\"tool\", type_=Tool, method=\"build_tool\"),\n ]\n\n def __init__(self, *args, **kwargs) -> None:\n super().__init__(*args, **kwargs)\n self._apify_client: ApifyClient | None = None\n\n def run_model(self) -> list[Data]:\n \"\"\"Run the Actor and return node output.\"\"\"\n input_ = json.loads(self.run_input)\n fields = ApifyActorsComponent.parse_dataset_fields(self.dataset_fields) if self.dataset_fields else None\n res = self._run_actor(self.actor_id, input_, fields=fields)\n if self.flatten_dataset:\n res = [ApifyActorsComponent.flatten(item) for item in res]\n data = [Data(data=item) for item in res]\n\n self.status = data\n return data\n\n def build_tool(self) -> Tool:\n \"\"\"Build a tool for an agent that runs the Apify Actor.\"\"\"\n actor_id = self.actor_id\n\n build = self._get_actor_latest_build(actor_id)\n readme = build.get(\"readme\", \"\")[:250] + \"...\"\n if not (input_schema_str := build.get(\"inputSchema\")):\n msg = \"Input schema not found\"\n raise ValueError(msg)\n input_schema = json.loads(input_schema_str)\n properties, required = ApifyActorsComponent.get_actor_input_schema_from_build(input_schema)\n properties = {\"run_input\": properties}\n\n # works from input schema\n info_ = [\n (\n \"JSON encoded as a string with input schema (STRICTLY FOLLOW JSON FORMAT AND SCHEMA):\\n\\n\"\n f\"{json.dumps(properties, separators=(',', ':'))}\"\n )\n ]\n if required:\n info_.append(\"\\n\\nRequired fields:\\n\" + \"\\n\".join(required))\n\n info = \"\".join(info_)\n\n input_model_cls = ApifyActorsComponent.create_input_model_class(info)\n tool_cls = ApifyActorsComponent.create_tool_class(self, readme, input_model_cls, actor_id)\n\n return cast(\"Tool\", tool_cls())\n\n @staticmethod\n def create_tool_class(\n parent: \"ApifyActorsComponent\", readme: str, input_model: type[BaseModel], actor_id: str\n ) -> type[BaseTool]:\n \"\"\"Create a tool class that runs an Apify Actor.\"\"\"\n\n class ApifyActorRun(BaseTool):\n \"\"\"Tool that runs Apify Actors.\"\"\"\n\n name: str = f\"apify_actor_{ApifyActorsComponent.actor_id_to_tool_name(actor_id)}\"\n description: str = (\n \"Run an Apify Actor with the given input. \"\n \"Here is a part of the currently loaded Actor README:\\n\\n\"\n f\"{readme}\\n\\n\"\n )\n\n args_schema: type[BaseModel] = input_model\n\n @field_serializer(\"args_schema\")\n def serialize_args_schema(self, args_schema):\n return args_schema.schema()\n\n def _run(self, run_input: str | dict) -> str:\n \"\"\"Use the Apify Actor.\"\"\"\n input_dict = json.loads(run_input) if isinstance(run_input, str) else run_input\n\n # retrieve if nested, just in case\n input_dict = input_dict.get(\"run_input\", input_dict)\n\n res = parent._run_actor(actor_id, input_dict)\n return \"\\n\\n\".join([ApifyActorsComponent.dict_to_json_str(item) for item in res])\n\n return ApifyActorRun\n\n @staticmethod\n def create_input_model_class(description: str) -> type[BaseModel]:\n \"\"\"Create a Pydantic model class for the Actor input.\"\"\"\n\n class ActorInput(BaseModel):\n \"\"\"Input for the Apify Actor tool.\"\"\"\n\n run_input: str = Field(..., description=description)\n\n return ActorInput\n\n def _get_apify_client(self) -> ApifyClient:\n \"\"\"Get the Apify client.\n\n Is created if not exists or token changes.\n \"\"\"\n if not self.apify_token:\n msg = \"API token is required.\"\n raise ValueError(msg)\n # when token changes, create a new client\n if self._apify_client is None or self._apify_client.token != self.apify_token:\n self._apify_client = ApifyClient(self.apify_token)\n if httpx_client := self._apify_client.http_client.httpx_client:\n httpx_client.headers[\"user-agent\"] += \"; Origin/langflow\"\n return self._apify_client\n\n def _get_actor_latest_build(self, actor_id: str) -> dict:\n \"\"\"Get the latest build of an Actor from the default build tag.\"\"\"\n client = self._get_apify_client()\n actor = client.actor(actor_id=actor_id)\n if not (actor_info := actor.get()):\n msg = f\"Actor {actor_id} not found.\"\n raise ValueError(msg)\n\n default_build_tag = actor_info.get(\"defaultRunOptions\", {}).get(\"build\")\n latest_build_id = actor_info.get(\"taggedBuilds\", {}).get(default_build_tag, {}).get(\"buildId\")\n\n if (build := client.build(latest_build_id).get()) is None:\n msg = f\"Build {latest_build_id} not found.\"\n raise ValueError(msg)\n\n return build\n\n @staticmethod\n def get_actor_input_schema_from_build(input_schema: dict) -> tuple[dict, list[str]]:\n \"\"\"Get the input schema from the Actor build.\n\n Trim the description to 250 characters.\n \"\"\"\n properties = input_schema.get(\"properties\", {})\n required = input_schema.get(\"required\", [])\n\n properties_out: dict = {}\n for item, meta in properties.items():\n properties_out[item] = {}\n if desc := meta.get(\"description\"):\n properties_out[item][\"description\"] = (\n desc[:MAX_DESCRIPTION_LEN] + \"...\" if len(desc) > MAX_DESCRIPTION_LEN else desc\n )\n for key_name in (\"type\", \"default\", \"prefill\", \"enum\"):\n if value := meta.get(key_name):\n properties_out[item][key_name] = value\n\n return properties_out, required\n\n def _get_run_dataset_id(self, run_id: str) -> str:\n \"\"\"Get the dataset id from the run id.\"\"\"\n client = self._get_apify_client()\n run = client.run(run_id=run_id)\n if (dataset := run.dataset().get()) is None:\n msg = \"Dataset not found\"\n raise ValueError(msg)\n if (did := dataset.get(\"id\")) is None:\n msg = \"Dataset id not found\"\n raise ValueError(msg)\n return did\n\n @staticmethod\n def dict_to_json_str(d: dict) -> str:\n \"\"\"Convert a dictionary to a JSON string.\"\"\"\n return json.dumps(d, separators=(\",\", \":\"), default=lambda _: \"\")\n\n @staticmethod\n def actor_id_to_tool_name(actor_id: str) -> str:\n \"\"\"Turn actor_id into a valid tool name.\n\n Tool name must only contain letters, numbers, underscores, dashes,\n and cannot contain spaces.\n \"\"\"\n valid_chars = string.ascii_letters + string.digits + \"_-\"\n return \"\".join(char if char in valid_chars else \"_\" for char in actor_id)\n\n def _run_actor(self, actor_id: str, run_input: dict, fields: list[str] | None = None) -> list[dict]:\n \"\"\"Run an Apify Actor and return the output dataset.\n\n Args:\n actor_id: Actor name from Apify store to run.\n run_input: JSON input for the Actor.\n fields: List of fields to extract from the dataset. Other fields will be ignored.\n \"\"\"\n client = self._get_apify_client()\n if (details := client.actor(actor_id=actor_id).call(run_input=run_input, wait_secs=1)) is None:\n msg = \"Actor run details not found\"\n raise ValueError(msg)\n if (run_id := details.get(\"id\")) is None:\n msg = \"Run id not found\"\n raise ValueError(msg)\n\n if (run_client := client.run(run_id)) is None:\n msg = \"Run client not found\"\n raise ValueError(msg)\n\n # stream logs\n with run_client.log().stream() as response:\n if response:\n for line in response.iter_lines():\n self.log(line)\n run_client.wait_for_finish()\n\n dataset_id = self._get_run_dataset_id(run_id)\n\n loader = ApifyDatasetLoader(\n dataset_id=dataset_id,\n dataset_mapping_function=lambda item: item\n if not fields\n else {k.replace(\".\", \"_\"): ApifyActorsComponent.get_nested_value(item, k) for k in fields},\n )\n return loader.load()\n\n @staticmethod\n def get_nested_value(data: dict[str, Any], key: str) -> Any:\n \"\"\"Get a nested value from a dictionary.\"\"\"\n keys = key.split(\".\")\n value = data\n for k in keys:\n if not isinstance(value, dict) or k not in value:\n return None\n value = value[k]\n return value\n\n @staticmethod\n def parse_dataset_fields(dataset_fields: str) -> list[str]:\n \"\"\"Convert a string of comma-separated fields into a list of fields.\"\"\"\n dataset_fields = dataset_fields.replace(\"'\", \"\").replace('\"', \"\").replace(\"`\", \"\")\n return [field.strip() for field in dataset_fields.split(\",\")]\n\n @staticmethod\n def flatten(d: dict) -> dict:\n \"\"\"Flatten a nested dictionary.\"\"\"\n\n def items():\n for key, value in d.items():\n if isinstance(value, dict):\n for subkey, subvalue in ApifyActorsComponent.flatten(value).items():\n yield key + \"_\" + subkey, subvalue\n else:\n yield key, value\n\n return dict(items())\n" }, "dataset_fields": { "_input_type": "MultilineInput", "advanced": false, "display_name": "Output fields", "dynamic": false, "info": "Fields to extract from the dataset, split by commas. Other fields will be ignored. Dots in nested structures will be replaced by underscores. Sample input: 'text, metadata.title'. Sample output: {'text': 'page content here', 'metadata_title': 'page title here'}. For example, for the 'apify/website-content-crawler' Actor, you can extract the 'markdown' field, which is the content of the website in markdown format.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "dataset_fields", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "flatten_dataset": { "_input_type": "BoolInput", "advanced": false, "display_name": "Flatten output", "dynamic": false, "info": "The output dataset will be converted from a nested format to a flat structure. Dots in nested structure will be replaced by underscores. This is useful for further processing of the Data object. For example, {'a': {'b': 1}} will be flattened to {'a_b': 1}.", "list": false, "list_add_label": "Add More", "name": "flatten_dataset", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": false }, "run_input": { "_input_type": "MultilineInput", "advanced": false, "display_name": "Run input", "dynamic": false, "info": "The JSON input for the Actor run. For example for the \"apify/website-content-crawler\" Actor: {\"startUrls\":[{\"url\":\"https://docs.apify.com/academy/web-scraping-for-beginners\"}],\"maxCrawlDepth\":0}", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "run_input", "placeholder": "", "required": true, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "{}" } }, "tool_mode": false }, "selected_output": "tool", "showNode": true, "type": "ApifyActors" }, "dragging": false, "id": "ApifyActors-Zrjnz", "measured": { "height": 526, "width": 320 }, "position": { "x": 667.740737396329, "y": 38.23718269967556 }, "selected": false, "type": "genericNode" }, { "data": { "id": "note-do2Nq", "node": { "description": "### 💡 Add your Apify API key here ", "display_name": "", "documentation": "", "template": { "backgroundColor": "transparent" } }, "type": "note" }, "dragging": false, "id": "note-do2Nq", "measured": { "height": 324, "width": 324 }, "position": { "x": 283.28440720113247, "y": -12.197383176721686 }, "selected": false, "type": "noteNode" }, { "data": { "id": "note-7z6Er", "node": { "description": "### 💡 Add your Apify API key here ", "display_name": "", "documentation": "", "template": { "backgroundColor": "transparent" } }, "type": "note" }, "dragging": false, "height": 324, "id": "note-7z6Er", "measured": { "height": 324, "width": 324 }, "position": { "x": 670.9327129574519, "y": -13.541445827465466 }, "resizing": false, "selected": false, "type": "noteNode", "width": 324 }, { "data": { "id": "note-NZDOa", "node": { "description": "# Social Media Agent\n\nExtract data with **Apify Actors** and analyze the data with an **Agent**.\n\n## Prerequisites\n\n* An [Apify API token](https://docs.apify.com/platform/integrations/api#api-token)\n* An [OpenAI API key](https://platform.openai.com/)\n\n## Quickstart\n\n1. Enter your **Apify** API token in the **Apify Token** fields of the **Apify Actors** components. \n2. Enter your **OpenAI** API token in the **OpenAI API Key** field of the **Agent** component.\n3. Open the **Playground** and chat with the agent. For example, task it with retrieving a profile bio and the latest video by using this prompt: \n ```\n Find the TikTok profile of the company OpenAI using Google search, then show me the profile bio and their latest video.\n ```", "display_name": "", "documentation": "", "template": { "backgroundColor": "amber" } }, "type": "note" }, "dragging": false, "height": 657, "id": "note-NZDOa", "measured": { "height": 657, "width": 524 }, "position": { "x": -313.0627945618906, "y": 7.352701184369295 }, "resizing": false, "selected": false, "type": "noteNode", "width": 524 }, { "data": { "id": "ChatInput-RBrnT", "node": { "base_classes": [ "Message" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Get chat inputs from the Playground.", "display_name": "Chat Input", "documentation": "", "edited": false, "field_order": [ "input_value", "should_store_message", "sender", "sender_name", "session_id", "files", "background_color", "chat_icon", "text_color" ], "frozen": false, "icon": "MessagesSquare", "legacy": false, "lf_version": "1.4.2", "metadata": {}, "minimized": true, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Chat Message", "group_outputs": false, "method": "message_response", "name": "message", "selected": "Message", "tool_mode": true, "types": [ "Message" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "from langflow.base.data.utils import IMG_FILE_TYPES, TEXT_FILE_TYPES\nfrom langflow.base.io.chat import ChatComponent\nfrom langflow.inputs.inputs import BoolInput\nfrom langflow.io import (\n DropdownInput,\n FileInput,\n MessageTextInput,\n MultilineInput,\n Output,\n)\nfrom langflow.schema.message import Message\nfrom langflow.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_USER,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatInput(ChatComponent):\n display_name = \"Chat Input\"\n description = \"Get chat inputs from the Playground.\"\n documentation: str = \"https://docs.langflow.org/components-io#chat-input\"\n icon = \"MessagesSquare\"\n name = \"ChatInput\"\n minimized = True\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Input Text\",\n value=\"\",\n info=\"Message to be passed as input.\",\n input_types=[],\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_USER,\n info=\"Type of sender.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_USER,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n FileInput(\n name=\"files\",\n display_name=\"Files\",\n file_types=TEXT_FILE_TYPES + IMG_FILE_TYPES,\n info=\"Files to be sent with the message.\",\n advanced=True,\n is_list=True,\n temp_file=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Chat Message\", name=\"message\", method=\"message_response\"),\n ]\n\n async def message_response(self) -> Message:\n # Ensure files is a list and filter out empty/None values\n files = self.files if self.files else []\n if files and not isinstance(files, list):\n files = [files]\n files = [f for f in files if f is not None and f != \"\"]\n\n message = await Message.create(\n text=self.input_value,\n sender=self.sender,\n sender_name=self.sender_name,\n session_id=self.session_id,\n files=files,\n )\n if self.session_id and isinstance(message, Message) and self.should_store_message:\n stored_message = await self.send_message(\n message,\n )\n self.message.value = stored_message\n message = stored_message\n\n self.status = message\n return message\n" }, "files": { "_input_type": "FileInput", "advanced": true, "display_name": "Files", "dynamic": false, "fileTypes": [ "csv", "json", "pdf", "txt", "md", "mdx", "yaml", "yml", "xml", "html", "htm", "docx", "py", "sh", "sql", "js", "ts", "tsx", "jpg", "jpeg", "png", "bmp", "image" ], "file_path": "", "info": "Files to be sent with the message.", "list": true, "list_add_label": "Add More", "name": "files", "placeholder": "", "required": false, "show": true, "temp_file": true, "title_case": false, "trace_as_metadata": true, "type": "file", "value": "" }, "input_value": { "_input_type": "MultilineInput", "advanced": false, "display_name": "Input Text", "dynamic": false, "info": "Message to be passed as input.", "input_types": [], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "input_value", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "sender": { "_input_type": "DropdownInput", "advanced": true, "combobox": false, "dialog_inputs": {}, "display_name": "Sender Type", "dynamic": false, "info": "Type of sender.", "name": "sender", "options": [ "Machine", "User" ], "options_metadata": [], "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "User" }, "sender_name": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Sender Name", "dynamic": false, "info": "Name of the sender.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "sender_name", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "User" }, "session_id": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Session ID", "dynamic": false, "info": "The session ID of the chat. If empty, the current session ID parameter will be used.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "session_id", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "should_store_message": { "_input_type": "BoolInput", "advanced": true, "display_name": "Store Messages", "dynamic": false, "info": "Store the message in the history.", "list": false, "list_add_label": "Add More", "name": "should_store_message", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true } }, "tool_mode": false }, "selected_output": "message", "showNode": false, "type": "ChatInput" }, "dragging": false, "id": "ChatInput-RBrnT", "measured": { "height": 48, "width": 192 }, "position": { "x": 656.0956221831866, "y": 792.3772894800933 }, "selected": false, "type": "genericNode" }, { "data": { "id": "ChatOutput-Lgpwq", "node": { "base_classes": [ "Message" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Display a chat message in the Playground.", "display_name": "Chat Output", "documentation": "", "edited": false, "field_order": [ "input_value", "should_store_message", "sender", "sender_name", "session_id", "data_template", "background_color", "chat_icon", "text_color", "clean_data" ], "frozen": false, "icon": "MessagesSquare", "legacy": false, "lf_version": "1.4.2", "metadata": {}, "minimized": true, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Output Message", "group_outputs": false, "method": "message_response", "name": "message", "selected": "Message", "tool_mode": true, "types": [ "Message" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom langflow.base.io.chat import ChatComponent\nfrom langflow.helpers.data import safe_convert\nfrom langflow.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\nfrom langflow.schema.properties import Source\nfrom langflow.template.field.base import Output\nfrom langflow.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/components-io#chat-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"DataFrame\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, icon, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message):\n message = self.input_value\n # Update message properties\n message.text = text\n else:\n message = Message(text=text)\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n message.session_id = self.session_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if self.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n" }, "data_template": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Data Template", "dynamic": false, "info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "data_template", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "{text}" }, "input_value": { "_input_type": "HandleInput", "advanced": false, "display_name": "Inputs", "dynamic": false, "info": "Message to be passed as output.", "input_types": [ "Data", "DataFrame", "Message" ], "list": false, "list_add_label": "Add More", "name": "input_value", "placeholder": "", "required": true, "show": true, "title_case": false, "trace_as_metadata": true, "type": "other", "value": "" }, "sender": { "_input_type": "DropdownInput", "advanced": true, "combobox": false, "dialog_inputs": {}, "display_name": "Sender Type", "dynamic": false, "info": "Type of sender.", "name": "sender", "options": [ "Machine", "User" ], "options_metadata": [], "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "Machine" }, "sender_name": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Sender Name", "dynamic": false, "info": "Name of the sender.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "sender_name", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "AI" }, "session_id": { "_input_type": "MessageTextInput", "advanced": true, "display_name": "Session ID", "dynamic": false, "info": "The session ID of the chat. If empty, the current session ID parameter will be used.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "session_id", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "should_store_message": { "_input_type": "BoolInput", "advanced": true, "display_name": "Store Messages", "dynamic": false, "info": "Store the message in the history.", "list": false, "list_add_label": "Add More", "name": "should_store_message", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true } }, "tool_mode": false }, "showNode": false, "type": "ChatOutput" }, "dragging": false, "id": "ChatOutput-Lgpwq", "measured": { "height": 48, "width": 192 }, "position": { "x": 1413.848308689952, "y": 856.7319843711496 }, "selected": false, "type": "genericNode" }, { "data": { "id": "note-1Ws1d", "node": { "description": "### Configure your Model Provider", "display_name": "", "documentation": "", "template": { "backgroundColor": "transparent" } }, "type": "note" }, "dragging": false, "id": "note-1Ws1d", "measured": { "height": 324, "width": 324 }, "position": { "x": 1035.6043472316023, "y": 238.36639317703757 }, "selected": false, "type": "noteNode" }, { "data": { "id": "Agent-0vMrI", "node": { "base_classes": [ "Message" ], "beta": false, "conditional_paths": [], "custom_fields": {}, "description": "Define the agent's instructions, then enter a task to complete using tools.", "display_name": "Agent", "documentation": "", "edited": false, "field_order": [ "agent_llm", "max_tokens", "model_kwargs", "json_mode", "model_name", "openai_api_base", "api_key", "temperature", "seed", "max_retries", "timeout", "system_prompt", "n_messages", "tools", "input_value", "handle_parsing_errors", "verbose", "max_iterations", "agent_description", "add_current_date_tool" ], "frozen": false, "icon": "bot", "legacy": false, "metadata": {}, "minimized": false, "output_types": [], "outputs": [ { "allows_loop": false, "cache": true, "display_name": "Response", "group_outputs": false, "method": "message_response", "name": "response", "selected": "Message", "tool_mode": true, "types": [ "Message" ], "value": "__UNDEFINED__" } ], "pinned": false, "template": { "_type": "Component", "add_current_date_tool": { "_input_type": "BoolInput", "advanced": true, "display_name": "Current Date", "dynamic": false, "info": "If true, will add a tool to the agent that returns the current date.", "list": false, "list_add_label": "Add More", "name": "add_current_date_tool", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true }, "agent_description": { "_input_type": "MultilineInput", "advanced": true, "copy_field": false, "display_name": "Agent Description [Deprecated]", "dynamic": false, "info": "The description of the agent. This is only used when in Tool Mode. Defaults to 'A helpful assistant with access to the following tools:' and tools are added dynamically. This feature is deprecated and will be removed in future versions.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "agent_description", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "A helpful assistant with access to the following tools:" }, "agent_llm": { "_input_type": "DropdownInput", "advanced": false, "combobox": false, "dialog_inputs": {}, "display_name": "Model Provider", "dynamic": false, "external_options": { "fields": { "data": { "node": { "display_name": "Connect other models", "icon": "CornerDownLeft", "name": "connect_other_models" } } } }, "info": "The provider of the language model that the agent will use to generate responses.", "input_types": [], "name": "agent_llm", "options": [ "Anthropic", "Google Generative AI", "OpenAI" ], "options_metadata": [ { "icon": "Anthropic" }, { "icon": "GoogleGenerativeAI" }, { "icon": "OpenAI" } ], "placeholder": "", "real_time_refresh": true, "required": false, "show": true, "title_case": false, "toggle": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "OpenAI" }, "api_key": { "_input_type": "SecretStrInput", "advanced": false, "display_name": "OpenAI API Key", "dynamic": false, "info": "The OpenAI API Key to use for the OpenAI model.", "input_types": [], "load_from_db": true, "name": "api_key", "password": true, "placeholder": "", "real_time_refresh": true, "required": false, "show": true, "title_case": false, "type": "str", "value": "OPENAI_API_KEY" }, "code": { "advanced": true, "dynamic": true, "fileTypes": [], "file_path": "", "info": "", "list": false, "load_from_db": false, "multiline": true, "name": "code", "password": false, "placeholder": "", "required": true, "show": true, "title_case": false, "type": "code", "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\nfrom pydantic import ValidationError\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n ALL_PROVIDER_FIELDS,\n MODEL_DYNAMIC_UPDATE_FIELDS,\n MODEL_PROVIDERS_DICT,\n MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import (\n ToolCallingAgentComponent,\n)\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.helpers.base_model import build_model_from_schema\nfrom langflow.io import (\n BoolInput,\n DropdownInput,\n IntInput,\n MultilineInput,\n Output,\n TableInput,\n)\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.schema.table import EditMode\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"OpenAI\"]\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 documentation: str = \"https://docs.langflow.org/agents\"\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 # Filter out json_mode from OpenAI inputs since we handle structured output differently\n openai_inputs_filtered = [\n input_field\n for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n ]\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=[*MODEL_PROVIDERS_LIST],\n value=\"OpenAI\",\n real_time_refresh=True,\n refresh_button=False,\n input_types=[],\n options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST],\n external_options={\n \"fields\": {\n \"data\": {\n \"node\": {\n \"name\": \"connect_other_models\",\n \"display_name\": \"Connect other models\",\n \"icon\": \"CornerDownLeft\",\n }\n }\n },\n },\n ),\n *openai_inputs_filtered,\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 IntInput(\n name=\"n_messages\",\n display_name=\"Number of Chat History Messages\",\n value=100,\n info=\"Number of chat history messages to retrieve.\",\n advanced=True,\n show=True,\n ),\n MultilineInput(\n name=\"format_instructions\",\n display_name=\"Output Format Instructions\",\n info=\"Generic Template for structured output formatting. Valid only with Structured response.\",\n value=(\n \"You are an AI that extracts structured JSON objects from unstructured text. \"\n \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n \"Fill missing or ambiguous values with defaults: null for missing values. \"\n \"Remove exact duplicates but keep variations that have different field values. \"\n \"Always return valid JSON in the expected format, never throw errors. \"\n \"If multiple objects can be extracted, return them all in the structured format.\"\n ),\n advanced=True,\n ),\n TableInput(\n name=\"output_schema\",\n display_name=\"Output Schema\",\n info=(\n \"Schema Validation: Define the structure and data types for structured output. \"\n \"No validation if no output schema.\"\n ),\n advanced=True,\n required=False,\n value=[],\n table_schema=[\n {\n \"name\": \"name\",\n \"display_name\": \"Name\",\n \"type\": \"str\",\n \"description\": \"Specify the name of the output field.\",\n \"default\": \"field\",\n \"edit_mode\": EditMode.INLINE,\n },\n {\n \"name\": \"description\",\n \"display_name\": \"Description\",\n \"type\": \"str\",\n \"description\": \"Describe the purpose of the output field.\",\n \"default\": \"description of field\",\n \"edit_mode\": EditMode.POPOVER,\n },\n {\n \"name\": \"type\",\n \"display_name\": \"Type\",\n \"type\": \"str\",\n \"edit_mode\": EditMode.INLINE,\n \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n \"default\": \"str\",\n },\n {\n \"name\": \"multiple\",\n \"display_name\": \"As List\",\n \"type\": \"boolean\",\n \"description\": \"Set to True if this output field should be a list of the specified type.\",\n \"default\": \"False\",\n \"edit_mode\": EditMode.INLINE,\n },\n ],\n ),\n *LCToolsAgentComponent._base_inputs,\n # removed memory inputs from agent component\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 = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n ]\n\n async def get_agent_requirements(self):\n \"\"\"Get the agent requirements for the agent.\"\"\"\n llm_model, display_name = await self.get_llm()\n if llm_model is None:\n msg = \"No language model selected. Please choose a model to proceed.\"\n raise ValueError(msg)\n self.model_name = get_model_name(llm_model, display_name=display_name)\n\n # Get memory data\n self.chat_history = await self.get_memory_data()\n if isinstance(self.chat_history, Message):\n self.chat_history = [self.chat_history]\n\n # Add current date tool if enabled\n if self.add_current_date_tool:\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n if not isinstance(current_date_tool, StructuredTool):\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n self.tools.append(current_date_tool)\n return llm_model, self.chat_history, self.tools\n\n async def message_response(self) -> Message:\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n # Set up and run agent\n self.set(\n llm=llm_model,\n tools=self.tools or [],\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 result = await self.run_agent(agent)\n\n # Store result for potential JSON output\n self._agent_result = result\n\n except (ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n raise\n except ExceptionWithMessageError as e:\n await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n raise\n # Avoid catching blind Exception; let truly unexpected exceptions propagate\n except Exception as e:\n await logger.aerror(f\"Unexpected error: {e!s}\")\n raise\n else:\n return result\n\n def _preprocess_schema(self, schema):\n \"\"\"Preprocess schema to ensure correct data types for build_model_from_schema.\"\"\"\n processed_schema = []\n for field in schema:\n processed_field = {\n \"name\": str(field.get(\"name\", \"field\")),\n \"type\": str(field.get(\"type\", \"str\")),\n \"description\": str(field.get(\"description\", \"\")),\n \"multiple\": field.get(\"multiple\", False),\n }\n # Ensure multiple is handled correctly\n if isinstance(processed_field[\"multiple\"], str):\n processed_field[\"multiple\"] = processed_field[\"multiple\"].lower() in [\n \"true\",\n \"1\",\n \"t\",\n \"y\",\n \"yes\",\n ]\n processed_schema.append(processed_field)\n return processed_schema\n\n async def build_structured_output_base(self, content: str):\n \"\"\"Build structured output with optional BaseModel validation.\"\"\"\n json_pattern = r\"\\{.*\\}\"\n schema_error_msg = \"Try setting an output schema\"\n\n # Try to parse content as JSON first\n json_data = None\n try:\n json_data = json.loads(content)\n except json.JSONDecodeError:\n json_match = re.search(json_pattern, content, re.DOTALL)\n if json_match:\n try:\n json_data = json.loads(json_match.group())\n except json.JSONDecodeError:\n return {\"content\": content, \"error\": schema_error_msg}\n else:\n return {\"content\": content, \"error\": schema_error_msg}\n\n # If no output schema provided, return parsed JSON without validation\n if not hasattr(self, \"output_schema\") or not self.output_schema or len(self.output_schema) == 0:\n return json_data\n\n # Use BaseModel validation with schema\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n\n # Validate against the schema\n if isinstance(json_data, list):\n # Multiple objects\n validated_objects = []\n for item in json_data:\n try:\n validated_obj = output_model.model_validate(item)\n validated_objects.append(validated_obj.model_dump())\n except ValidationError as e:\n await logger.aerror(f\"Validation error for item: {e}\")\n # Include invalid items with error info\n validated_objects.append({\"data\": item, \"validation_error\": str(e)})\n return validated_objects\n\n # Single object\n try:\n validated_obj = output_model.model_validate(json_data)\n return [validated_obj.model_dump()] # Return as list for consistency\n except ValidationError as e:\n await logger.aerror(f\"Validation error: {e}\")\n return [{\"data\": json_data, \"validation_error\": str(e)}]\n\n except (TypeError, ValueError) as e:\n await logger.aerror(f\"Error building structured output: {e}\")\n # Fallback to parsed JSON without validation\n return json_data\n\n async def json_response(self) -> Data:\n \"\"\"Convert agent response to structured JSON Data output with schema validation.\"\"\"\n # Always use structured chat agent for JSON response mode for better JSON formatting\n try:\n system_components = []\n\n # 1. Agent Instructions (system_prompt)\n agent_instructions = getattr(self, \"system_prompt\", \"\") or \"\"\n if agent_instructions:\n system_components.append(f\"{agent_instructions}\")\n\n # 2. Format Instructions\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n if format_instructions:\n system_components.append(f\"Format instructions: {format_instructions}\")\n\n # 3. Schema Information from BaseModel\n if hasattr(self, \"output_schema\") and self.output_schema and len(self.output_schema) > 0:\n try:\n processed_schema = self._preprocess_schema(self.output_schema)\n output_model = build_model_from_schema(processed_schema)\n schema_dict = output_model.model_json_schema()\n schema_info = (\n \"You are given some text that may include format instructions, \"\n \"explanations, or other content alongside a JSON schema.\\n\\n\"\n \"Your task:\\n\"\n \"- Extract only the JSON schema.\\n\"\n \"- Return it as valid JSON.\\n\"\n \"- Do not include format instructions, explanations, or extra text.\\n\\n\"\n \"Input:\\n\"\n f\"{json.dumps(schema_dict, indent=2)}\\n\\n\"\n \"Output (only JSON schema):\"\n )\n system_components.append(schema_info)\n except (ValidationError, ValueError, TypeError, KeyError) as e:\n await logger.aerror(f\"Could not build schema for prompt: {e}\", exc_info=True)\n\n # Combine all components\n combined_instructions = \"\\n\\n\".join(system_components) if system_components else \"\"\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n self.set(\n llm=llm_model,\n tools=self.tools or [],\n chat_history=self.chat_history,\n input_value=self.input_value,\n system_prompt=combined_instructions,\n )\n\n # Create and run structured chat agent\n try:\n structured_agent = self.create_agent_runnable()\n except (NotImplementedError, ValueError, TypeError) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n raise\n try:\n result = await self.run_agent(structured_agent)\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n RuntimeError,\n ) as e:\n await logger.aerror(f\"Error with structured agent result: {e}\")\n raise\n # Extract content from structured agent result\n if hasattr(result, \"content\"):\n content = result.content\n elif hasattr(result, \"text\"):\n content = result.text\n else:\n content = str(result)\n\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as e:\n await logger.aerror(f\"Error with structured chat agent: {e}\")\n # Fallback to regular agent\n content_str = \"No content returned from agent\"\n return Data(data={\"content\": content_str, \"error\": str(e)})\n\n # Process with structured output validation\n try:\n structured_output = await self.build_structured_output_base(content)\n\n # Handle different output formats\n if isinstance(structured_output, list) and structured_output:\n if len(structured_output) == 1:\n return Data(data=structured_output[0])\n return Data(data={\"results\": structured_output})\n if isinstance(structured_output, dict):\n return Data(data=structured_output)\n return Data(data={\"content\": content})\n\n except (ValueError, TypeError) as e:\n await logger.aerror(f\"Error in structured output processing: {e}\")\n return Data(data={\"content\": content, \"error\": str(e)})\n\n async def get_memory_data(self):\n # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n messages = (\n await MemoryComponent(**self.get_base_args())\n .set(\n session_id=self.graph.session_id,\n order=\"Ascending\",\n n_messages=self.n_messages,\n )\n .retrieve_messages()\n )\n return [\n message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n ]\n\n async def get_llm(self):\n if not isinstance(self.agent_llm, str):\n return self.agent_llm, None\n\n try:\n provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n if not provider_info:\n msg = f\"Invalid model provider: {self.agent_llm}\"\n raise ValueError(msg)\n\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\n return self._build_llm_model(component_class, inputs, prefix), display_name\n\n except (AttributeError, ValueError, TypeError, RuntimeError) as e:\n await logger.aerror(f\"Error building {self.agent_llm} language model: {e!s}\")\n msg = f\"Failed to initialize language model: {e!s}\"\n raise ValueError(msg) from e\n\n def _build_llm_model(self, component, inputs, prefix=\"\"):\n model_kwargs = {}\n for input_ in inputs:\n if hasattr(self, f\"{prefix}{input_.name}\"):\n model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\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 # Filter out json_mode and only use attributes that exist on this component\n model_kwargs = {}\n for input_ in inputs:\n if hasattr(self, f\"{prefix}{input_.name}\"):\n model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\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 build_config[\"agent_llm\"][\"value\"] = field_value\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, \"model_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 build_config[\"agent_llm\"][\"display_name\"] = \"Model Provider\"\n elif field_value == \"connect_other_models\":\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 info=\"The provider of the language model that the agent will use to generate responses.\",\n options=[*MODEL_PROVIDERS_LIST],\n real_time_refresh=True,\n refresh_button=False,\n input_types=[\"LanguageModel\"],\n placeholder=\"Awaiting model input.\",\n options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST],\n external_options={\n \"fields\": {\n \"data\": {\n \"node\": {\n \"name\": \"connect_other_models\",\n \"display_name\": \"Connect other models\",\n \"icon\": \"CornerDownLeft\",\n },\n }\n },\n },\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, \"model_name\"\n )\n return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n async def _get_tools(self) -> list[Tool]:\n component_toolkit = _get_component_toolkit()\n tools_names = self._build_tools_names()\n agent_description = self.get_tool_description()\n # TODO: Agent Description Depreciated Feature to be removed\n description = f\"{agent_description}{tools_names}\"\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n tool_description=description,\n callbacks=self.get_langchain_callbacks(),\n )\n if hasattr(self, \"tools_metadata\"):\n tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n return tools\n" }, "format_instructions": { "_input_type": "MultilineInput", "advanced": true, "copy_field": false, "display_name": "Output Format Instructions", "dynamic": false, "info": "Generic Template for structured output formatting. Valid only with Structured response.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "format_instructions", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "You are an AI that extracts structured JSON objects from unstructured text. Use a predefined schema with expected types (str, int, float, bool, dict). Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. Fill missing or ambiguous values with defaults: null for missing values. Remove exact duplicates but keep variations that have different field values. Always return valid JSON in the expected format, never throw errors. If multiple objects can be extracted, return them all in the structured format." }, "handle_parsing_errors": { "_input_type": "BoolInput", "advanced": true, "display_name": "Handle Parse Errors", "dynamic": false, "info": "Should the Agent fix errors when reading user input for better processing?", "list": false, "list_add_label": "Add More", "name": "handle_parsing_errors", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true }, "input_value": { "_input_type": "MessageTextInput", "advanced": false, "display_name": "Input", "dynamic": false, "info": "The input provided by the user for the agent to process.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "input_value", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": true, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "" }, "max_iterations": { "_input_type": "IntInput", "advanced": true, "display_name": "Max Iterations", "dynamic": false, "info": "The maximum number of attempts the agent can make to complete its task before it stops.", "list": false, "list_add_label": "Add More", "name": "max_iterations", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 15 }, "max_retries": { "_input_type": "IntInput", "advanced": true, "display_name": "Max Retries", "dynamic": false, "info": "The maximum number of retries to make when generating.", "list": false, "list_add_label": "Add More", "name": "max_retries", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 5 }, "max_tokens": { "_input_type": "IntInput", "advanced": true, "display_name": "Max Tokens", "dynamic": false, "info": "The maximum number of tokens to generate. Set to 0 for unlimited tokens.", "list": false, "list_add_label": "Add More", "name": "max_tokens", "placeholder": "", "range_spec": { "max": 128000, "min": 0, "step": 0.1, "step_type": "float" }, "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": "" }, "model_kwargs": { "_input_type": "DictInput", "advanced": true, "display_name": "Model Kwargs", "dynamic": false, "info": "Additional keyword arguments to pass to the model.", "list": false, "list_add_label": "Add More", "name": "model_kwargs", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "type": "dict", "value": {} }, "model_name": { "_input_type": "DropdownInput", "advanced": false, "combobox": true, "dialog_inputs": {}, "display_name": "Model Name", "dynamic": false, "info": "To see the model names, first choose a provider. Then, enter your API key and click the refresh button next to the model name.", "load_from_db": false, "name": "model_name", "options": [ "gpt-4o-mini", "gpt-4o", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "gpt-4-turbo", "gpt-4-turbo-preview", "gpt-4", "gpt-3.5-turbo", "gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-5-chat-latest", "o1", "o3-mini", "o3", "o3-pro", "o4-mini", "o4-mini-high" ], "options_metadata": [], "placeholder": "", "real_time_refresh": false, "required": false, "show": true, "title_case": false, "toggle": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "gpt-4.1" }, "n_messages": { "_input_type": "IntInput", "advanced": true, "display_name": "Number of Chat History Messages", "dynamic": false, "info": "Number of chat history messages to retrieve.", "list": false, "list_add_label": "Add More", "name": "n_messages", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 100 }, "openai_api_base": { "_input_type": "StrInput", "advanced": true, "display_name": "OpenAI API Base", "dynamic": false, "info": "The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.", "list": false, "list_add_label": "Add More", "load_from_db": false, "name": "openai_api_base", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "str", "value": "" }, "output_schema": { "_input_type": "TableInput", "advanced": true, "display_name": "Output Schema", "dynamic": false, "info": "Schema Validation: Define the structure and data types for structured output. No validation if no output schema.", "is_list": true, "list_add_label": "Add More", "name": "output_schema", "placeholder": "", "required": false, "show": true, "table_icon": "Table", "table_schema": { "columns": [ { "default": "field", "description": "Specify the name of the output field.", "disable_edit": false, "display_name": "Name", "edit_mode": "inline", "filterable": true, "formatter": "text", "hidden": false, "name": "name", "sortable": true, "type": "str" }, { "default": "description of field", "description": "Describe the purpose of the output field.", "disable_edit": false, "display_name": "Description", "edit_mode": "popover", "filterable": true, "formatter": "text", "hidden": false, "name": "description", "sortable": true, "type": "str" }, { "default": "str", "description": "Indicate the data type of the output field (e.g., str, int, float, bool, dict).", "disable_edit": false, "display_name": "Type", "edit_mode": "inline", "filterable": true, "formatter": "text", "hidden": false, "name": "type", "options": [ "str", "int", "float", "bool", "dict" ], "sortable": true, "type": "str" }, { "default": false, "description": "Set to True if this output field should be a list of the specified type.", "disable_edit": false, "display_name": "As List", "edit_mode": "inline", "filterable": true, "formatter": "boolean", "hidden": false, "name": "multiple", "sortable": true, "type": "boolean" } ] }, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "trigger_icon": "Table", "trigger_text": "Open table", "type": "table", "value": [] }, "seed": { "_input_type": "IntInput", "advanced": true, "display_name": "Seed", "dynamic": false, "info": "The seed controls the reproducibility of the job.", "list": false, "list_add_label": "Add More", "name": "seed", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 1 }, "system_prompt": { "_input_type": "MultilineInput", "advanced": false, "copy_field": false, "display_name": "Agent Instructions", "dynamic": false, "info": "System Prompt: Initial instructions and context provided to guide the agent's behavior.", "input_types": [ "Message" ], "list": false, "list_add_label": "Add More", "load_from_db": false, "multiline": true, "name": "system_prompt", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_input": true, "trace_as_metadata": true, "type": "str", "value": "You are a helpful assistant that can use tools to answer questions and perform tasks." }, "temperature": { "_input_type": "SliderInput", "advanced": true, "display_name": "Temperature", "dynamic": false, "info": "", "max_label": "", "max_label_icon": "", "min_label": "", "min_label_icon": "", "name": "temperature", "placeholder": "", "range_spec": { "max": 1, "min": 0, "step": 0.01, "step_type": "float" }, "required": false, "show": true, "slider_buttons": false, "slider_buttons_options": [], "slider_input": false, "title_case": false, "tool_mode": false, "type": "slider", "value": 0.1 }, "timeout": { "_input_type": "IntInput", "advanced": true, "display_name": "Timeout", "dynamic": false, "info": "The timeout for requests to OpenAI completion API.", "list": false, "list_add_label": "Add More", "name": "timeout", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "int", "value": 700 }, "tools": { "_input_type": "HandleInput", "advanced": false, "display_name": "Tools", "dynamic": false, "info": "These are the tools that the agent can use to help with tasks.", "input_types": [ "Tool" ], "list": true, "list_add_label": "Add More", "name": "tools", "placeholder": "", "required": false, "show": true, "title_case": false, "trace_as_metadata": true, "type": "other", "value": "" }, "verbose": { "_input_type": "BoolInput", "advanced": true, "display_name": "Verbose", "dynamic": false, "info": "", "list": false, "list_add_label": "Add More", "name": "verbose", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", "value": true } }, "tool_mode": false }, "selected_output": "response", "showNode": true, "type": "Agent" }, "dragging": false, "id": "Agent-0vMrI", "measured": { "height": 594, "width": 320 }, "position": { "x": 1023.5315500182937, "y": 280.6548808097231 }, "selected": true, "type": "genericNode" } ], "viewport": { "x": 281.02651297047544, "y": 209.9438393445942, "zoom": 0.6868478679218015 } }, "description": "Utilize Apify Actors as agent tools to search and analyze social media profiles.", "endpoint_name": null, "id": "6c13c359-1078-452d-acdb-863aedd98e23", "is_component": false, "last_tested_version": "1.4.3", "name": "Social Media Agent", "tags": [ "agent", "assistants" ] }