WORKFLOWFree BlueprintLicense: MIT
Workflow to Langflow Graph to Portfolio Website Code Generator
Workflow to Langflow Graph to Portfolio Website Code Generator is a verified WORKFLOW blueprint on Promptally in Make.com & Langflow Graphs optimized for leading AI models. Multi-step automated node blueprint for Langflow Graph to Portfolio Website Code Generator. Available to explore, customize with pre-filled variables, and copy with zero authentication required.
Created by @promptallyTechnical Specifications
| Specification | Value |
|---|---|
| Artifact type | WORKFLOW (Make.com & Langflow Graphs) |
| Compatible engines | Universal / Model Agnostic |
| Input variables | None (pre-filled) |
| Approximate tokens | 52,730 |
| Source file | Portfolio Website Code Generator.json |
| Access tier | Free public (MIT) |
Pre-Filled Template
Portfolio Website Code Generator.json
{
"data": {
"edges": [
{
"animated": false,
"className": "",
"data": {
"sourceHandle": {
"dataType": "File",
"id": "File-wvfA7",
"name": "message",
"output_types": [
"Message"
]
},
"targetHandle": {
"fieldName": "input_value",
"id": "Agent-portfolio",
"inputTypes": [
"Message"
],
"type": "str"
}
},
"id": "reactflow__edge-File-wvfA7{\u0153dataType\u0153:\u0153File\u0153,\u0153id\u0153:\u0153File-wvfA7\u0153,\u0153name\u0153:\u0153message\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-Agent-portfolio{\u0153fieldName\u0153:\u0153input_value\u0153,\u0153id\u0153:\u0153Agent-portfolio\u0153,\u0153inputTypes\u0153:[\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}",
"selected": false,
"source": "File-wvfA7",
"sourceHandle": "{\u0153dataType\u0153: \u0153File\u0153, \u0153id\u0153: \u0153File-wvfA7\u0153, \u0153name\u0153: \u0153message\u0153, \u0153output_types\u0153: [\u0153Message\u0153]}",
"target": "Agent-portfolio",
"targetHandle": "{\u0153fieldName\u0153: \u0153input_value\u0153, \u0153id\u0153: \u0153Agent-portfolio\u0153, \u0153inputTypes\u0153: [\u0153Message\u0153], \u0153type\u0153: \u0153str\u0153}"
},
{
"animated": false,
"className": "",
"data": {
"sourceHandle": {
"dataType": "Agent",
"id": "Agent-portfolio",
"name": "response",
"output_types": [
"Message"
]
},
"targetHandle": {
"fieldName": "input_value",
"id": "ChatOutput-ZuZUq",
"inputTypes": [
"Data",
"JSON",
"DataFrame",
"Table",
"Message"
],
"type": "str"
}
},
"id": "reactflow__edge-Agent-portfolio{\u0153dataType\u0153:\u0153Agent\u0153,\u0153id\u0153:\u0153Agent-portfolio\u0153,\u0153name\u0153:\u0153response\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-ChatOutput-ZuZUq{\u0153fieldName\u0153:\u0153input_value\u0153,\u0153id\u0153:\u0153ChatOutput-ZuZUq\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153JSON\u0153,\u0153DataFrame\u0153,\u0153Table\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}",
"selected": false,
"source": "Agent-portfolio",
"sourceHandle": "{\u0153dataType\u0153: \u0153Agent\u0153, \u0153id\u0153: \u0153Agent-portfolio\u0153, \u0153name\u0153: \u0153response\u0153, \u0153output_types\u0153: [\u0153Message\u0153]}",
"target": "ChatOutput-ZuZUq",
"targetHandle": "{\u0153fieldName\u0153: \u0153input_value\u0153, \u0153id\u0153: \u0153ChatOutput-ZuZUq\u0153, \u0153inputTypes\u0153: [\u0153Data\u0153, \u0153JSON\u0153, \u0153DataFrame\u0153, \u0153Table\u0153, \u0153Message\u0153], \u0153type\u0153: \u0153str\u0153}"
}
],
"nodes": [
{
"data": {
"id": "ChatOutput-ZuZUq",
"node": {
"base_classes": [
"Message"
],
"beta": false,
"category": "outputs",
"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",
"context_id",
"data_template",
"clean_data"
],
"frozen": false,
"icon": "MessagesSquare",
"key": "ChatOutput",
"legacy": false,
"lf_version": "1.6.0",
"metadata": {
"code_hash": "0aab1c78e1dc",
"component_class_name": "ChatOutput",
"dependencies": {
"dependencies": [
{
"name": "orjson",
"version": "3.11.9"
},
{
"name": "fastapi",
"version": "0.139.2"
},
{
"name": "lfx",
"version": null
}
],
"total_dependencies": 3
},
"module": "lfx.components.input_output.chat_output.ChatOutput"
},
"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,
"score": 0.003169567463043492,
"template": {
"_type": "Component",
"clean_data": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Basic Clean Data",
"dynamic": false,
"info": "Whether to clean data before converting to string.",
"list": false,
"list_add_label": "Add More",
"name": "clean_data",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"code": {
"advanced": true,
"api_editable": false,
"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 lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.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/chat-input-and-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\", \"JSON\", \"DataFrame\", \"Table\", \"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=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\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 BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\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, _, 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) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n # Preserve existing session_id from the incoming message if it exists\n existing_session_id = message.session_id\n else:\n message = Message(text=text)\n existing_session_id = None\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n # Preserve session_id from incoming message, or use component/graph session_id\n message.session_id = (\n self.session_id or existing_session_id or (self.graph.session_id if hasattr(self, \"graph\") else None) or \"\"\n )\n message.context_id = self.context_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 message.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 # Set accumulated token usage from all upstream LLM vertices.\n # This must happen AFTER send_message() because streaming captures\n # usage from chunks and would overwrite accumulated totals.\n if hasattr(self, \"_vertex\") and self._vertex is not None:\n accumulated_usage = self._vertex._accumulate_upstream_token_usage() # noqa: SLF001\n if accumulated_usage:\n message.properties.usage = accumulated_usage\n if self.should_store_message and message.get_id():\n message = await self._update_stored_message(message)\n await self._send_message_event(message, id_=message.get_id())\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 clean_data: bool = getattr(self, \"clean_data\", False)\n if isinstance(self.input_value, list):\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, clean_data=clean_data)\n"
},
"context_id": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Context ID",
"dynamic": false,
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "context_id",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"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": "MessageInput",
"advanced": false,
"display_name": "Inputs",
"dynamic": false,
"info": "Message to be passed as output.",
"input_types": [
"Data",
"JSON",
"DataFrame",
"Table",
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "input_value",
"placeholder": "",
"required": true,
"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": "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-ZuZUq",
"measured": {
"height": 52,
"width": 192
},
"position": {
"x": 2791.628210329036,
"y": 590.4917809253919
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"id": "File-wvfA7",
"node": {
"base_classes": [
"Message"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
"description": "Loads and returns the content from uploaded files.",
"display_name": "Read File",
"documentation": "",
"edited": false,
"field_order": [
"storage_location",
"path",
"file_path",
"separator",
"silent_errors",
"delete_server_file_after_processing",
"ignore_unsupported_extensions",
"ignore_unspecified_files",
"text_encoding",
"file_path_str",
"aws_access_key_id",
"aws_secret_access_key",
"bucket_name",
"aws_region",
"s3_file_key",
"service_account_key",
"file_id",
"advanced_mode",
"pipeline",
"ocr_engine",
"md_image_placeholder",
"md_page_break_placeholder",
"doc_key",
"use_multithreading",
"concurrency_multithreading",
"markdown"
],
"frozen": false,
"icon": "file-text",
"last_updated": "2026-06-25T14:47:49.919Z",
"legacy": false,
"lf_version": "1.10.0",
"metadata": {
"code_hash": "196bbc1a65f8",
"component_class_name": "FileComponent",
"dependencies": {
"dependencies": [
{
"name": "lfx",
"version": null
},
{
"name": "langchain_core",
"version": "1.5.1"
},
{
"name": "pydantic",
"version": "2.13.4"
},
{
"name": "googleapiclient",
"version": "2.198.0"
}
],
"total_dependencies": 4
},
"module": "lfx.components.files_and_knowledge.file.FileComponent"
},
"minimized": false,
"output_types": [],
"outputs": [
{
"allows_loop": false,
"cache": true,
"display_name": "Raw Content",
"group_outputs": false,
"method": "load_files_message",
"name": "message",
"selected": "Message",
"tool_mode": true,
"types": [
"Message"
],
"value": "__UNDEFINED__"
}
],
"pinned": false,
"template": {
"_type": "Component",
"advanced_mode": {
"_input_type": "BoolInput",
"advanced": false,
"display_name": "Advanced Parser",
"dynamic": false,
"info": "Enable advanced document processing and export with Docling for PDFs, images, and office documents. Note that advanced document processing can consume significant resources.",
"list": false,
"list_add_label": "Add More",
"name": "advanced_mode",
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"aws_access_key_id": {
"_input_type": "SecretStrInput",
"advanced": false,
"display_name": "AWS Access Key ID",
"dynamic": false,
"info": "AWS Access key ID.",
"input_types": [],
"load_from_db": false,
"name": "aws_access_key_id",
"override_skip": false,
"password": true,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"aws_region": {
"_input_type": "StrInput",
"advanced": false,
"display_name": "AWS Region",
"dynamic": false,
"info": "AWS region (e.g., us-east-1, eu-west-1).",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "aws_region",
"override_skip": false,
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"aws_secret_access_key": {
"_input_type": "SecretStrInput",
"advanced": false,
"display_name": "AWS Secret Key",
"dynamic": false,
"info": "AWS Secret Key.",
"input_types": [],
"load_from_db": false,
"name": "aws_secret_access_key",
"override_skip": false,
"password": true,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"bucket_name": {
"_input_type": "StrInput",
"advanced": false,
"display_name": "S3 Bucket Name",
"dynamic": false,
"info": "Enter the name of the S3 bucket.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "bucket_name",
"override_skip": false,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"code": {
"advanced": true,
"api_editable": false,
"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": "\"\"\"Enhanced file component with Docling support and process isolation.\n\nNotes:\n-----\n- ALL Docling parsing/export runs in a separate OS process to prevent memory\n growth and native library state from impacting the main Langflow process.\n- Standard text/structured parsing continues to use existing BaseFileComponent\n utilities, bounded by `concurrency_multithreading` via `aparallel_load_data`.\n- The loaders are coroutines (see BaseFileComponent): storage reads are awaited on\n the caller's event loop, parsing and the Docling subprocess run in worker threads.\n\"\"\"\n\nfrom __future__ import annotations\n\nimport asyncio\nimport contextlib\nimport json\nimport subprocess\nimport sys\nimport textwrap\nimport threading\nimport time\nfrom contextvars import ContextVar\nfrom copy import deepcopy\nfrom pathlib import Path\nfrom tempfile import NamedTemporaryFile\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.storage_utils import (\n parse_storage_path,\n read_file_bytes,\n require_storage_service,\n validate_image_content_type,\n)\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, aparallel_load_data, aparse_text_file_to_data\nfrom lfx.inputs import SortableListInput\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output, SecretStrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame # noqa: TC001\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_settings_service, get_storage_service\nfrom lfx.utils.async_helpers import delegates_to, run_until_complete\nfrom lfx.utils.validate_cloud import is_astra_cloud_environment\n\n_FILE_TOOL_CANCEL_EVENT: ContextVar[threading.Event | None] = ContextVar(\"file_tool_cancel_event\", default=None)\n_FILE_TOOL_CANCEL_WAIT_SECONDS = 6\n_FILE_TOOL_MAX_CONCURRENT_LOADS = 4\n_FILE_TOOL_LIMITER_ATTRIBUTE = \"_lfx_file_tool_load_limiter\"\n_FILE_TOOL_PROCESS_REAP_SECONDS = 2\n\n\nclass _FileToolCancelledError(RuntimeError):\n \"\"\"Stop synchronous file loading after its async tool call is cancelled.\"\"\"\n\n\ndef _raise_if_file_tool_cancelled(cancel_event: threading.Event | None = None) -> None:\n event = cancel_event or _FILE_TOOL_CANCEL_EVENT.get()\n if event is not None and event.is_set():\n raise _FileToolCancelledError\n\n\ndef _kill_and_reap_process(proc: subprocess.Popen) -> None:\n try:\n proc.kill()\n except ProcessLookupError:\n pass\n except OSError:\n logger.exception(\"Failed to kill cancelled Docling subprocess\")\n except Exception: # noqa: BLE001 - cleanup must not mask the caller's cancellation\n logger.exception(\"Unexpected error while killing cancelled Docling subprocess\")\n\n try:\n proc.communicate(timeout=_FILE_TOOL_PROCESS_REAP_SECONDS)\n except subprocess.TimeoutExpired:\n logger.warning(\"Timed out draining cancelled Docling subprocess; waiting for process exit\")\n except OSError:\n logger.exception(\"Failed to drain cancelled Docling subprocess\")\n except Exception: # noqa: BLE001 - cleanup must not mask the caller's cancellation\n logger.exception(\"Unexpected error while draining cancelled Docling subprocess\")\n else:\n return\n\n try:\n proc.wait(timeout=_FILE_TOOL_PROCESS_REAP_SECONDS)\n except subprocess.TimeoutExpired:\n logger.exception(\"Cancelled Docling subprocess could not be reaped within the cleanup timeout\")\n except OSError:\n logger.exception(\"Failed to reap cancelled Docling subprocess\")\n except Exception: # noqa: BLE001 - cleanup must not mask the caller's cancellation\n logger.exception(\"Unexpected error while reaping cancelled Docling subprocess\")\n\n\ndef _get_file_tool_limiter() -> asyncio.Semaphore:\n \"\"\"Return the bounded loader admission gate for the current event loop.\"\"\"\n loop = asyncio.get_running_loop()\n limiter = getattr(loop, _FILE_TOOL_LIMITER_ATTRIBUTE, None)\n if limiter is None:\n limiter = asyncio.Semaphore(_FILE_TOOL_MAX_CONCURRENT_LOADS)\n setattr(loop, _FILE_TOOL_LIMITER_ATTRIBUTE, limiter)\n return limiter\n\n\ndef _log_abandoned_file_loader_result(task: asyncio.Task) -> None:\n \"\"\"Observe unexpected failures from a synchronous loader that outlived its caller.\"\"\"\n try:\n error = task.exception()\n except asyncio.CancelledError:\n return\n if error is not None and not isinstance(error, _FileToolCancelledError):\n logger.error(\"Abandoned file loader failed after its caller was cancelled\", exc_info=error)\n\n\ndef _write_temp_file(content: bytes, suffix: str) -> str:\n with NamedTemporaryFile(mode=\"wb\", suffix=suffix, delete=False) as tmp_file:\n tmp_file.write(content)\n return tmp_file.name\n\n\ndef _unlink_orphaned_temp_file(write: asyncio.Future[str]) -> None:\n \"\"\"Remove a temp file whose writer finished after the awaiting coroutine was cancelled.\"\"\"\n if write.cancelled() or write.exception() is not None:\n return\n with contextlib.suppress(OSError):\n Path(write.result()).unlink()\n\n\nasync def _wait_for_cancelled_file_tool_loader(loader_task: asyncio.Task) -> None:\n \"\"\"Give a cancelled tool call's loader time to clean up, without cancelling it.\n\n This waits with ``asyncio.wait`` rather than ``asyncio.shield``. On Python 3.14, a\n shield whose outer future is cancelled reports the inner task's eventual exception to\n the loop's exception handler, which logged the expected ``_FileToolCancelledError`` as\n an ERROR on every cancelled tool call.\n \"\"\"\n try:\n await asyncio.wait({loader_task}, timeout=_FILE_TOOL_CANCEL_WAIT_SECONDS)\n finally:\n if not loader_task.done():\n loader_task.add_done_callback(_log_abandoned_file_loader_result)\n elif not loader_task.cancelled():\n error = loader_task.exception()\n if error is not None and not isinstance(error, _FileToolCancelledError):\n logger.error(\"File loader failed while cleaning up a cancelled tool call\", exc_info=error)\n\n\ndef _get_storage_location_options():\n \"\"\"Get storage location options, filtering out Local if in Astra cloud environment.\"\"\"\n all_options = [{\"name\": \"AWS\", \"icon\": \"Amazon\"}, {\"name\": \"Google Drive\", \"icon\": \"google\"}]\n if is_astra_cloud_environment():\n return all_options\n return [{\"name\": \"Local\", \"icon\": \"hard-drive\"}, *all_options]\n\n\nclass FileComponent(BaseFileComponent):\n \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n display_name = \"Read File\"\n # description is now a dynamic property - see get_tool_description()\n _base_description = \"Loads and returns the content from uploaded files.\"\n documentation: str = \"https://docs.langflow.org/read-file\"\n icon = \"file-text\"\n name = \"File\"\n add_tool_output = True # Enable tool mode toggle without requiring tool_mode inputs\n\n # Extensions that can be processed without Docling (using standard text parsing)\n TEXT_EXTENSIONS = TEXT_FILE_TYPES\n\n # Extensions that require Docling for processing (images, advanced office formats, etc.)\n DOCLING_ONLY_EXTENSIONS = [\n \"adoc\",\n \"asciidoc\",\n \"asc\",\n \"bmp\",\n \"dotx\",\n \"dotm\",\n \"docm\",\n \"jpg\",\n \"jpeg\",\n \"png\",\n \"potx\",\n \"ppsx\",\n \"pptm\",\n \"potm\",\n \"ppsm\",\n \"pptx\",\n \"tiff\",\n \"xls\",\n \"xlsx\",\n \"xhtml\",\n \"webp\",\n ]\n\n # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n VALID_EXTENSIONS = [\n *TEXT_EXTENSIONS,\n *DOCLING_ONLY_EXTENSIONS,\n ]\n\n # Fixed export settings used when markdown export is requested.\n EXPORT_FORMAT = \"Markdown\"\n IMAGE_MODE = \"placeholder\"\n\n _base_inputs = deepcopy(BaseFileComponent.get_base_inputs())\n\n for input_item in _base_inputs:\n if isinstance(input_item, FileInput) and input_item.name == \"path\":\n input_item.real_time_refresh = True\n input_item.tool_mode = False # Disable tool mode for file upload input\n input_item.required = False # Make it optional so it doesn't error in tool mode\n break\n\n inputs = [\n SortableListInput(\n name=\"storage_location\",\n display_name=\"Storage Location\",\n placeholder=\"Select Location\",\n info=\"Choose where to read the file from.\",\n options=_get_storage_location_options(),\n real_time_refresh=True,\n limit=1,\n value=[{\"name\": \"Local\", \"icon\": \"hard-drive\"}],\n advanced=True,\n ),\n *_base_inputs,\n StrInput(\n name=\"text_encoding\",\n display_name=\"Text Encoding\",\n value=\"\",\n advanced=True,\n info=(\n \"Leave blank to detect encoding automatically for standard text parsing, which reports the selected \"\n \"encoding in logs and raw output metadata. For structured CSV output, leaving this blank uses the \"\n \"parser default. If accents or punctuation look incorrect, enter the file's encoding, such as cp1252 \"\n \"or utf-8. The CSV reader uses the selected encoding but does not add it to structured output \"\n \"metadata. Applies to standard text parsing and CSV, not PDF, DOCX, or the Advanced Parser.\"\n ),\n ),\n StrInput(\n name=\"file_path_str\",\n display_name=\"File Path\",\n info=(\n \"Path to the file to read. Used when component is called as a tool. \"\n \"If not provided, will use the uploaded file from 'path' input.\"\n ),\n show=False,\n advanced=True,\n tool_mode=True, # Required for Toolset toggle, but _get_tools() ignores this parameter\n required=False,\n ),\n # AWS S3 specific inputs\n SecretStrInput(\n name=\"aws_access_key_id\",\n display_name=\"AWS Access Key ID\",\n info=\"AWS Access key ID.\",\n show=False,\n advanced=False,\n required=True,\n ),\n SecretStrInput(\n name=\"aws_secret_access_key\",\n display_name=\"AWS Secret Key\",\n info=\"AWS Secret Key.\",\n show=False,\n advanced=False,\n required=True,\n ),\n StrInput(\n name=\"bucket_name\",\n display_name=\"S3 Bucket Name\",\n info=\"Enter the name of the S3 bucket.\",\n show=False,\n advanced=False,\n required=True,\n ),\n StrInput(\n name=\"aws_region\",\n display_name=\"AWS Region\",\n info=\"AWS region (e.g., us-east-1, eu-west-1).\",\n show=False,\n advanced=False,\n ),\n StrInput(\n name=\"s3_file_key\",\n display_name=\"S3 File Key\",\n info=\"The key (path) of the file in S3 bucket.\",\n show=False,\n advanced=False,\n required=True,\n ),\n # Google Drive specific inputs\n SecretStrInput(\n name=\"service_account_key\",\n display_name=\"GCP Credentials Secret Key\",\n info=\"Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).\",\n show=False,\n advanced=False,\n required=True,\n ),\n StrInput(\n name=\"file_id\",\n display_name=\"Google Drive File ID\",\n info=(\"The Google Drive file ID to read. The file must be shared with the service account email.\"),\n show=False,\n advanced=False,\n required=True,\n ),\n BoolInput(\n name=\"advanced_mode\",\n display_name=\"Advanced Parser\",\n value=False,\n real_time_refresh=True,\n info=(\n \"Enable advanced document processing and export with Docling for PDFs, images, and office documents. \"\n \"Note that advanced document processing can consume significant resources.\"\n ),\n # Disabled in cloud\n show=not is_astra_cloud_environment(),\n ),\n DropdownInput(\n name=\"pipeline\",\n display_name=\"Pipeline\",\n info=\"Docling pipeline to use\",\n options=[\"standard\", \"vlm\"],\n value=\"standard\",\n advanced=True,\n real_time_refresh=True,\n ),\n DropdownInput(\n name=\"ocr_engine\",\n display_name=\"OCR Engine\",\n info=\"OCR engine to use. Only available when pipeline is set to 'standard'.\",\n options=[\"None\", \"easyocr\"],\n value=\"easyocr\",\n show=False,\n advanced=True,\n ),\n StrInput(\n name=\"md_image_placeholder\",\n display_name=\"Image placeholder\",\n info=\"Specify the image placeholder for markdown exports.\",\n value=\"<!-- image -->\",\n advanced=True,\n show=False,\n ),\n StrInput(\n name=\"md_page_break_placeholder\",\n display_name=\"Page break placeholder\",\n info=\"Add this placeholder between pages in the markdown output.\",\n value=\"\",\n advanced=True,\n show=False,\n ),\n MessageTextInput(\n name=\"doc_key\",\n display_name=\"Doc Key\",\n info=\"The key to use for the DoclingDocument column.\",\n value=\"doc\",\n advanced=True,\n show=False,\n ),\n # Deprecated input retained for backward-compatibility.\n BoolInput(\n name=\"use_multithreading\",\n display_name=\"[Deprecated] Use Multithreading\",\n advanced=True,\n value=True,\n info=\"Set 'Processing Concurrency' greater than 1 to enable multithreading.\",\n ),\n IntInput(\n name=\"concurrency_multithreading\",\n display_name=\"Processing Concurrency\",\n advanced=True,\n info=\"When multiple files are being processed, the number of files to process concurrently.\",\n value=1,\n ),\n BoolInput(\n name=\"markdown\",\n display_name=\"Markdown Export\",\n info=\"Export processed documents to Markdown format. Only available when advanced mode is enabled.\",\n value=False,\n show=False,\n ),\n ]\n\n outputs = [\n Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\", tool_mode=True),\n ]\n\n # ------------------------------ Tool description with file names --------------\n\n def get_tool_description(self) -> str:\n \"\"\"Return a dynamic description that includes the names of uploaded files.\n\n This helps the Agent understand which files are available to read.\n \"\"\"\n base_description = type(self)._base_description # noqa: SLF001\n\n # Get the list of uploaded file paths\n file_paths = getattr(self, \"path\", None)\n if not file_paths:\n return base_description\n\n # Ensure it's a list\n if not isinstance(file_paths, list):\n file_paths = [file_paths]\n\n # Extract just the file names from the paths\n file_names = []\n for fp in file_paths:\n if fp:\n name = Path(fp).name\n file_names.append(name)\n\n if file_names:\n files_str = \", \".join(file_names)\n return f\"{base_description} Available files: {files_str}. Call this tool to read these files.\"\n\n return base_description\n\n @property\n def description(self) -> str:\n \"\"\"Dynamic description property that includes uploaded file names.\"\"\"\n return self.get_tool_description()\n\n async def _get_tools(self) -> list:\n \"\"\"Override to create a tool without parameters.\n\n The Read File component should use the files already uploaded via UI,\n not accept file paths from the Agent (which wouldn't know the internal paths).\n \"\"\"\n from langchain_core.tools import StructuredTool\n from pydantic import BaseModel\n\n # Empty schema - no parameters needed\n class EmptySchema(BaseModel):\n \"\"\"No parameters required - uses pre-uploaded files.\"\"\"\n\n async def read_files_tool() -> str:\n \"\"\"Read the content of uploaded files.\"\"\"\n cancel_event = threading.Event()\n cancel_token = _FILE_TOOL_CANCEL_EVENT.set(cancel_event)\n try:\n if getattr(self, \"advanced_mode\", False):\n # In advanced mode, use the markdown output path so that the\n # tool shares the same Docling processing as the advanced\n # outputs rather than triggering a second subprocess via\n # load_files_message.\n self.markdown = True\n loader_name = \"load_files_markdown\"\n else:\n loader_name = \"load_files_message\"\n # Await the async loader chain on this loop: storage reads are awaited here,\n # while parsing and the Docling subprocess run in worker threads, so\n # streaming/heartbeats on the same loop keep flowing while the agent waits.\n # A subclass that overrides the sync loader still has it run in a thread.\n # Keep admission bounded until the real work exits so cancelled parsers\n # cannot build an unbounded default-executor backlog.\n load_limiter = _get_file_tool_limiter()\n await load_limiter.acquire()\n try:\n loader_task = asyncio.create_task(self._adispatch(loader_name))\n except BaseException:\n load_limiter.release()\n raise\n loader_task.add_done_callback(lambda _task: load_limiter.release())\n try:\n # asyncio.wait neither cancels the loader nor leaves an orphaned\n # shield behind to report its outcome if this call is cancelled.\n await asyncio.wait({loader_task})\n # A cancelled loader task raises CancelledError here while its\n # worker thread keeps running, so it takes the same path below.\n result = loader_task.result()\n except asyncio.CancelledError:\n cancel_event.set()\n # Give cooperative cleanup time to kill/reap Docling and remove\n # temporary files before releasing this tool invocation.\n await _wait_for_cancelled_file_tool_loader(loader_task)\n raise\n if hasattr(result, \"get_text\"):\n return result.get_text()\n if hasattr(result, \"text\"):\n return result.text\n return str(result)\n except (FileNotFoundError, ValueError, OSError, RuntimeError) as e:\n return f\"Error reading files: {e}\"\n finally:\n _FILE_TOOL_CANCEL_EVENT.reset(cancel_token)\n\n description = self.get_tool_description()\n\n tool = StructuredTool(\n name=\"load_files_message\",\n description=description,\n coroutine=read_files_tool,\n args_schema=EmptySchema,\n handle_tool_error=True,\n tags=[\"load_files_message\"],\n metadata={\n \"display_name\": \"Read File\",\n \"display_description\": description,\n },\n )\n\n return [tool]\n\n # ------------------------------ UI helpers --------------------------------------\n\n def _path_value(self, template: dict) -> list[str]:\n \"\"\"Return the list of currently selected file paths from the template.\"\"\"\n return template.get(\"path\", {}).get(\"file_path\", [])\n\n def _disable_docling_fields_in_cloud(self, build_config: dict[str, Any]) -> None:\n \"\"\"Disable all Docling-related fields in cloud environments.\"\"\"\n if \"advanced_mode\" in build_config:\n build_config[\"advanced_mode\"][\"show\"] = False\n build_config[\"advanced_mode\"][\"value\"] = False\n # Hide all Docling-related fields\n docling_fields = (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\")\n for field in docling_fields:\n if field in build_config:\n build_config[field][\"show\"] = False\n # Also disable OCR engine specifically\n if \"ocr_engine\" in build_config:\n build_config[\"ocr_engine\"][\"value\"] = \"None\"\n\n def update_build_config(\n self,\n build_config: dict[str, Any],\n field_value: Any,\n field_name: str | None = None,\n ) -> dict[str, Any]:\n \"\"\"Show/hide Advanced Parser and related fields based on selection context.\"\"\"\n # Update storage location options dynamically based on cloud environment\n if \"storage_location\" in build_config:\n updated_options = _get_storage_location_options()\n build_config[\"storage_location\"][\"options\"] = updated_options\n\n # Handle storage location selection\n if field_name == \"storage_location\":\n # Extract selected storage location\n selected = [location[\"name\"] for location in field_value] if isinstance(field_value, list) else []\n\n # Hide all storage-specific fields first\n storage_fields = [\n \"aws_access_key_id\",\n \"aws_secret_access_key\",\n \"bucket_name\",\n \"aws_region\",\n \"s3_file_key\",\n \"service_account_key\",\n \"file_id\",\n ]\n\n for f_name in storage_fields:\n if f_name in build_config:\n build_config[f_name][\"show\"] = False\n\n # Show fields based on selected storage location\n if len(selected) == 1:\n location = selected[0]\n\n if location == \"Local\":\n # Show file upload input for local storage\n if \"path\" in build_config:\n build_config[\"path\"][\"show\"] = True\n\n elif location == \"AWS\":\n # Hide file upload input, show AWS fields\n if \"path\" in build_config:\n build_config[\"path\"][\"show\"] = False\n\n aws_fields = [\n \"aws_access_key_id\",\n \"aws_secret_access_key\",\n \"bucket_name\",\n \"aws_region\",\n \"s3_file_key\",\n ]\n for f_name in aws_fields:\n if f_name in build_config:\n build_config[f_name][\"show\"] = True\n build_config[f_name][\"advanced\"] = False\n\n elif location == \"Google Drive\":\n # Hide file upload input, show Google Drive fields\n if \"path\" in build_config:\n build_config[\"path\"][\"show\"] = False\n\n gdrive_fields = [\"service_account_key\", \"file_id\"]\n for f_name in gdrive_fields:\n if f_name in build_config:\n build_config[f_name][\"show\"] = True\n build_config[f_name][\"advanced\"] = False\n # No storage location selected - show file upload by default\n elif \"path\" in build_config:\n build_config[\"path\"][\"show\"] = True\n\n return build_config\n\n if field_name == \"path\":\n paths = self._path_value(build_config)\n\n # Disable in cloud environments\n if is_astra_cloud_environment():\n self._disable_docling_fields_in_cloud(build_config)\n else:\n # If all files can be processed by docling, do so\n allow_advanced = all(not file_path.endswith((\".csv\", \".xlsx\", \".parquet\")) for file_path in paths)\n build_config[\"advanced_mode\"][\"show\"] = allow_advanced\n if not allow_advanced:\n build_config[\"advanced_mode\"][\"value\"] = False\n docling_fields = (\n \"pipeline\",\n \"ocr_engine\",\n \"doc_key\",\n \"md_image_placeholder\",\n \"md_page_break_placeholder\",\n )\n for field in docling_fields:\n if field in build_config:\n build_config[field][\"show\"] = False\n\n # Docling Processing\n elif field_name == \"advanced_mode\":\n # Disable in cloud environments - don't show Docling fields even if advanced_mode is toggled\n if is_astra_cloud_environment():\n self._disable_docling_fields_in_cloud(build_config)\n else:\n docling_fields = (\n \"pipeline\",\n \"ocr_engine\",\n \"doc_key\",\n \"md_image_placeholder\",\n \"md_page_break_placeholder\",\n )\n for field in docling_fields:\n if field in build_config:\n build_config[field][\"show\"] = bool(field_value)\n if field == \"pipeline\":\n build_config[field][\"advanced\"] = not bool(field_value)\n\n elif field_name == \"pipeline\":\n # Disable in cloud environments - don't show OCR engine even if pipeline is changed\n if is_astra_cloud_environment():\n self._disable_docling_fields_in_cloud(build_config)\n elif field_value == \"standard\":\n build_config[\"ocr_engine\"][\"show\"] = True\n build_config[\"ocr_engine\"][\"value\"] = \"easyocr\"\n else:\n build_config[\"ocr_engine\"][\"show\"] = False\n build_config[\"ocr_engine\"][\"value\"] = \"None\"\n\n return build_config\n\n def update_outputs(self, frontend_node: dict[str, Any], field_name: str, field_value: Any) -> dict[str, Any]: # noqa: ARG002\n \"\"\"Dynamically show outputs based on file count/type and advanced mode.\"\"\"\n if field_name not in [\"path\", \"advanced_mode\", \"pipeline\"]:\n return frontend_node\n\n template = frontend_node.get(\"template\", {})\n paths = self._path_value(template)\n if not paths:\n return frontend_node\n\n frontend_node[\"outputs\"] = []\n if len(paths) == 1:\n file_path = paths[0] if field_name == \"path\" else frontend_node[\"template\"][\"path\"][\"file_path\"][0]\n if file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Structured Content\",\n name=\"dataframe\",\n method=\"load_files_structured\",\n types=[\"Table\"],\n selected=\"Table\",\n tool_mode=True,\n ),\n )\n elif file_path.endswith(\".json\"):\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Structured Content\",\n name=\"json\",\n method=\"load_files_json\",\n types=[\"JSON\"],\n selected=\"JSON\",\n tool_mode=True,\n ),\n )\n\n advanced_mode = frontend_node.get(\"template\", {}).get(\"advanced_mode\", {}).get(\"value\", False)\n if advanced_mode:\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Structured Output\",\n name=\"advanced_dataframe\",\n method=\"load_files_dataframe\",\n types=[\"Table\"],\n selected=\"Table\",\n tool_mode=True,\n ),\n )\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Markdown\",\n name=\"advanced_markdown\",\n method=\"load_files_markdown\",\n types=[\"Message\"],\n selected=\"Message\",\n tool_mode=True,\n ),\n )\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"File Path\",\n name=\"path\",\n method=\"load_files_path\",\n types=[\"Message\"],\n selected=\"Message\",\n tool_mode=True,\n ),\n )\n else:\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Raw Content\",\n name=\"message\",\n method=\"load_files_message\",\n types=[\"Message\"],\n selected=\"Message\",\n tool_mode=True,\n ),\n )\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"File Path\",\n name=\"path\",\n method=\"load_files_path\",\n types=[\"Message\"],\n selected=\"Message\",\n tool_mode=True,\n ),\n )\n else:\n # Multiple files => DataFrame and Message outputs; advanced parser disabled\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Files\",\n name=\"dataframe\",\n method=\"load_files\",\n types=[\"Table\"],\n selected=\"Table\",\n tool_mode=True,\n )\n )\n frontend_node[\"outputs\"].append(\n Output(\n display_name=\"Raw Content\",\n name=\"message\",\n method=\"load_files_message\",\n types=[\"Message\"],\n selected=\"Message\",\n tool_mode=True,\n )\n )\n\n return frontend_node\n\n # ------------------------------ Core processing ----------------------------------\n\n def _get_selected_storage_location(self) -> str:\n \"\"\"Get the selected storage location from the SortableListInput.\"\"\"\n if hasattr(self, \"storage_location\") and self.storage_location:\n if isinstance(self.storage_location, list) and len(self.storage_location) > 0:\n return self.storage_location[0].get(\"name\", \"\")\n if isinstance(self.storage_location, dict):\n return self.storage_location.get(\"name\", \"\")\n return \"Local\" # Default to Local if not specified\n\n def _validate_and_resolve_paths(self) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Override to handle file_path_str input from tool mode and cloud storage.\n\n Priority:\n 1. Cloud storage (AWS/Google Drive) if selected\n 2. file_path_str (if provided by the tool call)\n 3. path (uploaded file from UI)\n \"\"\"\n storage_location = self._get_selected_storage_location()\n\n # Handle AWS S3\n if storage_location == \"AWS\":\n return self._read_from_aws_s3()\n\n # Handle Google Drive\n if storage_location == \"Google Drive\":\n return self._read_from_google_drive()\n\n # Handle Local storage\n # Check if file_path_str is provided (from tool mode)\n file_path_str = getattr(self, \"file_path_str\", None)\n if file_path_str:\n # Use the string path from tool mode\n from pathlib import Path\n\n from lfx.schema.data import Data\n from lfx.utils.file_path_security import (\n StorageNamespaceError,\n component_file_access_scopes,\n enforce_local_file_access,\n )\n\n # Use same resolution logic as BaseFileComponent (support storage paths)\n path_str = str(file_path_str)\n if parse_storage_path(path_str):\n try:\n resolved_path = Path(self.get_full_path(path_str))\n except StorageNamespaceError:\n # A storage namespace outside this graph's scope is an access denial,\n # not a resolution failure: never retry it as a plain local path.\n raise\n except (ValueError, AttributeError):\n resolved_path = Path(self.resolve_path(path_str))\n else:\n resolved_path = Path(self.resolve_path(path_str))\n\n # Security: confine tool-mode reads to the storage dir in restricted (multi-tenant)\n # mode so a tenant cannot read arbitrary server files via file_path_str.\n resolved_path = enforce_local_file_access(resolved_path, scope_ids=component_file_access_scopes(self))\n\n if not resolved_path.exists():\n msg = f\"File or directory not found: {file_path_str}\"\n self.log(msg)\n if not self.silent_errors:\n raise ValueError(msg)\n return []\n\n data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(resolved_path)})\n return [BaseFileComponent.BaseFile(data_obj, resolved_path, delete_after_processing=False)]\n\n # Otherwise use the default implementation (uses path FileInput)\n return super()._validate_and_resolve_paths()\n\n def _read_from_aws_s3(self) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Read file from AWS S3.\"\"\"\n from lfx.base.data.cloud_storage_utils import create_s3_client, validate_aws_credentials\n\n # Validate AWS credentials\n validate_aws_credentials(self)\n if not getattr(self, \"s3_file_key\", None):\n msg = \"S3 File Key is required\"\n raise ValueError(msg)\n\n # Create S3 client\n s3_client = create_s3_client(self)\n\n # Download file to temp location\n import tempfile\n\n # Get file extension from S3 key\n file_extension = Path(self.s3_file_key).suffix or \"\"\n\n temp_file_path: str | None = None\n try:\n with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n temp_file_path = temp_file.name\n s3_client.download_fileobj(self.bucket_name, self.s3_file_key, temp_file)\n except Exception as e:\n # The context manager has already closed the handle by the time this runs, which is\n # what Windows requires before the partial download can be deleted. Keeping the\n # cleanup here also covers a failure raised by the closing flush itself.\n if temp_file_path is not None:\n with contextlib.suppress(OSError):\n Path(temp_file_path).unlink()\n msg = f\"Failed to download file from S3: {e}\"\n raise RuntimeError(msg) from e\n\n # Create BaseFile object\n from lfx.schema.data import Data\n\n temp_path = Path(temp_file_path)\n data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n return [\n BaseFileComponent.BaseFile(\n data_obj,\n temp_path,\n delete_after_processing=True,\n cleanup_local_file=True,\n )\n ]\n\n def _read_from_google_drive(self) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Read file from Google Drive.\"\"\"\n import tempfile\n\n from googleapiclient.http import MediaIoBaseDownload\n\n from lfx.base.data.cloud_storage_utils import create_google_drive_service\n\n # Validate Google Drive credentials\n if not getattr(self, \"service_account_key\", None):\n msg = \"GCP Credentials Secret Key is required for Google Drive storage\"\n raise ValueError(msg)\n if not getattr(self, \"file_id\", None):\n msg = \"Google Drive File ID is required\"\n raise ValueError(msg)\n\n # Create Google Drive service with read-only scope\n drive_service = create_google_drive_service(\n self.service_account_key, scopes=[\"https://www.googleapis.com/auth/drive.readonly\"]\n )\n\n # Get file metadata to determine file name and extension\n try:\n file_metadata = drive_service.files().get(fileId=self.file_id, fields=\"name,mimeType\").execute()\n file_name = file_metadata.get(\"name\", \"download\")\n except Exception as e:\n msg = (\n f\"Unable to access file with ID '{self.file_id}'. \"\n f\"Error: {e!s}. \"\n \"Please ensure: 1) The file ID is correct, 2) The file exists, \"\n \"3) The service account has been granted access to this file.\"\n )\n raise ValueError(msg) from e\n\n # Download file to temp location\n file_extension = Path(file_name).suffix or \"\"\n temp_file_path: str | None = None\n try:\n with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n temp_file_path = temp_file.name\n request = drive_service.files().get_media(fileId=self.file_id)\n downloader = MediaIoBaseDownload(temp_file, request)\n done = False\n while not done:\n _status, done = downloader.next_chunk()\n except Exception as e:\n # The context manager has already closed the handle by the time this runs, which is\n # what Windows requires before the partial download can be deleted. Keeping the\n # cleanup here also covers a failure raised by the closing flush itself.\n if temp_file_path is not None:\n with contextlib.suppress(OSError):\n Path(temp_file_path).unlink()\n msg = f\"Failed to download file from Google Drive: {e}\"\n raise RuntimeError(msg) from e\n\n # Create BaseFile object\n from lfx.schema.data import Data\n\n temp_path = Path(temp_file_path)\n data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n return [\n BaseFileComponent.BaseFile(\n data_obj,\n temp_path,\n delete_after_processing=True,\n cleanup_local_file=True,\n )\n ]\n\n def _is_docling_compatible(self, file_path: str) -> bool:\n \"\"\"Lightweight extension gate for Docling-compatible types.\"\"\"\n docling_exts = (\n \".adoc\",\n \".asciidoc\",\n \".asc\",\n \".bmp\",\n \".csv\",\n \".dotx\",\n \".dotm\",\n \".docm\",\n \".docx\",\n \".htm\",\n \".html\",\n \".jpg\",\n \".jpeg\",\n \".json\",\n \".md\",\n \".pdf\",\n \".png\",\n \".potx\",\n \".ppsx\",\n \".pptm\",\n \".potm\",\n \".ppsm\",\n \".pptx\",\n \".tiff\",\n \".txt\",\n \".xls\",\n \".xlsx\",\n \".xhtml\",\n \".xml\",\n \".webp\",\n )\n return file_path.lower().endswith(docling_exts)\n\n async def _get_local_file_for_docling(\n self, file_path: str, *, is_local_temp_file: bool = False\n ) -> tuple[str, bool]:\n \"\"\"Get a local file path for Docling processing, downloading from S3 if needed.\n\n Args:\n file_path: Either a local path or S3 key (format \"flow_id/filename\")\n is_local_temp_file: Whether file_path is an internally created local temporary file.\n\n Returns:\n tuple[str, bool]: (local_path, should_delete) where should_delete indicates\n if this is a temporary file that should be cleaned up\n \"\"\"\n if is_local_temp_file:\n local_temp_path = Path(file_path)\n if not local_temp_path.is_absolute() or not local_temp_path.is_file():\n msg = f\"Invalid local temporary path: {file_path}\"\n raise ValueError(msg)\n return file_path, False\n\n settings = get_settings_service().settings\n if settings.storage_type == \"local\":\n return file_path, False\n\n # S3 storage - download to temp file\n parsed = parse_storage_path(file_path)\n if not parsed:\n msg = f\"Invalid S3 path format: {file_path}. Expected 'flow_id/filename'\"\n raise ValueError(msg)\n\n storage_service = require_storage_service(get_storage_service())\n flow_id, filename = parsed\n\n # Get file content from S3\n content = await storage_service.get_file(flow_id, filename)\n\n write = asyncio.ensure_future(asyncio.to_thread(_write_temp_file, content, Path(filename).suffix))\n try:\n temp_path = await asyncio.shield(write)\n except asyncio.CancelledError:\n write.add_done_callback(_unlink_orphaned_temp_file)\n raise\n\n return temp_path, True\n\n def _process_docling_in_subprocess(self, file_path: str, *, is_local_temp_file: bool = False) -> Data | None:\n \"\"\"Sync wrapper around ``_aprocess_docling_in_subprocess``.\"\"\"\n return run_until_complete(\n self._aprocess_docling_in_subprocess(file_path, is_local_temp_file=is_local_temp_file)\n )\n\n async def _aprocess_docling_in_subprocess(self, file_path: str, *, is_local_temp_file: bool = False) -> Data | None:\n \"\"\"Run Docling in a separate OS process and map the result to a Data object.\n\n We avoid multiprocessing pickling by launching `python -c \"<script>\"` and\n passing JSON config via stdin. The child prints a JSON result to stdout.\n\n For S3 storage, the file is downloaded to a temp file first; the download is\n awaited, and the subprocess is driven from a worker thread.\n \"\"\"\n if not file_path:\n return None\n\n _raise_if_file_tool_cancelled()\n settings = get_settings_service().settings\n if settings.storage_type == \"s3\":\n local_path, should_delete = await self._get_local_file_for_docling(\n file_path, is_local_temp_file=is_local_temp_file\n )\n else:\n local_path = file_path\n should_delete = False\n\n # The worker owns a downloaded temp file: if this coroutine is cancelled mid-parse the\n # subprocess may still be reading it, so only the worker may delete it.\n work = asyncio.create_task(\n asyncio.to_thread(self._process_docling_local_file, local_path, file_path, should_delete=should_delete)\n )\n try:\n return await asyncio.shield(work)\n except asyncio.CancelledError:\n work.add_done_callback(_log_abandoned_file_loader_result)\n raise\n\n def _process_docling_local_file(\n self, local_path: str, original_file_path: str, *, should_delete: bool\n ) -> Data | None:\n try:\n _raise_if_file_tool_cancelled()\n return self._process_docling_subprocess_impl(local_path, original_file_path)\n finally:\n # Clean up temp file if we created one\n if should_delete:\n with contextlib.suppress(Exception):\n Path(local_path).unlink() # Ignore cleanup errors\n\n def _process_docling_subprocess_impl(self, local_file_path: str, original_file_path: str) -> Data | None:\n \"\"\"Implementation of Docling subprocess processing.\n\n Args:\n local_file_path: Path to local file to process\n original_file_path: Original file path to include in metadata\n Returns:\n Data object with processed content\n \"\"\"\n args: dict[str, Any] = {\n \"file_path\": local_file_path,\n \"markdown\": bool(self.markdown),\n \"image_mode\": str(self.IMAGE_MODE),\n \"md_image_placeholder\": str(self.md_image_placeholder),\n \"md_page_break_placeholder\": str(self.md_page_break_placeholder),\n \"pipeline\": str(self.pipeline),\n \"ocr_engine\": (\n self.ocr_engine if self.ocr_engine and self.ocr_engine != \"None\" and self.pipeline != \"vlm\" else None\n ),\n }\n\n # Child script for isolating the docling processing\n child_script = textwrap.dedent(\n r\"\"\"\n import json, sys\n\n def try_imports():\n try:\n from docling.datamodel.base_models import ConversionStatus, InputFormat # type: ignore\n from docling.document_converter import DocumentConverter # type: ignore\n from docling_core.types.doc import ImageRefMode # type: ignore\n return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"latest\"\n except Exception as e:\n raise e\n\n def create_converter(strategy, input_format, DocumentConverter, pipeline, ocr_engine):\n # --- Standard PDF/IMAGE pipeline (your existing behavior), with optional OCR ---\n if pipeline == \"standard\":\n try:\n from docling.datamodel.pipeline_options import PdfPipelineOptions # type: ignore\n from docling.document_converter import PdfFormatOption # type: ignore\n\n pipe = PdfPipelineOptions()\n pipe.do_ocr = False\n\n if ocr_engine:\n try:\n from docling.models.factories import get_ocr_factory # type: ignore\n pipe.do_ocr = True\n fac = get_ocr_factory(allow_external_plugins=False)\n pipe.ocr_options = fac.create_options(kind=ocr_engine)\n except Exception:\n # If OCR setup fails, disable it\n pipe.do_ocr = False\n\n fmt = {}\n if hasattr(input_format, \"PDF\"):\n fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(pipeline_options=pipe)\n if hasattr(input_format, \"IMAGE\"):\n fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(pipeline_options=pipe)\n\n return DocumentConverter(format_options=fmt)\n except Exception:\n return DocumentConverter()\n\n # --- Vision-Language Model (VLM) pipeline ---\n if pipeline == \"vlm\":\n try:\n from docling.datamodel.pipeline_options import VlmPipelineOptions\n from docling.datamodel.vlm_model_specs import GRANITEDOCLING_MLX, GRANITEDOCLING_TRANSFORMERS\n from docling.document_converter import PdfFormatOption\n from docling.pipeline.vlm_pipeline import VlmPipeline\n\n vl_pipe = VlmPipelineOptions(\n vlm_options=GRANITEDOCLING_TRANSFORMERS,\n )\n\n if sys.platform == \"darwin\":\n try:\n import mlx_vlm\n vl_pipe.vlm_options = GRANITEDOCLING_MLX\n except ImportError as e:\n raise e\n\n # VLM paths generally don't need OCR; keep OCR off by default here.\n fmt = {}\n if hasattr(input_format, \"PDF\"):\n fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(\n pipeline_cls=VlmPipeline,\n pipeline_options=vl_pipe\n )\n if hasattr(input_format, \"IMAGE\"):\n fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(\n pipeline_cls=VlmPipeline,\n pipeline_options=vl_pipe\n )\n\n return DocumentConverter(format_options=fmt)\n except Exception as e:\n raise e\n\n # --- Fallback: default converter with no special options ---\n return DocumentConverter()\n\n def export_markdown(document, ImageRefMode, image_mode, img_ph, pg_ph):\n try:\n mode = getattr(ImageRefMode, image_mode.upper(), image_mode)\n return document.export_to_markdown(\n image_mode=mode,\n image_placeholder=img_ph,\n page_break_placeholder=pg_ph,\n )\n except Exception:\n try:\n return document.export_to_text()\n except Exception:\n return str(document)\n\n def to_rows(doc_dict):\n rows = []\n for t in doc_dict.get(\"texts\", []):\n prov = t.get(\"prov\") or []\n page_no = None\n if prov and isinstance(prov, list) and isinstance(prov[0], dict):\n page_no = prov[0].get(\"page_no\")\n rows.append({\n \"page_no\": page_no,\n \"label\": t.get(\"label\"),\n \"text\": t.get(\"text\"),\n \"level\": t.get(\"level\"),\n })\n return rows\n\n def main():\n cfg = json.loads(sys.stdin.read())\n file_path = cfg[\"file_path\"]\n markdown = cfg[\"markdown\"]\n image_mode = cfg[\"image_mode\"]\n img_ph = cfg[\"md_image_placeholder\"]\n pg_ph = cfg[\"md_page_break_placeholder\"]\n pipeline = cfg[\"pipeline\"]\n ocr_engine = cfg.get(\"ocr_engine\")\n meta = {\"file_path\": file_path}\n\n try:\n ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, strategy = try_imports()\n converter = create_converter(strategy, InputFormat, DocumentConverter, pipeline, ocr_engine)\n try:\n res = converter.convert(file_path)\n except Exception as e:\n print(json.dumps({\"ok\": False, \"error\": f\"Docling conversion error: {e}\", \"meta\": meta}))\n return\n\n ok = False\n if hasattr(res, \"status\"):\n try:\n ok = (res.status == ConversionStatus.SUCCESS) or (str(res.status).lower() == \"success\")\n except Exception:\n ok = (str(res.status).lower() == \"success\")\n if not ok and hasattr(res, \"document\"):\n ok = getattr(res, \"document\", None) is not None\n if not ok:\n print(json.dumps({\"ok\": False, \"error\": \"Docling conversion failed\", \"meta\": meta}))\n return\n\n doc = getattr(res, \"document\", None)\n if doc is None:\n print(json.dumps({\"ok\": False, \"error\": \"Docling produced no document\", \"meta\": meta}))\n return\n\n # Extract DoclingDocument metadata\n if hasattr(doc, \"name\") and doc.name:\n meta[\"name\"] = doc.name\n if hasattr(doc, \"origin\") and doc.origin is not None:\n origin = doc.origin\n if hasattr(origin, \"filename\") and origin.filename:\n meta[\"filename\"] = origin.filename\n if hasattr(origin, \"binary_hash\") and origin.binary_hash:\n meta[\"document_id\"] = str(origin.binary_hash)\n if hasattr(origin, \"mimetype\") and origin.mimetype:\n meta[\"mimetype\"] = origin.mimetype\n\n if markdown:\n text = export_markdown(doc, ImageRefMode, image_mode, img_ph, pg_ph)\n print(json.dumps({\"ok\": True, \"mode\": \"markdown\", \"text\": text, \"meta\": meta}))\n return\n\n # structured\n try:\n doc_dict = doc.export_to_dict()\n except Exception as e:\n print(json.dumps({\"ok\": False, \"error\": f\"Docling export_to_dict failed: {e}\", \"meta\": meta}))\n return\n\n rows = to_rows(doc_dict)\n print(json.dumps({\"ok\": True, \"mode\": \"structured\", \"doc\": rows, \"meta\": meta}))\n except Exception as e:\n print(\n json.dumps({\n \"ok\": False,\n \"error\": f\"Docling processing error: {e}\",\n \"meta\": {\"file_path\": file_path},\n })\n )\n\n if __name__ == \"__main__\":\n main()\n \"\"\"\n )\n\n # The path is passed as JSON over stdin to an argument-list subprocess, so shell\n # metacharacters are ordinary filename characters here.\n if not isinstance(args[\"file_path\"], str):\n return Data(data={\"error\": \"Unsafe file path detected.\", \"file_path\": args[\"file_path\"]})\n\n # Use communicate() in bounded intervals so stdout/stderr are drained while the\n # child runs without losing the heartbeat that keeps the SSE event stream alive.\n docling_timeout = 600 # 10 minutes; large PDFs with OCR may need this\n poll_interval = 5 # seconds between progress heartbeats\n\n proc = subprocess.Popen( # noqa: S603\n [sys.executable, \"-u\", \"-c\", child_script],\n stdin=subprocess.PIPE,\n stdout=subprocess.PIPE,\n stderr=subprocess.PIPE,\n )\n\n start = time.monotonic()\n input_bytes: bytes | None = json.dumps(args).encode(\"utf-8\")\n cancel_event = _FILE_TOOL_CANCEL_EVENT.get()\n try:\n while True:\n _raise_if_file_tool_cancelled(cancel_event)\n elapsed = time.monotonic() - start\n if elapsed >= docling_timeout:\n proc.kill()\n proc.communicate()\n return Data(\n data={\n \"error\": (\n f\"Docling processing timed out after {docling_timeout}s. \"\n \"Consider using the standalone Docling component for large documents.\"\n ),\n \"file_path\": original_file_path,\n },\n )\n try:\n stdout_bytes, stderr_bytes = proc.communicate(\n input=input_bytes,\n timeout=min(poll_interval, docling_timeout - elapsed),\n )\n _raise_if_file_tool_cancelled(cancel_event)\n break\n except subprocess.TimeoutExpired:\n # communicate() retains partially written input and collected output across\n # retries, so subsequent calls continue draining without resending stdin.\n input_bytes = None\n elapsed = time.monotonic() - start\n self.log(f\"Docling processing in progress ({int(elapsed)}s elapsed)...\")\n finally:\n if (cancel_event is not None and cancel_event.is_set()) or proc.poll() is None:\n _kill_and_reap_process(proc)\n\n if not stdout_bytes:\n err_msg = stderr_bytes.decode(\"utf-8\", errors=\"replace\") if stderr_bytes else \"no output from child process\"\n return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": original_file_path})\n\n try:\n result = json.loads(stdout_bytes.decode(\"utf-8\"))\n except Exception as e: # noqa: BLE001\n err_msg = stderr_bytes.decode(\"utf-8\", errors=\"replace\")\n return Data(\n data={\n \"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\",\n \"file_path\": original_file_path,\n },\n )\n\n if not result.get(\"ok\"):\n error_msg = result.get(\"error\", \"Unknown Docling error\")\n # Override meta file_path with original_file_path to ensure correct path matching\n meta = result.get(\"meta\", {})\n meta[\"file_path\"] = original_file_path\n return Data(data={\"error\": error_msg, **meta})\n\n meta = result.get(\"meta\", {})\n # Override meta file_path with original_file_path to ensure correct path matching\n # The subprocess returns the temp file path, but we need the original S3/local path for rollup_data\n meta[\"file_path\"] = original_file_path\n if result.get(\"mode\") == \"markdown\":\n exported_content = str(result.get(\"text\", \"\"))\n return Data(\n text=exported_content,\n data={\"exported_content\": exported_content, \"export_format\": self.EXPORT_FORMAT, **meta},\n )\n\n rows = list(result.get(\"doc\", []))\n return Data(data={\"doc\": rows, \"export_format\": self.EXPORT_FORMAT, **meta})\n\n @delegates_to(\"aprocess_files\")\n def process_files(\n self,\n file_list: list[BaseFileComponent.BaseFile],\n ) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Process input files. Sync wrapper around ``aprocess_files``.\"\"\"\n return run_until_complete(self.aprocess_files(file_list))\n\n async def aprocess_files(\n self,\n file_list: list[BaseFileComponent.BaseFile],\n ) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Process input files.\n\n - advanced_mode => Docling in a separate process.\n - Otherwise => standard parsing, up to ``concurrency_multithreading`` files at once.\n\n Storage reads are awaited on the running loop; parsing and the Docling subprocess\n run in worker threads.\n \"\"\"\n cancel_event = _FILE_TOOL_CANCEL_EVENT.get()\n _raise_if_file_tool_cancelled(cancel_event)\n if not file_list:\n msg = \"No files to process.\"\n raise ValueError(msg)\n\n # Validate image files to detect content/extension mismatches\n # This prevents API errors like \"Image does not match the provided media type\"\n image_extensions = {\"jpeg\", \"jpg\", \"png\", \"gif\", \"webp\", \"bmp\", \"tiff\"}\n settings = get_settings_service().settings\n for file in file_list:\n _raise_if_file_tool_cancelled(cancel_event)\n extension = file.path.suffix[1:].lower()\n if extension in image_extensions:\n # Read bytes based on storage type\n try:\n if settings.storage_type == \"s3\":\n # For S3 storage, use storage service to read file bytes\n file_path_str = str(file.path)\n content = await read_file_bytes(file_path_str)\n else:\n # For local storage, read bytes directly from filesystem\n content = await asyncio.to_thread(file.path.read_bytes)\n\n is_valid, error_msg = validate_image_content_type(\n str(file.path),\n content=content,\n )\n if not is_valid:\n self.log(error_msg)\n if not self.silent_errors:\n raise ValueError(error_msg)\n except (OSError, FileNotFoundError) as e:\n self.log(f\"Could not read file for validation: {e}\")\n # Continue - let it fail later with better error\n\n # Validate that files requiring Docling are only processed when advanced mode is enabled\n if not self.advanced_mode:\n for file in file_list:\n _raise_if_file_tool_cancelled(cancel_event)\n extension = file.path.suffix[1:].lower()\n if extension in self.DOCLING_ONLY_EXTENSIONS:\n if is_astra_cloud_environment():\n msg = (\n f\"File '{file.path.name}' has extension '.{extension}' which requires \"\n f\"Advanced Parser mode. Advanced Parser is not available in cloud environments.\"\n )\n else:\n msg = (\n f\"File '{file.path.name}' has extension '.{extension}' which requires \"\n f\"Advanced Parser mode. Please enable 'Advanced Parser' to process this file.\"\n )\n self.log(msg)\n raise ValueError(msg)\n\n async def process_file_standard(file_path: str, *, silent_errors: bool = False) -> Data | None:\n try:\n _raise_if_file_tool_cancelled(cancel_event)\n encoding = (getattr(self, \"text_encoding\", \"\") or \"\").strip() or None\n result = await aparse_text_file_to_data(file_path, silent_errors=silent_errors, encoding=encoding)\n _raise_if_file_tool_cancelled(cancel_event)\n if result is not None and (selected := result.data.get(\"encoding\")):\n selection = \"explicit\" if encoding else \"automatic\"\n self.log(\n f\"Read {Path(file_path).name} with text encoding '{selected}' ({selection}). \"\n \"If text looks incorrect, set Text Encoding to the file's encoding.\"\n )\n except _FileToolCancelledError:\n raise\n except FileNotFoundError as e:\n self.log(f\"File not found: {file_path}. Error: {e}\")\n if not silent_errors:\n raise\n return None\n except Exception as e:\n self.log(f\"Unexpected error processing {file_path}: {e}\")\n if not silent_errors:\n raise\n return None\n else:\n return result\n\n docling_compatible = all(self._is_docling_compatible(str(f.path)) for f in file_list)\n\n # Advanced path: Check if ALL files are compatible with Docling\n if self.advanced_mode and docling_compatible:\n final_return: list[BaseFileComponent.BaseFile] = []\n for file in file_list:\n _raise_if_file_tool_cancelled(cancel_event)\n file_path = str(file.path)\n advanced_data: Data | None = await self._aprocess_docling_in_subprocess(\n file_path, is_local_temp_file=file.cleanup_local_file\n )\n _raise_if_file_tool_cancelled(cancel_event)\n\n # Expanding a large Docling export into rows is O(rows), so it stays off the event loop.\n final_return.extend(\n await asyncio.to_thread(self._docling_result_to_files, file, file_path, advanced_data)\n )\n return final_return\n\n # Standard multi-file (or single non-advanced) path\n concurrency = max(1, self.concurrency_multithreading)\n\n file_paths = [str(f.path) for f in file_list]\n self.log(f\"Starting parallel processing of {len(file_paths)} files with concurrency: {concurrency}.\")\n my_data = await aparallel_load_data(\n file_paths,\n silent_errors=self.silent_errors,\n load_function=process_file_standard,\n max_concurrency=concurrency,\n )\n _raise_if_file_tool_cancelled(cancel_event)\n return await asyncio.to_thread(self.rollup_data, file_list, my_data)\n\n def _docling_result_to_files(\n self, file: BaseFileComponent.BaseFile, file_path: str, advanced_data: Data | None\n ) -> list[BaseFileComponent.BaseFile]:\n \"\"\"Map one file's Docling result onto BaseFile rows (one Data row per ``doc`` element).\"\"\"\n # Handle None case - Docling processing failed or returned None\n if advanced_data is None:\n error_data = Data(\n data={\n \"file_path\": file_path,\n \"error\": \"Docling processing returned no result. Check logs for details.\",\n },\n )\n return self.rollup_data([file], [error_data])\n\n # --- UNNEST: expand each element in `doc` to its own Data row\n payload = getattr(advanced_data, \"data\", {}) or {}\n\n # Check for errors first\n if \"error\" in payload:\n error_msg = payload.get(\"error\", \"Unknown error\")\n error_data = Data(\n data={\n \"file_path\": file_path,\n \"error\": error_msg,\n **{k: v for k, v in payload.items() if k not in (\"error\", \"file_path\")},\n },\n )\n return self.rollup_data([file], [error_data])\n\n doc_rows = payload.get(\"doc\")\n if isinstance(doc_rows, list) and doc_rows:\n # Non-empty list of structured rows\n rows: list[Data | None] = [\n Data(\n data={\n \"file_path\": file_path,\n **(item if isinstance(item, dict) else {\"value\": item}),\n },\n )\n for item in doc_rows\n ]\n return self.rollup_data([file], rows)\n if isinstance(doc_rows, list):\n # Empty list - file was processed but no text content found\n # Create a Data object indicating no content was extracted\n self.log(f\"No text extracted from '{file_path}', creating placeholder data\")\n empty_data = Data(\n data={\n \"file_path\": file_path,\n \"text\": \"(No text content extracted from image)\",\n \"info\": \"Image processed successfully but contained no extractable text\",\n **{k: v for k, v in payload.items() if k != \"doc\"},\n },\n )\n return self.rollup_data([file], [empty_data])\n\n # If not structured, keep as-is (e.g., markdown export or error dict)\n # Ensure file_path is set for proper rollup matching\n if not payload.get(\"file_path\"):\n payload[\"file_path\"] = file_path\n # Create new Data with file_path\n advanced_data = Data(\n data=payload,\n text=getattr(advanced_data, \"text\", None),\n )\n return self.rollup_data([file], [advanced_data])\n\n # ------------------------------ Output helpers -----------------------------------\n\n @delegates_to(\"aload_files_helper\")\n def load_files_helper(self) -> DataFrame:\n return self._run_sync_loader(self.aload_files_helper)\n\n async def aload_files_helper(self) -> DataFrame:\n result = await self._adispatch(\"load_files\")\n\n # Result is a DataFrame - check if it has any rows\n if result.empty:\n msg = \"Could not extract content from the provided file(s).\"\n raise ValueError(msg)\n\n # Check for error column with error messages\n if \"error\" in result.columns:\n errors = result[\"error\"].dropna().tolist()\n if errors and not any(col in result.columns for col in [\"text\", \"doc\", \"exported_content\"]):\n raise ValueError(errors[0])\n\n return result\n\n @delegates_to(\"aload_files_dataframe\")\n def load_files_dataframe(self) -> DataFrame:\n \"\"\"Load files using advanced Docling processing and export to DataFrame format.\"\"\"\n return self._run_sync_loader(self.aload_files_dataframe)\n\n async def aload_files_dataframe(self) -> DataFrame:\n \"\"\"Load files using advanced Docling processing and export to DataFrame format.\"\"\"\n self.markdown = False\n return await self._adispatch(\"load_files_helper\")\n\n @delegates_to(\"aload_files_markdown\")\n def load_files_markdown(self) -> Message:\n \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n return self._run_sync_loader(self.aload_files_markdown)\n\n async def aload_files_markdown(self) -> Message:\n \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n self.markdown = True\n result = await self._adispatch(\"load_files_helper\")\n\n # Result is a DataFrame - check for text or exported_content columns\n if \"text\" in result.columns and not result[\"text\"].isna().all():\n text_values = result[\"text\"].dropna().tolist()\n if text_values:\n return Message(text=str(text_values[0]))\n\n if \"exported_content\" in result.columns and not result[\"exported_content\"].isna().all():\n content_values = result[\"exported_content\"].dropna().tolist()\n if content_values:\n return Message(text=str(content_values[0]))\n\n # Return empty message with info that no text was found\n return Message(text=\"(No text content extracted from file)\")\n"
},
"concurrency_multithreading": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Processing Concurrency",
"dynamic": false,
"info": "When multiple files are being processed, the number of files to process concurrently.",
"list": false,
"list_add_label": "Add More",
"name": "concurrency_multithreading",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "int",
"value": 1
},
"delete_server_file_after_processing": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Delete Server File After Processing",
"dynamic": false,
"info": "If true, the Server File Path will be deleted after processing.",
"list": false,
"list_add_label": "Add More",
"name": "delete_server_file_after_processing",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"doc_key": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Doc Key",
"dynamic": false,
"info": "The key to use for the DoclingDocument column.",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "doc_key",
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": "doc"
},
"file_id": {
"_input_type": "StrInput",
"advanced": false,
"display_name": "Google Drive File ID",
"dynamic": false,
"info": "The Google Drive file ID to read. The file must be shared with the service account email.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "file_id",
"override_skip": false,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"file_path": {
"_input_type": "HandleInput",
"advanced": true,
"display_name": "Server File Path",
"dynamic": false,
"info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
"input_types": [
"Data",
"JSON",
"Message"
],
"list": true,
"list_add_label": "Add More",
"name": "file_path",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "other",
"value": ""
},
"file_path_str": {
"_input_type": "StrInput",
"advanced": true,
"display_name": "File Path",
"dynamic": false,
"info": "Path to the file to read. Used when component is called as a tool. If not provided, will use the uploaded file from 'path' input.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "file_path_str",
"override_skip": false,
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"ignore_unspecified_files": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Ignore Unspecified Files",
"dynamic": false,
"info": "If true, Data with no 'file_path' property will be ignored.",
"list": false,
"list_add_label": "Add More",
"name": "ignore_unspecified_files",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"ignore_unsupported_extensions": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Ignore Unsupported Extensions",
"dynamic": false,
"info": "If true, files with unsupported extensions will not be processed.",
"list": false,
"list_add_label": "Add More",
"name": "ignore_unsupported_extensions",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"markdown": {
"_input_type": "BoolInput",
"advanced": false,
"display_name": "Markdown Export",
"dynamic": false,
"info": "Export processed documents to Markdown format. Only available when advanced mode is enabled.",
"list": false,
"list_add_label": "Add More",
"name": "markdown",
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"md_image_placeholder": {
"_input_type": "StrInput",
"advanced": true,
"display_name": "Image placeholder",
"dynamic": false,
"info": "Specify the image placeholder for markdown exports.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "md_image_placeholder",
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "<!-- image -->"
},
"md_page_break_placeholder": {
"_input_type": "StrInput",
"advanced": true,
"display_name": "Page break placeholder",
"dynamic": false,
"info": "Add this placeholder between pages in the markdown output.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "md_page_break_placeholder",
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"ocr_engine": {
"_input_type": "DropdownInput",
"advanced": true,
"combobox": false,
"dialog_inputs": {},
"display_name": "OCR Engine",
"dynamic": false,
"external_options": {},
"info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
"name": "ocr_engine",
"options": [
"None",
"easyocr"
],
"options_metadata": [],
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"toggle": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "easyocr"
},
"path": {
"_input_type": "FileInput",
"advanced": false,
"display_name": "Files",
"dynamic": false,
"fileTypes": [
"csv",
"json",
"pdf",
"txt",
"md",
"mdx",
"yaml",
"yml",
"xml",
"html",
"htm",
"docx",
"py",
"sh",
"sql",
"js",
"ts",
"tsx",
"adoc",
"asciidoc",
"asc",
"bmp",
"dotx",
"dotm",
"docm",
"jpg",
"jpeg",
"png",
"potx",
"ppsx",
"pptm",
"potm",
"ppsm",
"pptx",
"tiff",
"xls",
"xlsx",
"xhtml",
"webp",
"zip",
"tar",
"tgz",
"bz2",
"gz"
],
"file_path": [],
"info": "Supported file extensions: csv, json, pdf, txt, md, mdx, yaml, yml, xml, html, htm, docx, py, sh, sql, js, ts, tsx, adoc, asciidoc, asc, bmp, dotx, dotm, docm, jpg, jpeg, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, xls, xlsx, xhtml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
"list": true,
"list_add_label": "Add More",
"name": "path",
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": true,
"temp_file": false,
"title_case": false,
"trace_as_metadata": true,
"type": "file",
"value": ""
},
"pipeline": {
"_input_type": "DropdownInput",
"advanced": true,
"combobox": false,
"dialog_inputs": {},
"display_name": "Pipeline",
"dynamic": false,
"external_options": {},
"info": "Docling pipeline to use",
"name": "pipeline",
"options": [
"standard",
"vlm"
],
"options_metadata": [],
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": false,
"title_case": false,
"toggle": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "standard"
},
"s3_file_key": {
"_input_type": "StrInput",
"advanced": false,
"display_name": "S3 File Key",
"dynamic": false,
"info": "The key (path) of the file in S3 bucket.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "s3_file_key",
"override_skip": false,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"separator": {
"_input_type": "StrInput",
"advanced": true,
"display_name": "Separator",
"dynamic": false,
"info": "Specify the separator to use between multiple outputs in Message format.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "separator",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "str",
"value": "\n\n"
},
"service_account_key": {
"_input_type": "SecretStrInput",
"advanced": false,
"display_name": "GCP Credentials Secret Key",
"dynamic": false,
"info": "Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).",
"input_types": [],
"load_from_db": false,
"name": "service_account_key",
"override_skip": false,
"password": true,
"placeholder": "",
"required": true,
"show": false,
"title_case": false,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"silent_errors": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Silent Errors",
"dynamic": false,
"info": "If true, errors will not raise an exception.",
"list": false,
"list_add_label": "Add More",
"name": "silent_errors",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"storage_location": {
"_input_type": "SortableListInput",
"advanced": false,
"display_name": "Storage Location",
"dynamic": false,
"info": "Choose where to read the file from.",
"limit": 1,
"name": "storage_location",
"options": [
{
"icon": "hard-drive",
"name": "Local"
},
{
"icon": "Amazon",
"name": "AWS"
},
{
"icon": "google",
"name": "Google Drive"
}
],
"override_skip": false,
"placeholder": "Select Location",
"real_time_refresh": true,
"required": false,
"search_category": [],
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "sortableList",
"value": ""
},
"text_encoding": {
"_input_type": "StrInput",
"advanced": true,
"api_editable": false,
"display_name": "Text Encoding",
"dynamic": false,
"info": "Leave blank to detect encoding automatically for standard text parsing, which reports the selected encoding in logs and raw output metadata. For structured CSV output, leaving this blank uses the parser default. If accents or punctuation look incorrect, enter the file's encoding, such as cp1252 or utf-8. The CSV reader uses the selected encoding but does not add it to structured output metadata. Applies to standard text parsing and CSV, not PDF, DOCX, or the Advanced Parser.",
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "text_encoding",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"use_multithreading": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "[Deprecated] Use Multithreading",
"dynamic": false,
"info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
"list": false,
"list_add_label": "Add More",
"name": "use_multithreading",
"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": true,
"type": "File"
},
"dragging": false,
"id": "File-wvfA7",
"measured": {
"height": 360,
"width": 320
},
"position": {
"x": 1606.1874496815992,
"y": 402.68202839127423
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"_connectionMode": false,
"id": "Agent-portfolio",
"node": {
"base_classes": [
"Data",
"JSON",
"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": "https://docs.langflow.org/agents",
"edited": false,
"field_order": [
"model",
"api_key",
"base_url_ibm_watsonx",
"project_id",
"system_prompt",
"context_id",
"n_messages",
"max_tokens",
"format_instructions",
"output_schema",
"tools",
"input_value",
"handle_parsing_errors",
"max_iterations",
"stream",
"add_current_date_tool",
"add_calculator_tool"
],
"frozen": false,
"icon": "bot",
"last_updated": "2026-06-23T18:53:59.793Z",
"legacy": false,
"lf_version": "1.10.0",
"metadata": {
"code_hash": "9fcfe75813e7",
"component_class_name": "AgentComponent",
"dependencies": {
"dependencies": [
{
"name": "langchain",
"version": "1.3.14"
},
{
"name": "langgraph",
"version": "1.2.19"
},
{
"name": "lfx",
"version": null
},
{
"name": "langchain_core",
"version": "1.5.1"
}
],
"total_dependencies": 4
},
"module": "lfx.components.models_and_agents.agent.AgentComponent"
},
"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__"
},
{
"allows_loop": false,
"cache": true,
"display_name": "Structured Response",
"group_outputs": false,
"method": "json_response",
"name": "structured_response",
"selected": "JSON",
"tool_mode": true,
"types": [
"Data",
"JSON"
],
"value": "__UNDEFINED__"
}
],
"pinned": false,
"template": {
"_type": "Component",
"add_calculator_tool": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Calculator",
"dynamic": false,
"info": "If true, adds a zero-config arithmetic calculator tool to the agent (safe: only +, -, *, /, ** operators via AST).",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "add_calculator_tool",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "bool",
"value": false
},
"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.",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "add_current_date_tool",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "bool",
"value": false
},
"api_key": {
"_input_type": "SecretStrInput",
"advanced": true,
"display_name": "API Key",
"dynamic": false,
"info": "Overrides global provider settings. Leave blank to use your pre-configured API Key.",
"input_types": [],
"load_from_db": false,
"name": "api_key",
"override_skip": false,
"password": true,
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": true,
"title_case": false,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"base_url_ibm_watsonx": {
"_input_type": "DropdownInput",
"advanced": false,
"combobox": true,
"dialog_inputs": {},
"display_name": "watsonx API Endpoint",
"dynamic": false,
"external_options": {},
"info": "The base URL of the API (IBM watsonx.ai only)",
"input_types": [],
"name": "base_url_ibm_watsonx",
"options": [
"https://us-south.ml.cloud.ibm.com",
"https://eu-de.ml.cloud.ibm.com",
"https://eu-gb.ml.cloud.ibm.com",
"https://au-syd.ml.cloud.ibm.com",
"https://jp-tok.ml.cloud.ibm.com",
"https://ca-tor.ml.cloud.ibm.com"
],
"options_metadata": [],
"override_skip": false,
"placeholder": "",
"real_time_refresh": true,
"required": false,
"show": false,
"title_case": false,
"toggle": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "str",
"value": "https://us-south.ml.cloud.ibm.com"
},
"code": {
"advanced": true,
"api_editable": false,
"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 __future__ import annotations\n\nimport uuid\nfrom collections.abc import Mapping\nfrom contextlib import contextmanager\nfrom datetime import datetime, timezone\nfrom typing import TYPE_CHECKING, Any, cast\n\nfrom langchain.agents import create_agent\nfrom langchain.agents.middleware import (\n HumanInTheLoopMiddleware,\n ModelCallLimitMiddleware,\n ToolRetryMiddleware,\n)\nfrom langgraph.types import Command\n\nfrom lfx.components.models_and_agents.agent_helpers.graph_event_adapter import (\n adapt_graph_events_to_executor_shape,\n)\nfrom lfx.components.models_and_agents.agent_helpers.messages_input_builder import (\n build_initial_messages,\n)\nfrom lfx.components.models_and_agents.agent_helpers.placeholder_corrective_middleware import (\n WatsonXPlaceholderMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.single_tool_call_middleware import (\n SingleToolCallMiddleware,\n)\nfrom lfx.components.models_and_agents.agent_helpers.tool_approval import ToolApprovalMixin\nfrom lfx.components.models_and_agents.agent_helpers.tool_call_id_middleware import ToolCallIDMiddleware\nfrom lfx.components.models_and_agents.memory import MemoryComponent, _safe_graph_user_id, aget_agent_chat_history\n\nif TYPE_CHECKING:\n from collections.abc import Awaitable, Callable\n\n from langchain_core.tools import Tool\n\n from lfx.schema.log import OnTokenFunctionType, SendMessageFunctionType\n\nfrom lfx.base.agents.agent import LCToolsAgentComponent\nfrom lfx.base.agents.callback import AgentAsyncHandler\nfrom lfx.base.agents.default_system_prompt import DEFAULT_SYSTEM_PROMPT_TEMPLATE\nfrom lfx.base.agents.events import AgentPausedError, ExceptionWithMessageError, process_agent_events\nfrom lfx.base.agents.token_callback import TokenUsageCallbackHandler\nfrom lfx.base.agents.utils import get_chat_output_sender_name\nfrom lfx.base.constants import STREAM_INFO_TEXT\nfrom lfx.base.models.unified_models import (\n get_language_model_options,\n get_llm,\n handle_model_input_update,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.components.agentics.helpers.model_config import validate_model_selection\nfrom lfx.components.helpers import CalculatorComponent, CurrentDateComponent\nfrom lfx.components.langchain_utilities.ibm_granite_handler import is_watsonx_model\nfrom lfx.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom lfx.custom.custom_component.component import get_component_toolkit\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, ModelInput, StrInput\nfrom lfx.io import IntInput, MessageTextInput, MultilineInput, Output, SecretStrInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.memory import delete_message\nfrom lfx.schema.data import Data\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.schema.message import Message\nfrom lfx.schema.table import EditMode\nfrom lfx.utils.constants import MESSAGE_SENDER_AI\n\n\ndef set_advanced_true(component_input):\n component_input.advanced = True\n return component_input\n\n\ndef _agent_base_inputs():\n \"\"\"Return base inputs tailored to AgentComponent's create_agent path.\n\n `get_base_inputs()` returns a shared list \u2014 replace, don't mutate. We drop\n inputs that are no-ops here and override info text on the inputs whose\n semantics shifted under create_agent.\n\n `verbose` is dropped because the create_agent event stream already surfaces\n every agent step via the \"Agent Steps\" content blocks; the legacy boolean\n has nothing to toggle. Saved flows that still carry a `verbose` value just\n ignore it on load (the schema no longer declares it).\n \"\"\"\n drop = {\"verbose\"}\n overrides = {\n \"handle_parsing_errors\": BoolInput(\n name=\"handle_parsing_errors\",\n display_name=\"Handle Parse Errors\",\n value=True,\n advanced=True,\n info=(\n \"Adds tool-execution retry as a safety net. `create_agent` already \"\n \"feeds tool-call validation errors back to the LLM automatically; \"\n \"this flag layers `ToolRetryMiddleware` on top so transient tool \"\n \"runtime failures are retried (max 2 retries).\"\n ),\n ),\n \"max_iterations\": IntInput(\n name=\"max_iterations\",\n display_name=\"Max Iterations\",\n value=15,\n advanced=True,\n range_spec=RangeSpec(min=1, max=128000, step=1, step_type=\"int\"),\n info=(\n \"Maximum number of model calls the agent can make before stopping \"\n \"(maps to `ModelCallLimitMiddleware.run_limit` on the create_agent \"\n \"path). Must be at least 1 \u2014 it is a safety cap, never 'unlimited'.\"\n ),\n ),\n }\n return [overrides.get(inp.name, inp) for inp in LCToolsAgentComponent.get_base_inputs() if inp.name not in drop]\n\n\ndef _extract_text_content(value) -> str:\n \"\"\"Pull a string payload from a Message-like, AIMessage-like, or string value.\"\"\"\n if isinstance(value, str):\n return value\n text = getattr(value, \"text\", None)\n if isinstance(text, str):\n return text\n content = getattr(value, \"content\", None)\n if isinstance(content, str):\n return content\n return str(value) if value is not None else \"\"\n\n\n@contextmanager\ndef _suppress_send_message(component: Any):\n \"\"\"Temporarily replace component.send_message with a no-op for the duration of the block.\n\n Used during the structured-output prompt fallback: run_agent streams the agent's\n final answer through self.send_message (correct for message_response), but in\n json_response the orchestrator parses that text into structured Data which the\n downstream Chat Output emits \u2014 leaving the original emission in place produces a\n duplicate message in the playground. The original method is always restored on exit,\n even when the wrapped call raises.\n \"\"\"\n original = component.send_message\n\n async def _noop(message, *_args, **_kwargs):\n return message\n\n component.send_message = _noop\n try:\n yield\n finally:\n component.send_message = original\n\n\nclass AgentComponent(ToolApprovalMixin, 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 inputs = [\n ModelInput(\n name=\"model\",\n display_name=\"Language Model\",\n info=\"Select your model provider\",\n real_time_refresh=True,\n required=True,\n # Agents require tool calling \u2014 the filter is honored by\n # ``handle_model_input_update`` so models that can't run with\n # tools never reach the picker (and any saved selection that\n # no longer satisfies the constraint is auto-replaced).\n filters={\"tool_calling\": True},\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"API Key\",\n info=\"Overrides global provider settings. Leave blank to use your pre-configured API Key.\",\n real_time_refresh=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n combobox=True,\n show=False,\n real_time_refresh=True,\n ),\n StrInput(\n name=\"project_id\",\n display_name=\"watsonx Project ID\",\n info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n show=False,\n required=False,\n ),\n MultilineInput(\n name=\"system_prompt\",\n display_name=\"Agent Instructions\",\n info=(\n \"System Prompt: Initial instructions and context provided to guide the agent's behavior. \"\n \"Supports dynamic placeholders: {current_date}, {model_name}, {optional_user_context}.\"\n ),\n value=DEFAULT_SYSTEM_PROMPT_TEMPLATE,\n advanced=False,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\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 IntInput(\n name=\"max_tokens\",\n display_name=\"Max Tokens\",\n info=\"Maximum number of tokens to generate. Set to 0 for no explicit limit. Field name varies by provider.\",\n advanced=True,\n range_spec=RangeSpec(min=0, max=128000, step=1, step_type=\"int\"),\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 *_agent_base_inputs(),\n # removed memory inputs from agent component\n # *memory_inputs,\n BoolInput(\n name=\"stream\",\n display_name=\"Stream\",\n info=STREAM_INFO_TEXT,\n value=True,\n advanced=True,\n ),\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 BoolInput(\n name=\"add_calculator_tool\",\n display_name=\"Calculator\",\n advanced=True,\n info=(\n \"If true, adds a zero-config arithmetic calculator tool to the agent \"\n \"(safe: only +, -, *, /, ** operators via AST).\"\n ),\n value=True,\n ),\n ]\n outputs = [\n Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n Output(\n name=\"structured_response\",\n display_name=\"Structured Response\",\n method=\"json_response\",\n types=[\"Data\"],\n ),\n ]\n\n async def _additional_model_provider_policy_ids(self, purpose, parameters=None) -> tuple[str, ...]:\n \"\"\"Gate the provider selector retained by legacy Agent/ALTK flows.\"\"\"\n _ = purpose\n from lfx.base.models.provider_registry import resolve_provider_id\n\n effective_parameters = parameters if isinstance(parameters, Mapping) else getattr(self, \"_parameters\", None)\n if not isinstance(effective_parameters, Mapping):\n effective_parameters = {}\n selected_model = effective_parameters.get(\"model\", getattr(self, \"model\", None))\n if selected_model:\n # The shared Component hook already handles a selected ModelInput;\n # connected model objects are gated by their upstream vertex.\n return ()\n legacy_provider = effective_parameters.get(\"agent_llm\", getattr(self, \"agent_llm\", None))\n if not isinstance(legacy_provider, str) or not legacy_provider.strip() or legacy_provider == \"Custom\":\n return ()\n return (resolve_provider_id(legacy_provider),)\n\n async def _filter_legacy_provider_options(self, build_config: Mapping[str, Any]) -> None:\n \"\"\"Filter ALTK/legacy Agent provider choices through the active scope.\"\"\"\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose, aresolve_model_provider_policy\n\n provider_field = build_config.get(\"agent_llm\")\n if not isinstance(provider_field, dict):\n return\n options = provider_field.get(\"options\")\n if not isinstance(options, list):\n return\n candidates = [option for option in options if isinstance(option, str) and option != \"Custom\"]\n if not candidates:\n return\n snapshot = await aresolve_model_provider_policy(\n user_id=self.user_id,\n providers=candidates,\n purpose=ModelProviderPolicyPurpose.CONFIGURE,\n )\n allowed = set(snapshot.filter(candidates))\n keep_indexes = [index for index, option in enumerate(options) if option == \"Custom\" or option in allowed]\n provider_field[\"options\"] = [options[index] for index in keep_indexes]\n metadata = provider_field.get(\"options_metadata\")\n if isinstance(metadata, list) and len(metadata) == len(options):\n provider_field[\"options_metadata\"] = [metadata[index] for index in keep_indexes]\n\n def _resolve_selected_model(self):\n \"\"\"Resolve the selected model, including legacy agent_llm/model_name inputs.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return self.model\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n return self.model\n\n legacy_provider = getattr(self, \"agent_llm\", None)\n legacy_model_name = getattr(self, \"model_name\", None)\n if not legacy_provider or not legacy_model_name:\n return self.model\n\n options = get_language_model_options(user_id=self.user_id)\n for option in options:\n if option.get(\"provider\") == legacy_provider and option.get(\"name\") == legacy_model_name:\n return [option]\n\n return [\n {\n \"name\": legacy_model_name,\n \"provider\": legacy_provider,\n \"metadata\": {},\n }\n ]\n\n def _get_max_tokens_value(self):\n \"\"\"Return the user-supplied max_tokens or None when unset/zero.\"\"\"\n val = getattr(self, \"max_tokens\", None)\n if val in {\"\", 0}:\n return None\n return val\n\n def _get_llm(self):\n \"\"\"Override parent to include max_tokens from the Agent's input field.\n\n Streaming is mandatory for AgentComponent: ``runnable.astream_events(v2)`` only\n emits ``on_chat_model_stream`` chunks when the underlying chat model is\n instantiated with ``streaming=True``. Unlike the LanguageModel component (where\n ``stream`` is a user-facing toggle), the Agent has no opt-out \u2014 the toggle is\n kept in the UI for backwards compatibility but is intentionally ignored here.\n Without ``stream=True``, the chat model accumulates the whole response and\n only emits ``on_chat_model_end``, silently disabling the Playground's live-\n typing view and breaking the streaming contract on the /events surface.\n \"\"\"\n return get_llm(\n model=self.model,\n user_id=self.user_id,\n api_key=getattr(self, \"api_key\", None),\n stream=True,\n max_tokens=self._get_max_tokens_value(),\n watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n watsonx_project_id=getattr(self, \"project_id\", None),\n overrides=getattr(self, \"_model_overrides\", None),\n )\n\n async def get_agent_requirements(self):\n \"\"\"Get the agent requirements for the agent.\"\"\"\n from langchain_core.tools import StructuredTool\n\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n await self.arequire_model_provider_policy(ModelProviderPolicyPurpose.USE)\n\n selected_model = self._resolve_selected_model()\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n is_connected_model = isinstance(selected_model, BaseLanguageModel)\n except ImportError:\n is_connected_model = False\n\n if not is_connected_model:\n validate_model_selection(selected_model)\n\n # Ensure _get_llm() uses the resolved model (e.g. from legacy agent_llm/model_name)\n self.model = selected_model\n llm_model = 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\n # Get memory data\n self.chat_history = await self.get_memory_data()\n await logger.adebug(f\"Retrieved {len(self.chat_history)} chat history messages\")\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\n if not isinstance(current_date_tool, StructuredTool):\n msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == current_date_tool.name for t in self.tools):\n self.tools.append(current_date_tool)\n\n # Add calculator tool if enabled (zero-config arithmetic)\n if getattr(self, \"add_calculator_tool\", False):\n if not isinstance(self.tools, list): # type: ignore[has-type]\n self.tools = []\n calculator_tool = (await CalculatorComponent(**self.get_base_args()).to_toolkit()).pop(0)\n\n if not isinstance(calculator_tool, StructuredTool):\n msg = \"CalculatorComponent must be converted to a StructuredTool\"\n raise TypeError(msg)\n # Skip if an externally-connected tool already provides the same name.\n # Duplicate tool names are rejected by Anthropic/Gemini with HTTP 400.\n if not any(getattr(t, \"name\", None) == calculator_tool.name for t in self.tools):\n self.tools.append(calculator_tool)\n\n # Set shared callbacks for tracing the tools used by the agent\n self.set_tools_callbacks(self.tools, self._get_shared_callbacks())\n\n return llm_model, self.chat_history, self.tools\n\n def _get_resolved_model_name(self) -> str:\n \"\"\"Best-effort human-readable model name for {model_name} injection.\"\"\"\n try:\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(self.model, BaseLanguageModel):\n return type(self.model).__name__\n except ImportError:\n pass\n\n if isinstance(self.model, list) and self.model:\n first = self.model[0]\n if isinstance(first, dict):\n name = first.get(\"name\")\n if isinstance(name, str) and name:\n return name\n\n legacy_model_name = getattr(self, \"model_name\", None)\n if isinstance(legacy_model_name, str) and legacy_model_name:\n return legacy_model_name\n return \"\"\n\n def _inject_dynamic_prompt_values(self, prompt: Any | None) -> str | None:\n \"\"\"Replace known env placeholders in the system prompt.\n\n Handles {current_date}, {model_name}, and {optional_user_context} (the\n last one ships with the structured DEFAULT_SYSTEM_PROMPT_TEMPLATE and\n is currently unused at the AgentComponent layer, so it resolves to \"\").\n Uses str.replace (not str.format) so user prompts containing literal\n braces such as JSON examples ({\"key\": 1}) never break the agent.\n\n `system_prompt` is a connectable MultilineInput, so the value can arrive\n as a Message (e.g. a Prompt node wired in). Normalize it to text first \u2014\n a raw Message has no `.replace` and used to crash the agent build.\n \"\"\"\n if prompt is None:\n return None\n prompt = _extract_text_content(prompt)\n if not prompt:\n return prompt\n replacements = {\n # Day precision keeps the system prompt byte-identical across turns so\n # providers can serve the chat history from their prompt cache.\n \"{current_date}\": datetime.now(tz=timezone.utc).date().isoformat(),\n \"{model_name}\": self._get_resolved_model_name(),\n \"{optional_user_context}\": \"\",\n }\n for placeholder, value in replacements.items():\n prompt = prompt.replace(placeholder, value)\n return prompt\n\n def create_agent_runnable(self, *, allow_interrupts: bool = True):\n \"\"\"Build the LangGraph `CompiledStateGraph` via `langchain.agents.create_agent`.\n\n Replaces the legacy `AgentExecutor` runnable inherited from\n `ToolCallingAgentComponent`. Other agent components (tool_calling, csv, json,\n openapi, sql*, vector_store_router) keep the legacy path \u2014 only AgentComponent\n runs on the new graph API.\n\n `max_iterations` and `handle_parsing_errors` (legacy AgentExecutor knobs) are\n translated to LangGraph middleware. Without that translation those user inputs\n would silently become no-ops on the new API.\n\n Provider notes:\n - WatsonX/Granite work natively with create_agent \u2014 `ChatWatsonx.bind_tools`\n handles tool_choice correctly. The legacy `create_granite_agent` path was\n dropped because it hardcoded `tool_choice='required'`, which the WatsonX\n API now rejects.\n - Ollama and other small/local models often emit malformed tool args. The\n ToolRetryMiddleware (default `retry_on=(Exception,)`, `on_failure='continue'`)\n catches Pydantic ValidationErrors from bad args and feeds the error back\n to the LLM as a retry signal, so the agent recovers gracefully.\n \"\"\"\n llm = self._get_llm()\n tools = self.tools or []\n\n # Eager bind_tools validation. `create_agent(...)` is lazy \u2014 without this,\n # an LLM that doesn't support tool calling fails on the first user message\n # instead of when the user wires up the component, which is a much worse UX.\n # Gated on a non-empty tools list so a no-tool Agent on a plain chat model\n # (which legitimately has no `bind_tools`) isn't shut out at flow-build time.\n # Providers signal \"no tool calling\" inconsistently \u2014 `NotImplementedError`\n # (langchain default), `AttributeError` (no `bind_tools` attr), or `TypeError`\n # (signature mismatch). Treat all three as the same UX failure.\n if tools:\n try:\n llm.bind_tools(tools)\n except (NotImplementedError, AttributeError, TypeError) as exc:\n # Include the underlying error so a broken tool schema or a\n # provider implementation bug is not silently disguised as a\n # \"model can't call tools\" UX error.\n msg = (\n f\"{self.display_name} does not support tool calling, \"\n \"or one of the connected tools failed to bind. \"\n \"Please connect a tool-calling capable language model and \"\n f\"verify your tools are well-formed. Underlying error: {exc!s}\"\n )\n raise NotImplementedError(msg) from exc\n\n middleware = self._build_middleware(llm, allow_interrupts=allow_interrupts)\n checkpointer = self._build_agent_checkpointer() if allow_interrupts else None\n return create_agent(\n model=llm,\n tools=tools,\n system_prompt=self.system_prompt or \"\",\n middleware=middleware or None,\n checkpointer=checkpointer,\n )\n\n def _compute_recursion_limit(self) -> int:\n \"\"\"Derive the LangGraph recursion_limit from the user-set max_iterations.\n\n Mirrors the clamp in `_build_middleware` (max(1, max_iterations)) so a\n saved 0 or negative value cannot under-cap the graph below one full\n iteration.\n\n A tool-calling cycle visits the model-call limiter's before_model and\n after_model nodes, the model, and tools. When any tool requires approval,\n HumanInTheLoopMiddleware adds another after_model node to every cycle,\n even if the model repeatedly calls an ungated tool. Leave transition\n room so the model-call limiter can end the run first.\n \"\"\"\n raw = getattr(self, \"max_iterations\", None)\n run_limit = max(1, int(raw)) if raw is not None else 15\n steps_per_cycle = 4 + bool(self._gated_interrupt_on())\n return run_limit * steps_per_cycle + 10\n\n def _build_middleware(self, llm: Any, *, allow_interrupts: bool = True) -> list:\n # `llm` is passed in (rather than re-fetched via `self._get_llm()`)\n # because some providers do credential resolution / client instantiation\n # lazily on each call. The caller \u2014 `create_agent_runnable` \u2014 already\n # resolved it once for `bind_tools`, so reuse that instance here.\n middleware: list = []\n # LangChain accepts missing IDs on AIMessage.tool_calls, but LangGraph's\n # invalid-call path and ToolRetryMiddleware both require a string when\n # they construct an error ToolMessage. Normalize at the model boundary\n # so either recovery path can return the error to the model instead of\n # crashing the flow.\n if self.tools:\n middleware.append(ToolCallIDMiddleware())\n max_iterations = getattr(self, \"max_iterations\", None)\n if max_iterations is not None:\n # `max_iterations` is a safety cap, not an \"unlimited\" toggle. A saved\n # 0 or negative value (falsy) must NOT silently drop the limiter and\n # allow an unbounded model/tool loop \u2014 clamp it to a real minimum.\n run_limit = max(1, int(max_iterations))\n middleware.append(ModelCallLimitMiddleware(run_limit=run_limit))\n # ToolRetryMiddleware only matters when there ARE tools to retry. Attaching\n # it on a no-tools agent inflates the compiled graph and adds per-invocation\n # middleware overhead for nothing, which is a measurable contributor to\n # trivial-prompt latency (QA UI-003).\n if getattr(self, \"handle_parsing_errors\", False) and self.tools:\n middleware.append(ToolRetryMiddleware(max_retries=2))\n # WatsonX models have two known platform quirks; both still reproduce on\n # the current API, so we keep the protections from the legacy\n # `create_granite_agent` path.\n # 1. Multi-tool-call assistant turns are rejected (\"This model only\n # supports single tool-calls at once!\"). Clamp to one per turn.\n # 2. Tool args occasionally come back as literal placeholder strings\n # (e.g. `<result-from-search>`). Re-invoke once with a corrective\n # SystemMessage.\n # Order: SingleToolCallMiddleware first (outermost) so the clamp is\n # applied to the final response, including any corrective re-invoke\n # produced by WatsonXPlaceholderMiddleware.\n if is_watsonx_model(llm):\n middleware.append(SingleToolCallMiddleware())\n middleware.append(WatsonXPlaceholderMiddleware())\n # Human-in-the-loop: attach only when a tool is gated AND interrupts are allowed\n # (the structured-output path disables them), keeping ungated flows unchanged.\n interrupt_on = self._gated_interrupt_on() if allow_interrupts else {}\n if interrupt_on:\n middleware.append(HumanInTheLoopMiddleware(interrupt_on=interrupt_on))\n return middleware\n\n async def run_agent(self, agent) -> Message:\n \"\"\"Run the LangGraph `CompiledStateGraph` and return the final agent Message.\n\n Overrides the legacy `LCAgentComponent.run_agent` (which builds an\n `{\"input\": str, \"chat_history\": [...]}` dict for `AgentExecutor`). The graph\n wants `{\"messages\": [BaseMessage, ...]}`. The event stream is wrapped with\n `adapt_graph_events_to_executor_shape` so the legacy `process_agent_events`\n (in `lfx.base.agents.events`) can be reused unchanged.\n \"\"\"\n messages = build_initial_messages(\n input_value=self.input_value,\n chat_history=getattr(self, \"chat_history\", None),\n )\n input_dict = {\"messages\": messages}\n\n agent_message = self._build_initial_agent_message()\n token_usage_handler = TokenUsageCallbackHandler()\n\n # Stream tokens to the event manager when running inside the Langflow runtime.\n # This is what powers the live-typing view in the chat UI.\n on_token_callback: OnTokenFunctionType | None = None\n if getattr(self, \"_event_manager\", None):\n on_token_callback = cast(\"OnTokenFunctionType\", self._event_manager.on_token)\n\n # Align LangGraph's `recursion_limit` with `max_iterations` so the\n # middleware cap (ModelCallLimitMiddleware) is what bounds the loop \u2014\n # not LangGraph's default 25-step guard, which fires at ~12 model+tool\n # iterations and raises a raw GraphRecursionError (QA UI-009/UI-010).\n # Include the extra after_model node when tool approval is configured.\n recursion_limit = self._compute_recursion_limit()\n\n agent_config: dict[str, Any] = {\n \"callbacks\": [\n AgentAsyncHandler(self.log),\n token_usage_handler,\n *self._get_shared_callbacks(),\n ],\n \"recursion_limit\": recursion_limit,\n }\n # The durable checkpointer keys on the per-run thread_id; it must be in the\n # astream_events config (not just create_agent) for both initial run and resume.\n thread_id = self._agent_thread_id()\n get_pending_interrupt = None\n stream_input: Any = input_dict\n # A checkpointer is only present when the agent was built with interrupts enabled\n # (the structured-output path builds without one); never probe its state otherwise.\n interrupts_enabled = getattr(agent, \"checkpointer\", None) is not None\n if interrupts_enabled and thread_id and self._gated_interrupt_on():\n agent_config[\"configurable\"] = {\"thread_id\": thread_id}\n get_pending_interrupt = self._pending_interrupt_getter(agent, agent_config)\n if self._has_candidate_decision(thread_id):\n # The injected decision must match the pending interrupt's nonce, so read\n # the interrupt first; a matched decision resumes the checkpointed thread.\n value, interrupt_id = await self._read_pending_interrupt(agent, agent_config)\n decision = self._injected_agent_decision(thread_id, interrupt_id)\n if decision is not None:\n action_requests = (value or {}).get(\"action_requests\") or []\n stream_input = Command(\n resume={\"decisions\": self._build_resume_decisions(decision, action_requests)}\n )\n stream = adapt_graph_events_to_executor_shape(\n agent.astream_events(stream_input, config=agent_config, version=\"v2\")\n )\n try:\n result = await process_agent_events(\n stream,\n agent_message,\n cast(\"SendMessageFunctionType\", self.send_message),\n on_token_callback,\n get_pending_interrupt=get_pending_interrupt,\n )\n except AgentPausedError as e:\n # Why: retract the empty partial bubble (leaks as \"[]\"); the HITL card supersedes it, resume re-emits it.\n paused_message = e.agent_message or agent_message\n msg_id = paused_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(paused_message, category=\"remove_message\")\n return self._suspend_for_tool_approval(e.request, paused_message)\n except ExceptionWithMessageError as e:\n # Drop the half-stored partial message from the DB (only if it was\n # actually persisted) and tell the frontend to remove the stale bubble.\n if hasattr(e, \"agent_message\"):\n msg_id = e.agent_message.get_id()\n if msg_id:\n await delete_message(id_=msg_id)\n await self._send_message_event(e.agent_message, category=\"remove_message\")\n # exception(), not error(f\"...{e}\"): this class's str() interpolates the model's\n # partial completion, and passing the exception rather than formatting it is what\n # gives the exported record an error.type to triage on.\n logger.exception(\"Agent run failed after a partial message was emitted\")\n raise\n\n usage_data = token_usage_handler.get_usage()\n if usage_data:\n self._token_usage = usage_data\n result.properties.usage = usage_data\n # Only round-trip the DB when the message was stored (Chat Output wired).\n # `_should_skip_message=True` leaves `result.get_id()` empty; persisting\n # then would create a phantom row.\n if result.get_id():\n stored_result = await self._update_stored_message(result)\n await self._send_message_event(stored_result)\n result = stored_result\n\n self.status = result\n return result\n\n def _build_initial_agent_message(self) -> Message:\n \"\"\"Construct the placeholder agent Message that `process_agent_events` mutates.\"\"\"\n if hasattr(self, \"graph\"):\n session_id = self.graph.session_id\n elif hasattr(self, \"_session_id\"):\n session_id = self._session_id\n else:\n session_id = None\n\n sender_name = get_chat_output_sender_name(self) or self.display_name or \"AI\"\n return Message(\n sender=MESSAGE_SENDER_AI,\n sender_name=sender_name,\n properties={\"icon\": \"Bot\", \"state\": \"partial\"},\n # `text=\"\"` sentinel so MessageTable's no_content check accepts\n # an in-flight agent message whose content_blocks haven't been\n # populated yet. Mirrors ChatInput's convention.\n text=\"\",\n # Flat chronological event log; see lfx.base.agents.events.\n content_blocks=[],\n session_id=session_id or uuid.uuid4(),\n )\n\n def _selected_model_remediation_context(self) -> tuple[str | None, str | None, Any | None]:\n \"\"\"Return provider/name plus a connected model target, when present.\"\"\"\n try:\n selected = self._resolve_selected_model()\n if isinstance(selected, list) and selected and isinstance(selected[0], dict):\n return selected[0].get(\"provider\"), selected[0].get(\"name\"), None\n\n from langchain_core.language_models import BaseLanguageModel\n\n if isinstance(selected, BaseLanguageModel):\n model_name = None\n for attr in (\"model_name\", \"model\", \"model_id\"):\n value = getattr(selected, attr, None)\n if isinstance(value, str) and value:\n model_name = value\n break\n return self._connected_model_provider(selected), model_name, selected\n except (AttributeError, TypeError, ValueError, KeyError, ImportError):\n pass\n return None, None, None\n\n def _connected_model_provider(self, model: Any) -> str | None:\n \"\"\"Resolve a connected model's provider from the source component.\n\n Runtime model classes are not provider identities: OpenAI, OpenRouter,\n and compatible endpoints can all produce ``ChatOpenAI``. The incoming\n model edge preserves the source component, so prefer its explicit\n provider override or selected-model metadata, then its provider display\n name. If the Agent is used without graph provenance, leave the provider\n unknown so provider-scoped remediations remain disabled.\n \"\"\"\n vertex = getattr(self, \"_vertex\", None)\n if vertex is None:\n return None\n source_id = vertex.get_incoming_edge_by_target_param(\"model\")\n if not source_id:\n return None\n source = vertex.graph.get_vertex(source_id)\n component = getattr(source, \"custom_component\", None)\n if component is None:\n return None\n\n candidate = getattr(component, \"provider\", None)\n\n if not isinstance(candidate, str) or not candidate:\n selected_model = getattr(component, \"model\", None)\n if isinstance(selected_model, list) and selected_model and isinstance(selected_model[0], dict):\n candidate = selected_model[0].get(\"provider\")\n\n if not isinstance(candidate, str) or not candidate:\n candidate = getattr(component, \"display_name\", None)\n if not isinstance(candidate, str) or not candidate:\n return None\n\n from lfx.base.models.unified_models.provider_queries import get_model_provider_metadata\n\n provider_metadata = get_model_provider_metadata().get(candidate, {})\n expected_class = provider_metadata.get(\"mapping\", {}).get(\"model_class\")\n model_classes = {base.__name__ for base in type(model).__mro__}\n return candidate if expected_class in model_classes else None\n\n async def _run_agent_with_model_remediation(\n self,\n run_once: Callable[[], Awaitable[Message]],\n ) -> Message:\n \"\"\"Run one Agent operation, retrying safe provider-validation failures.\n\n Registered remediations must identify request-validation failures that\n occur before tool execution. A failure that can happen after a tool runs\n must instead retry at the model-call boundary to avoid repeating tool\n side effects.\n \"\"\"\n from lfx.base.models.model_remediation import apply_overrides_to_model, find_remediation, remember\n\n provider, model_name, connected_model = self._selected_model_remediation_context()\n applied: set[str] = set()\n while True:\n try:\n result = await run_once()\n except (ValueError, TypeError, KeyError):\n await logger.aexception(\"Agent run failed\")\n raise\n except Exception as exc:\n # run_agent may wrap the provider error in ExceptionWithMessageError, whose\n # str() carries the model's partial completion. Matching on it locally is fine;\n # logging it is not, so the record below passes the exception instead.\n error_text = f\"{exc} {getattr(exc, '__cause__', '') or ''}\"\n remediation = find_remediation(error_text, provider, already_applied=applied)\n if remediation is None:\n await logger.aexception(\"Agent run failed with no remediation available\")\n raise\n if connected_model is not None and not apply_overrides_to_model(connected_model, remediation.overrides):\n await logger.aerror(\n f\"model.remediation.unapplied name={remediation.name} provider={provider} model={model_name}\"\n )\n raise\n applied.add(remediation.name)\n if connected_model is None:\n self._model_overrides = {\n **(getattr(self, \"_model_overrides\", None) or {}),\n **remediation.overrides,\n }\n else:\n # Connected outputs are shared objects across downstream flow\n # branches. The mutation is intentionally flow-scoped: sibling\n # branches holding this model will see the matched override too.\n await logger.adebug(\n f\"model.remediation.shared_model name={remediation.name} provider={provider} model={model_name}\"\n )\n await logger.awarning(\n f\"model.remediation.applied name={remediation.name} provider={provider} model={model_name}\"\n )\n else:\n if connected_model is None and getattr(self, \"_model_overrides\", None):\n remember(provider, model_name, self._model_overrides)\n return result\n\n async def message_response(self) -> Message:\n async def _run_once() -> Message:\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=self._inject_dynamic_prompt_values(self.system_prompt),\n )\n agent = self.create_agent_runnable()\n return await self.run_agent(agent)\n\n result = await self._run_agent_with_model_remediation(_run_once)\n self._agent_result = result\n return result\n\n async def json_response(self) -> Data:\n \"\"\"Produce structured Data via native LLM structured output, with prompt-based fallback.\n\n Native path (no tools, llm has with_structured_output) bypasses the agent loop and\n returns provider-validated JSON. When tools are attached, falls back to running the\n agent with a schema-augmented system prompt and parsing the final message content.\n \"\"\"\n from lfx.components.models_and_agents.structured_output.structured_output_orchestrator import (\n orchestrate_structured_output,\n )\n\n try:\n llm_model, self.chat_history, self.tools = await self.get_agent_requirements()\n except (ValueError, TypeError) as exc:\n await logger.aexception(\"json_response.requirements_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n injected_system_prompt = self._inject_dynamic_prompt_values(getattr(self, \"system_prompt\", \"\") or \"\") or \"\"\n format_instructions = getattr(self, \"format_instructions\", \"\") or \"\"\n output_schema = getattr(self, \"output_schema\", None) or []\n has_tools = bool(self.tools)\n\n async def _run_agent_for_fallback(augmented_prompt: str) -> str:\n first_attempt = True\n\n async def _run_once() -> Message:\n nonlocal first_attempt, llm_model\n if first_attempt:\n first_attempt = False\n 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=augmented_prompt,\n )\n # Structured output cannot suspend mid-parse: disable tool-approval interrupts.\n agent_runnable = self.create_agent_runnable(allow_interrupts=False)\n return await self.run_agent(agent_runnable)\n\n with _suppress_send_message(self):\n result = await self._run_agent_with_model_remediation(_run_once)\n return _extract_text_content(result)\n\n try:\n return await orchestrate_structured_output(\n llm=llm_model,\n output_schema=output_schema,\n system_prompt=injected_system_prompt,\n format_instructions=format_instructions,\n input_value=_extract_text_content(self.input_value),\n run_prompt_fallback=_run_agent_for_fallback,\n prefer_native=not has_tools,\n )\n except (\n ExceptionWithMessageError,\n ValueError,\n TypeError,\n NotImplementedError,\n AttributeError,\n ) as exc:\n await logger.aexception(\"json_response.orchestration_failed\")\n return Data(data={\"content\": \"\", \"error\": str(exc)})\n\n async def get_memory_data(self):\n # Scope by flow_id so default playground session names (e.g. \"New Session 0\")\n # cannot leak chat history across unrelated flows. See issue #13059.\n # The helper also returns [] when n_messages == 0, preserving the\n # explicit \"memory disabled\" contract from MemoryComponent.retrieve_messages.\n messages = await aget_agent_chat_history(\n session_id=self.graph.session_id,\n flow_id=getattr(self.graph, \"flow_id\", None),\n context_id=self.context_id,\n n_messages=self.n_messages,\n user_id=_safe_graph_user_id(self),\n )\n return [\n message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n ]\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,\n build_config: dotdict,\n field_value: list[dict],\n field_name: str | None = None,\n ) -> dotdict:\n from lfx.services.model_provider_policy import ModelProviderPolicyPurpose\n\n policy_parameters = dict(getattr(self, \"_parameters\", {}) or {})\n if field_name:\n policy_parameters[field_name] = field_value\n await self.arequire_model_provider_policy(\n ModelProviderPolicyPurpose.CONFIGURE,\n parameters=policy_parameters,\n )\n # Update model options with caching (for all field changes).\n # The tool-calling constraint lives on the ModelInput's ``filters``\n # field (declared above); ``handle_model_input_update`` reads it\n # and applies the filter to both the dropdown options and the\n # sticky-default re-injection path.\n build_config = handle_model_input_update(\n component=self,\n build_config=dict(build_config),\n field_value=field_value,\n field_name=field_name,\n )\n build_config = dotdict(build_config)\n\n if field_name == \"model\":\n build_config = self.update_input_types(build_config)\n\n # Validate required keys. `verbose` was dropped from the input set\n # (see `_agent_base_inputs` \u2014 the create_agent event stream already\n # surfaces every step), so it is intentionally NOT required here.\n # Saved flows that still carry a `verbose` value just ignore it on\n # load.\n default_keys = [\n \"code\",\n \"_type\",\n \"model\",\n \"tools\",\n \"input_value\",\n \"add_current_date_tool\",\n \"add_calculator_tool\",\n \"system_prompt\",\n \"max_iterations\",\n \"handle_parsing_errors\",\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 await self._filter_legacy_provider_options(build_config)\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\n tools = component_toolkit(component=self).get_tools(\n tool_name=\"Call_Agent\",\n # here we do not use the shared callbacks as we are exposing the agent as a tool\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\n return tools\n"
},
"context_id": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Context ID",
"dynamic": false,
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "context_id",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"format_instructions": {
"_input_type": "MultilineInput",
"advanced": true,
"ai_enabled": false,
"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",
"override_skip": false,
"password": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"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": "Adds tool-execution retry as a safety net. `create_agent` already feeds tool-call validation errors back to the LLM automatically; this flag layers `ToolRetryMiddleware` on top so transient tool runtime failures are retried (max 2 retries).",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "handle_parsing_errors",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "bool",
"value": true
},
"input_value": {
"_input_type": "MessageInput",
"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",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": true,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"max_iterations": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Iterations",
"dynamic": false,
"info": "Maximum number of model calls the agent can make before stopping (maps to `ModelCallLimitMiddleware.run_limit` on the create_agent path). Must be at least 1 \u2014 it is a safety cap, never 'unlimited'.",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "max_iterations",
"override_skip": false,
"placeholder": "",
"range_spec": {
"max": 128000,
"min": 1,
"step": 1,
"step_type": "int"
},
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "int",
"value": 15
},
"max_tokens": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Tokens",
"dynamic": false,
"info": "Maximum number of tokens to generate. Set to 0 for no explicit limit. Field name varies by provider.",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "max_tokens",
"override_skip": false,
"placeholder": "",
"range_spec": {
"max": 128000,
"min": 1,
"step": 1,
"step_type": "int"
},
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "int",
"value": 0
},
"model": {
"_input_type": "ModelInput",
"advanced": false,
"display_name": "Language Model",
"dynamic": false,
"external_options": {
"fields": {
"data": {
"node": {
"display_name": "Connect other models",
"icon": "CornerDownLeft",
"name": "connect_other_models"
}
}
}
},
"filters": {
"tool_calling": true
},
"info": "Select your model provider",
"input_types": [
"LanguageModel"
],
"list": false,
"list_add_label": "Add More",
"model_type": "language",
"name": "model",
"options": [
{
"category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"api_key_param": "api_key",
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
"model_name_param": "model",
"reasoning_models": [
"gpt-5.5-pro"
]
},
"name": "gpt-5.5-pro",
"provider": "OpenAI"
},
{
"category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"api_key_param": "api_key",
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
"model_name_param": "model",
"reasoning_models": [
"gpt-5.5"
]
},
"name": "gpt-5.5",
"provider": "OpenAI"
},
{
"category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"api_key_param": "api_key",
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
"model_name_param": "model",
"reasoning_models": [
"gpt-5.4-nano"
]
},
"name": "gpt-5.4-nano",
"provider": "OpenAI"
},
{
"category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"api_key_param": "api_key",
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
"model_name_param": "model",
"reasoning_models": [
"gpt-5.4-mini"
]
},
"name": "gpt-5.4-mini",
"provider": "OpenAI"
},
{
"category": "OpenAI",
"icon": "OpenAI",
"metadata": {
"api_key_param": "api_key",
"context_length": 128000,
"max_tokens_field_name": "max_tokens",
"model_class": "ChatOpenAI",
"model_name_param": "model",
"reasoning_models": [
"gpt-5.4"
]
},
"name": "gpt-5.4",
"provider": "OpenAI"
},
{
"category": "Google Generative AI",
"icon": "GoogleGenerativeAI",
"metadata": {
"api_key_param": "google_api_key",
"context_length": 128000,
"max_tokens_field_name": "max_output_tokens",
"model_class": "ChatGoogleGenerativeAIFixed",
"model_name_param": "model"
},
"name": "gemini-3.5-flash",
"provider": "Google Generative AI"
},
{
"category": "Google Generative AI",
"icon": "GoogleGenerativeAI",
"metadata": {
"api_key_param": "google_api_key",
"context_length": 128000,
"max_tokens_field_name": "max_output_tokens",
"model_class": "ChatGoogleGenerativeAIFixed",
"model_name_param": "model"
},
"name": "gemini-3.1-flash-lite",
"provider": "Google Generative AI"
},
{
"category": "Google Generative AI",
"icon": "GoogleGenerativeAI",
"metadata": {
"api_key_param": "google_api_key",
"context_length": 128000,
"max_tokens_field_name": "max_output_tokens",
"model_class": "ChatGoogleGenerativeAIFixed",
"model_name_param": "model"
},
"name": "gemma-4-31b-it",
"provider": "Google Generative AI"
},
{
"category": "Google Generative AI",
"icon": "GoogleGenerativeAI",
"metadata": {
"api_key_param": "google_api_key",
"context_length": 128000,
"max_tokens_field_name": "max_output_tokens",
"model_class": "ChatGoogleGenerativeAIFixed",
"model_name_param": "model"
},
"name": "gemma-4-26b-a4b-it",
"provider": "Google Generative AI"
}
],
"override_skip": false,
"placeholder": "Setup Provider",
"real_time_refresh": true,
"refresh_button": true,
"required": true,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"track_in_telemetry": false,
"type": "model",
"value": ""
},
"n_messages": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Number of Chat History Messages",
"dynamic": false,
"info": "Number of chat history messages to retrieve.",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "n_messages",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "int",
"value": 100
},
"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.",
"input_types": [
"DataFrame",
"Table"
],
"is_list": true,
"list_add_label": "Add More",
"name": "output_schema",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"table_icon": "Table",
"table_schema": [
{
"default": "field",
"description": "Specify the name of the output field.",
"display_name": "Name",
"edit_mode": "inline",
"formatter": "text",
"name": "name",
"type": "str"
},
{
"default": "description of field",
"description": "Describe the purpose of the output field.",
"display_name": "Description",
"edit_mode": "popover",
"formatter": "text",
"name": "description",
"type": "str"
},
{
"default": "str",
"description": "Indicate the data type of the output field (e.g., str, int, float, bool, dict).",
"display_name": "Type",
"edit_mode": "inline",
"formatter": "text",
"name": "type",
"options": [
"str",
"int",
"float",
"bool",
"dict"
],
"type": "str"
},
{
"default": "False",
"description": "Set to True if this output field should be a list of the specified type.",
"display_name": "As List",
"edit_mode": "inline",
"formatter": "text",
"name": "multiple",
"type": "boolean"
}
],
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"trigger_icon": "Table",
"trigger_text": "Open table",
"type": "table",
"value": []
},
"project_id": {
"_input_type": "StrInput",
"advanced": false,
"display_name": "watsonx Project ID",
"dynamic": false,
"info": "The project ID associated with the foundation model (IBM watsonx.ai only)",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"name": "project_id",
"override_skip": false,
"placeholder": "",
"required": false,
"show": false,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": ""
},
"stream": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Stream",
"dynamic": false,
"info": "Stream the response from the model. Streaming works only in Chat.",
"input_types": [],
"list": false,
"list_add_label": "Add More",
"name": "stream",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"track_in_telemetry": true,
"type": "bool",
"value": true
},
"system_prompt": {
"_input_type": "MultilineInput",
"advanced": false,
"ai_enabled": false,
"copy_field": false,
"display_name": "Agent Instructions",
"dynamic": false,
"info": "System Prompt: Initial instructions and context provided to guide the agent's behavior. Supports dynamic placeholders: {current_date}, {model_name}, {optional_user_context}.",
"input_types": [
"Message"
],
"list": false,
"list_add_label": "Add More",
"load_from_db": false,
"multiline": true,
"name": "system_prompt",
"override_skip": false,
"password": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "str",
"value": "You are a portfolio website generator. You receive a candidate's resume (an uploaded file). First read the resume and extract the relevant details (name, job title, professional summary, experience, projects, skills, education, and contact/links). Then produce the website.\n\nGenerate a single-page portfolio website using HTML and CSS that takes a resume in JSON format as input and dynamically renders the following sections with a well-structured and aesthetic layout:\n\n\ud83d\udccc Sections & Content Requirements:\n\t1.\tHeader:\n\t\u2022\tDisplay the person\u2019s name, job title, and a professional tagline prominently.\n\t\u2022\tEnsure the name is bold and eye-catching, with subtle emphasis on the job title.\n\t2.\tAbout Me:\n\t\u2022\tExtract and enhance the personal summary from the resume, making it engaging, concise, and readable.\n\t\u2022\tUse short, well-structured sentences to improve clarity.\n\t3.\tExperience:\n\t\u2022\tList past job roles with company names, durations, and a refined description of responsibilities.\n\t\u2022\tEnsure descriptions are professionally formatted, with key contributions highlighted.\n\t4.\tProjects:\n\t\u2022\tDisplay projects as a neatly styled list.\n\t\u2022\tEach project includes a title, refined description, technologies used, and rounded buttons linking to GitHub or live demo (if available).\n\t5.\tSkills:\n\t\u2022\tDisplay skills as aesthetic pill-style badges below the Skills section title. Display all skills mentioned\n\t\u2022\tArrange in a well-balanced, ensuring readability and consistent spacing.\n\t6.\tEducation:\n\t\u2022\tList degrees, institutions, and years attended in a clean and professional format.\n\t\u2022\tMaintain uniformity in typography and spacing.\n\t7.\tAwards & Publications (if any):\n\t\u2022\tIf the resume contains awards or publications, display them in a separate section.\n\t\u2022\tEach entry includes the title, organization, and year, ensuring clean alignment.\n\t8.\tContact:\n\t\u2022\tDisplay email, social media links, and an optional contact button.\n\t\u2022\tEnsure social media links are clearly visible, with modern and accessible icon buttons.\n\n\ud83c\udfa8 Styling & Aesthetic Requirements:\n\n\u2705 Minimalist & Elegant:\n\t\u2022\tClean layout with ample whitespace for breathing room.\n\t\u2022\tConsistent spacing across all sections.\n\n\u2705 Fast & Lightweight:\n\t\u2022\tUse only HTML & CSS (no JavaScript required).\n\t\u2022\tEnsure a smooth, fast-loading experience.\n\n\u2705 Beautiful Typography:\n\t\u2022\tUse a modern, professional Google Font that complements the design.\n\t\u2022\tEnsure text readability with proper size, weight, and contrast.\n\n\u2705 Visually Harmonious Colors & Themes:\n\t\u2022\tFollow a cohesive color palette that ensures a modern, professional feel.\n\t\u2022\tEnsure background colors, text colors, and section dividers are consistent and complementary.\n\t\u2022\tAvoid hard-to-read combinations (e.g., light text on a light background).\n\n\u2705 Responsive & Readable Design:\n\t\u2022\tMobile-first approach, adapting to desktop, tablet, and mobile views.\n\t\u2022\tMaintain consistency in padding, margins, and alignment.\n\n\u2705 Dark Mode Support:\n\t\u2022\tAuto-detect system settings and adjust the theme accordingly.\n\t\u2022\tEnsure clear contrasts and readability in both light and dark modes.\n\n\u2705 Embedded CSS:\n\t\u2022\tEnsure CSS is written directly in the HTML file within <style> tags for easy integration.\n\n\ud83d\ude80 Key Enhancements for a Superior First Impression:\n\t\u2022\tEnsure the color scheme is visually cohesive and all text is legible against the background.\n\t\u2022\tMaintain uniform padding and spacing for a professional, structured appearance.\n\t\u2022\tImprove text formatting, ensuring sections are balanced and visually engaging.\n\t\u2022\tFollow aesthetically pleasing, simple yet modern design principles.\n\n\ud83c\udf1f End Goal:\n\nThe final output should be a well-balanced, visually stunning, and highly readable portfolio website that immediately impresses viewers. The design must be polished, with an intuitive layout, ensuring consistency, clarity, and elegance.\nEnsuring all details in resume are well displayed in portfolio website.\nInclude all experiences, projects and education details from resume in the html code generated.\n"
},
"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",
"override_skip": false,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"track_in_telemetry": false,
"type": "other",
"value": ""
}
},
"tool_mode": false
},
"selected_output": "response",
"showNode": true,
"type": "Agent"
},
"dragging": false,
"id": "Agent-portfolio",
"measured": {
"height": 430,
"width": 320
},
"position": {
"x": 2174.626510909065,
"y": 439.5147119393939
},
"positionAbsolute": {
"x": 2174.626510909065,
"y": 439.5147119393939
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"id": "note-pf",
"node": {
"description": "# \ud83d\udcbb Portfolio Website Code Generator\n\nUpload your resume and an **Agent** generates a single-page portfolio website (HTML + CSS).\n\n## Setup\n1. **File** - upload your resume (PDF or TXT).\n2. **Agent** - add your LLM key (any provider in the Model dropdown).\n\n## How it works\n1. **File \u2192 Agent** - the Agent reads your resume.\n2. **Agent** - extracts your details and writes the portfolio site (header, about, experience, projects, skills, contact) as HTML/CSS.\n3. **Agent \u2192 Chat Output** - copy the generated code.\n\n## Run\nUpload your resume, open **Playground**, and run. Tip: a clearly formatted resume (headings, bullet points) produces the best result.",
"display_name": "",
"documentation": "",
"i18n_key": "template_notes.portfolio_website_code_generator.c217664c",
"template": {
"backgroundColor": "blue"
}
},
"type": "note"
},
"dragging": false,
"height": 720,
"id": "note-pf",
"measured": {
"height": 720,
"width": 675
},
"position": {
"x": 871.5194833283779,
"y": 331.15289143738033
},
"positionAbsolute": {
"x": 1674.626510909065,
"y": 399.5147119393939
},
"resizing": false,
"selected": false,
"type": "noteNode",
"width": 675
}
],
"viewport": {
"x": -181.9651182422731,
"y": -55.290304920133394,
"zoom": 0.5523066405247259
}
},
"description": "Upload a resume and an Agent generates a single-page portfolio website (HTML/CSS).",
"endpoint_name": null,
"id": "31eca84e-2c28-45e8-9d10-0ad237c01455",
"is_component": false,
"last_tested_version": "1.10.0",
"locked": false,
"name": "Portfolio Website Code Generator",
"tags": [
"chatbots",
"coding"
]
}How to use this workflow
- Review the pre-filled example and source files above.
- Copy the template or download
Portfolio Website Code Generator.json, then use it in your model, IDE, or workflow tool. - Compare your result with the sample output when one is provided.
Frequently Asked Questions
How do I use Workflow to Langflow Graph to Portfolio Website Code Generator?
Open the workflow on Promptally, review the pre-filled example, then copy the template or download Portfolio Website Code Generator.json and paste it into your model, IDE or workflow tool. Workflow to Langflow Graph to Portfolio Website Code Generator is a static blueprint with no dynamic variables. Copy it and use it as-is.
Is Workflow to Langflow Graph to Portfolio Website Code Generator free?
Yes. Workflow to Langflow Graph to Portfolio Website Code Generator is free to view, copy and download on Promptally without creating an account. It is published under the MIT license.
What variables does Workflow to Langflow Graph to Portfolio Website Code Generator need?
Workflow to Langflow Graph to Portfolio Website Code Generator is a static blueprint with no dynamic variables. Copy it and use it as-is.