langflow-base-nightly 1.7.0.dev18__py3-none-any.whl → 1.7.0.dev20__py3-none-any.whl

langflow/initial_setup/starter_projects/News Aggregator.json

@@ -1184,7 +1184,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -1896,7 +1896,7 @@
             "last_updated": "2025-09-30T16:16:26.172Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "5d810fae1fd1",
+              "code_hash": "790473c08728",
               "dependencies": {
                 "dependencies": [
                   {
@@ -1957,6 +1957,25 @@
             "pinned": false,
             "template": {
               "_type": "Component",
+              "append_mode": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Append",
+                "dynamic": false,
+                "info": "Append to file if it exists (only for plain text formats). Disabled for binary formats like Excel.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "append_mode",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "track_in_telemetry": true,
+                "type": "bool",
+                "value": false
+              },
               "aws_access_key_id": {
                 "_input_type": "SecretStrInput",
                 "advanced": true,
@@ -2081,7 +2100,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nfrom collections.abc import AsyncIterator, Iterator\nfrom pathlib import Path\n\nimport orjson\nimport pandas as pd\nfrom fastapi import UploadFile\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.custom import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import DropdownInput, HandleInput, SecretStrInput, StrInput\nfrom lfx.schema import Data, DataFrame, Message\nfrom lfx.services.deps import get_settings_service, get_storage_service, session_scope\nfrom lfx.template.field.base import Output\n\n\nclass SaveToFileComponent(Component):\n    display_name = \"Write File\"\n    description = \"Save data to local file, AWS S3, or Google Drive in the selected format.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#save-file\"\n    icon = \"file-text\"\n    name = \"SaveToFile\"\n\n    # File format options for different storage types\n    LOCAL_DATA_FORMAT_CHOICES = [\"csv\", \"excel\", \"json\", \"markdown\"]\n    LOCAL_MESSAGE_FORMAT_CHOICES = [\"txt\", \"json\", \"markdown\"]\n    AWS_FORMAT_CHOICES = [\n        \"txt\",\n        \"json\",\n        \"csv\",\n        \"xml\",\n        \"html\",\n        \"md\",\n        \"yaml\",\n        \"log\",\n        \"tsv\",\n        \"jsonl\",\n        \"parquet\",\n        \"xlsx\",\n        \"zip\",\n    ]\n    GDRIVE_FORMAT_CHOICES = [\"txt\", \"json\", \"csv\", \"xlsx\", \"slides\", \"docs\", \"jpg\", \"mp3\"]\n\n    inputs = [\n        # Storage location selection\n        SortableListInput(\n            name=\"storage_location\",\n            display_name=\"Storage Location\",\n            placeholder=\"Select Location\",\n            info=\"Choose where to save the file.\",\n            options=[\n                {\"name\": \"Local\", \"icon\": \"hard-drive\"},\n                {\"name\": \"AWS\", \"icon\": \"Amazon\"},\n                {\"name\": \"Google Drive\", \"icon\": \"google\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        # Common inputs\n        HandleInput(\n            name=\"input\",\n            display_name=\"File Content\",\n            info=\"The input to save.\",\n            dynamic=True,\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        StrInput(\n            name=\"file_name\",\n            display_name=\"File Name\",\n            info=\"Name file will be saved as (without extension).\",\n            required=True,\n            show=False,\n            tool_mode=True,\n        ),\n        # Format inputs (dynamic based on storage location)\n        DropdownInput(\n            name=\"local_format\",\n            display_name=\"File Format\",\n            options=list(dict.fromkeys(LOCAL_DATA_FORMAT_CHOICES + LOCAL_MESSAGE_FORMAT_CHOICES)),\n            info=\"Select the file format for local storage.\",\n            value=\"json\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"aws_format\",\n            display_name=\"File Format\",\n            options=AWS_FORMAT_CHOICES,\n            info=\"Select the file format for AWS S3 storage.\",\n            value=\"txt\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"gdrive_format\",\n            display_name=\"File Format\",\n            options=GDRIVE_FORMAT_CHOICES,\n            info=\"Select the file format for Google Drive storage.\",\n            value=\"txt\",\n            show=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=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=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=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=True,\n        ),\n        StrInput(\n            name=\"s3_prefix\",\n            display_name=\"S3 Prefix\",\n            info=\"Prefix for all files in S3.\",\n            show=False,\n            advanced=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=True,\n        ),\n        StrInput(\n            name=\"folder_id\",\n            display_name=\"Google Drive Folder ID\",\n            info=(\n                \"The Google Drive folder ID where the file will be uploaded. \"\n                \"The folder must be shared with the service account email.\"\n            ),\n            show=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [Output(display_name=\"File Path\", name=\"message\", method=\"save_to_file\")]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        \"\"\"Update build configuration to show/hide fields based on storage location selection.\"\"\"\n        if field_name != \"storage_location\":\n            return build_config\n\n        # Extract selected storage location\n        selected = [location[\"name\"] for location in field_value] if isinstance(field_value, list) else []\n\n        # Hide all dynamic fields first\n        dynamic_fields = [\n            \"file_name\",  # Common fields (input is always visible)\n            \"local_format\",\n            \"aws_format\",\n            \"gdrive_format\",\n            \"aws_access_key_id\",\n            \"aws_secret_access_key\",\n            \"bucket_name\",\n            \"aws_region\",\n            \"s3_prefix\",\n            \"service_account_key\",\n            \"folder_id\",\n        ]\n\n        for f_name in dynamic_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            # Show file_name when any storage location is selected (input is always visible)\n            if \"file_name\" in build_config:\n                build_config[\"file_name\"][\"show\"] = True\n\n            if location == \"Local\":\n                if \"local_format\" in build_config:\n                    build_config[\"local_format\"][\"show\"] = True\n\n            elif location == \"AWS\":\n                aws_fields = [\n                    \"aws_format\",\n                    \"aws_access_key_id\",\n                    \"aws_secret_access_key\",\n                    \"bucket_name\",\n                    \"aws_region\",\n                    \"s3_prefix\",\n                ]\n                for f_name in aws_fields:\n                    if f_name in build_config:\n                        build_config[f_name][\"show\"] = True\n\n            elif location == \"Google Drive\":\n                gdrive_fields = [\"gdrive_format\", \"service_account_key\", \"folder_id\"]\n                for f_name in gdrive_fields:\n                    if f_name in build_config:\n                        build_config[f_name][\"show\"] = True\n\n        return build_config\n\n    async def save_to_file(self) -> Message:\n        \"\"\"Save the input to a file and upload it, returning a confirmation message.\"\"\"\n        # Validate inputs\n        if not self.file_name:\n            msg = \"File name must be provided.\"\n            raise ValueError(msg)\n        if not self._get_input_type():\n            msg = \"Input type is not set.\"\n            raise ValueError(msg)\n\n        # Get selected storage location\n        storage_location = self._get_selected_storage_location()\n        if not storage_location:\n            msg = \"Storage location must be selected.\"\n            raise ValueError(msg)\n\n        # Route to appropriate save method based on storage location\n        if storage_location == \"Local\":\n            return await self._save_to_local()\n        if storage_location == \"AWS\":\n            return await self._save_to_aws()\n        if storage_location == \"Google Drive\":\n            return await self._save_to_google_drive()\n        msg = f\"Unsupported storage location: {storage_location}\"\n        raise ValueError(msg)\n\n    def _get_input_type(self) -> str:\n        \"\"\"Determine the input type based on the provided input.\"\"\"\n        # Use exact type checking (type() is) instead of isinstance() to avoid inheritance issues.\n        # Since Message inherits from Data, isinstance(message, Data) would return True for Message objects,\n        # causing Message inputs to be incorrectly identified as Data type.\n        if type(self.input) is DataFrame:\n            return \"DataFrame\"\n        if type(self.input) is Message:\n            return \"Message\"\n        if type(self.input) is Data:\n            return \"Data\"\n        msg = f\"Unsupported input type: {type(self.input)}\"\n        raise ValueError(msg)\n\n    def _get_default_format(self) -> str:\n        \"\"\"Return the default file format based on input type.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return \"csv\"\n        if self._get_input_type() == \"Data\":\n            return \"json\"\n        if self._get_input_type() == \"Message\":\n            return \"json\"\n        return \"json\"  # Fallback\n\n    def _adjust_file_path_with_format(self, path: Path, fmt: str) -> Path:\n        \"\"\"Adjust the file path to include the correct extension.\"\"\"\n        file_extension = path.suffix.lower().lstrip(\".\")\n        if fmt == \"excel\":\n            return Path(f\"{path}.xlsx\").expanduser() if file_extension not in [\"xlsx\", \"xls\"] else path\n        return Path(f\"{path}.{fmt}\").expanduser() if file_extension != fmt else path\n\n    async def _upload_file(self, file_path: Path) -> None:\n        \"\"\"Upload the saved file using the upload_user_file service.\"\"\"\n        from langflow.api.v2.files import upload_user_file\n        from langflow.services.database.models.user.crud import get_user_by_id\n\n        # Ensure the file exists\n        if not file_path.exists():\n            msg = f\"File not found: {file_path}\"\n            raise FileNotFoundError(msg)\n\n        # Upload the file\n        with file_path.open(\"rb\") as f:\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for file saving.\"\n                    raise ValueError(msg)\n                current_user = await get_user_by_id(db, self.user_id)\n\n                await upload_user_file(\n                    file=UploadFile(filename=file_path.name, file=f, size=file_path.stat().st_size),\n                    session=db,\n                    current_user=current_user,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                )\n\n    def _save_dataframe(self, dataframe: DataFrame, path: Path, fmt: str) -> str:\n        \"\"\"Save a DataFrame to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            dataframe.to_csv(path, index=False)\n        elif fmt == \"excel\":\n            dataframe.to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            dataframe.to_json(path, orient=\"records\", indent=2)\n        elif fmt == \"markdown\":\n            path.write_text(dataframe.to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported DataFrame format: {fmt}\"\n            raise ValueError(msg)\n        return f\"DataFrame saved successfully as '{path}'\"\n\n    def _save_data(self, data: Data, path: Path, fmt: str) -> str:\n        \"\"\"Save a Data object to the specified file format.\"\"\"\n        if fmt == \"csv\":\n            pd.DataFrame(data.data).to_csv(path, index=False)\n        elif fmt == \"excel\":\n            pd.DataFrame(data.data).to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            path.write_text(\n                orjson.dumps(jsonable_encoder(data.data), option=orjson.OPT_INDENT_2).decode(\"utf-8\"), encoding=\"utf-8\"\n            )\n        elif fmt == \"markdown\":\n            path.write_text(pd.DataFrame(data.data).to_markdown(index=False), encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Data format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Data saved successfully as '{path}'\"\n\n    async def _save_message(self, message: Message, path: Path, fmt: str) -> str:\n        \"\"\"Save a Message to the specified file format, handling async iterators.\"\"\"\n        content = \"\"\n        if message.text is None:\n            content = \"\"\n        elif isinstance(message.text, AsyncIterator):\n            async for item in message.text:\n                content += str(item) + \" \"\n            content = content.strip()\n        elif isinstance(message.text, Iterator):\n            content = \" \".join(str(item) for item in message.text)\n        else:\n            content = str(message.text)\n\n        if fmt == \"txt\":\n            path.write_text(content, encoding=\"utf-8\")\n        elif fmt == \"json\":\n            path.write_text(json.dumps({\"message\": content}, indent=2), encoding=\"utf-8\")\n        elif fmt == \"markdown\":\n            path.write_text(f\"**Message:**\\n\\n{content}\", encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Message format: {fmt}\"\n            raise ValueError(msg)\n        return f\"Message saved successfully as '{path}'\"\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 \"\"\n\n    def _get_file_format_for_location(self, location: str) -> str:\n        \"\"\"Get the appropriate file format based on storage location.\"\"\"\n        if location == \"Local\":\n            return getattr(self, \"local_format\", None) or self._get_default_format()\n        if location == \"AWS\":\n            return getattr(self, \"aws_format\", \"txt\")\n        if location == \"Google Drive\":\n            return getattr(self, \"gdrive_format\", \"txt\")\n        return self._get_default_format()\n\n    async def _save_to_local(self) -> Message:\n        \"\"\"Save file to local storage (original functionality).\"\"\"\n        file_format = self._get_file_format_for_location(\"Local\")\n\n        # Validate file format based on input type\n        allowed_formats = (\n            self.LOCAL_MESSAGE_FORMAT_CHOICES if self._get_input_type() == \"Message\" else self.LOCAL_DATA_FORMAT_CHOICES\n        )\n        if file_format not in allowed_formats:\n            msg = f\"Invalid file format '{file_format}' for {self._get_input_type()}. Allowed: {allowed_formats}\"\n            raise ValueError(msg)\n\n        # Prepare file path\n        file_path = Path(self.file_name).expanduser()\n        if not file_path.parent.exists():\n            file_path.parent.mkdir(parents=True, exist_ok=True)\n        file_path = self._adjust_file_path_with_format(file_path, file_format)\n\n        # Save the input to file based on type\n        if self._get_input_type() == \"DataFrame\":\n            confirmation = self._save_dataframe(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Data\":\n            confirmation = self._save_data(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Message\":\n            confirmation = await self._save_message(self.input, file_path, file_format)\n        else:\n            msg = f\"Unsupported input type: {self._get_input_type()}\"\n            raise ValueError(msg)\n\n        # Upload the saved file\n        await self._upload_file(file_path)\n\n        # Return the final file path and confirmation message\n        final_path = Path.cwd() / file_path if not file_path.is_absolute() else file_path\n        return Message(text=f\"{confirmation} at {final_path}\")\n\n    async def _save_to_aws(self) -> Message:\n        \"\"\"Save file to AWS S3 using S3 functionality.\"\"\"\n        # Validate AWS credentials\n        if not getattr(self, \"aws_access_key_id\", None):\n            msg = \"AWS Access Key ID is required for S3 storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"aws_secret_access_key\", None):\n            msg = \"AWS Secret Key is required for S3 storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"bucket_name\", None):\n            msg = \"S3 Bucket Name is required for S3 storage\"\n            raise ValueError(msg)\n\n        # Use S3 upload functionality\n        try:\n            import boto3\n        except ImportError as e:\n            msg = \"boto3 is not installed. Please install it using `uv pip install boto3`.\"\n            raise ImportError(msg) from e\n\n        # Create S3 client\n        client_config = {\n            \"aws_access_key_id\": self.aws_access_key_id,\n            \"aws_secret_access_key\": self.aws_secret_access_key,\n        }\n\n        if hasattr(self, \"aws_region\") and self.aws_region:\n            client_config[\"region_name\"] = self.aws_region\n\n        s3_client = boto3.client(\"s3\", **client_config)\n\n        # Extract content\n        content = self._extract_content_for_upload()\n        file_format = self._get_file_format_for_location(\"AWS\")\n\n        # Generate file path\n        file_path = f\"{self.file_name}.{file_format}\"\n        if hasattr(self, \"s3_prefix\") and self.s3_prefix:\n            file_path = f\"{self.s3_prefix.rstrip('/')}/{file_path}\"\n\n        # Create temporary file\n        import tempfile\n\n        with tempfile.NamedTemporaryFile(mode=\"w\", suffix=f\".{file_format}\", delete=False) as temp_file:\n            temp_file.write(content)\n            temp_file_path = temp_file.name\n\n        try:\n            # Upload to S3\n            s3_client.upload_file(temp_file_path, self.bucket_name, file_path)\n            s3_url = f\"s3://{self.bucket_name}/{file_path}\"\n            return Message(text=f\"File successfully uploaded to {s3_url}\")\n        finally:\n            # Clean up temp file\n            if Path(temp_file_path).exists():\n                Path(temp_file_path).unlink()\n\n    async def _save_to_google_drive(self) -> Message:\n        \"\"\"Save file to Google Drive using Google Drive functionality.\"\"\"\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, \"folder_id\", None):\n            msg = \"Google Drive Folder ID is required for Google Drive storage\"\n            raise ValueError(msg)\n\n        # Use Google Drive upload functionality\n        try:\n            import json\n            import tempfile\n\n            from google.oauth2 import service_account\n            from googleapiclient.discovery import build\n            from googleapiclient.http import MediaFileUpload\n        except ImportError as e:\n            msg = \"Google API client libraries are not installed. Please install them.\"\n            raise ImportError(msg) from e\n\n        # Parse credentials\n        try:\n            credentials_dict = json.loads(self.service_account_key)\n        except json.JSONDecodeError as e:\n            msg = f\"Invalid JSON in service account key: {e!s}\"\n            raise ValueError(msg) from e\n\n        # Create Google Drive service\n        credentials = service_account.Credentials.from_service_account_info(\n            credentials_dict, scopes=[\"https://www.googleapis.com/auth/drive.file\"]\n        )\n        drive_service = build(\"drive\", \"v3\", credentials=credentials)\n\n        # Extract content and format\n        content = self._extract_content_for_upload()\n        file_format = self._get_file_format_for_location(\"Google Drive\")\n\n        # Handle special Google Drive formats\n        if file_format in [\"slides\", \"docs\"]:\n            return await self._save_to_google_apps(drive_service, credentials, content, file_format)\n\n        # Create temporary file\n        file_path = f\"{self.file_name}.{file_format}\"\n        with tempfile.NamedTemporaryFile(mode=\"w\", suffix=f\".{file_format}\", delete=False) as temp_file:\n            temp_file.write(content)\n            temp_file_path = temp_file.name\n\n        try:\n            # Upload to Google Drive\n            file_metadata = {\"name\": file_path, \"parents\": [self.folder_id]}\n            media = MediaFileUpload(temp_file_path, resumable=True)\n\n            uploaded_file = drive_service.files().create(body=file_metadata, media_body=media, fields=\"id\").execute()\n\n            file_id = uploaded_file.get(\"id\")\n            file_url = f\"https://drive.google.com/file/d/{file_id}/view\"\n            return Message(text=f\"File successfully uploaded to Google Drive: {file_url}\")\n        finally:\n            # Clean up temp file\n            if Path(temp_file_path).exists():\n                Path(temp_file_path).unlink()\n\n    async def _save_to_google_apps(self, drive_service, credentials, content: str, app_type: str) -> Message:\n        \"\"\"Save content to Google Apps (Slides or Docs).\"\"\"\n        import time\n\n        if app_type == \"slides\":\n            from googleapiclient.discovery import build\n\n            slides_service = build(\"slides\", \"v1\", credentials=credentials)\n\n            file_metadata = {\n                \"name\": self.file_name,\n                \"mimeType\": \"application/vnd.google-apps.presentation\",\n                \"parents\": [self.folder_id],\n            }\n\n            created_file = drive_service.files().create(body=file_metadata, fields=\"id\").execute()\n            presentation_id = created_file[\"id\"]\n\n            time.sleep(2)  # Wait for file to be available  # noqa: ASYNC251\n\n            presentation = slides_service.presentations().get(presentationId=presentation_id).execute()\n            slide_id = presentation[\"slides\"][0][\"objectId\"]\n\n            # Add content to slide\n            requests = [\n                {\n                    \"createShape\": {\n                        \"objectId\": \"TextBox_01\",\n                        \"shapeType\": \"TEXT_BOX\",\n                        \"elementProperties\": {\n                            \"pageObjectId\": slide_id,\n                            \"size\": {\n                                \"height\": {\"magnitude\": 3000000, \"unit\": \"EMU\"},\n                                \"width\": {\"magnitude\": 6000000, \"unit\": \"EMU\"},\n                            },\n                            \"transform\": {\n                                \"scaleX\": 1,\n                                \"scaleY\": 1,\n                                \"translateX\": 1000000,\n                                \"translateY\": 1000000,\n                                \"unit\": \"EMU\",\n                            },\n                        },\n                    }\n                },\n                {\"insertText\": {\"objectId\": \"TextBox_01\", \"insertionIndex\": 0, \"text\": content}},\n            ]\n\n            slides_service.presentations().batchUpdate(\n                presentationId=presentation_id, body={\"requests\": requests}\n            ).execute()\n            file_url = f\"https://docs.google.com/presentation/d/{presentation_id}/edit\"\n\n        elif app_type == \"docs\":\n            from googleapiclient.discovery import build\n\n            docs_service = build(\"docs\", \"v1\", credentials=credentials)\n\n            file_metadata = {\n                \"name\": self.file_name,\n                \"mimeType\": \"application/vnd.google-apps.document\",\n                \"parents\": [self.folder_id],\n            }\n\n            created_file = drive_service.files().create(body=file_metadata, fields=\"id\").execute()\n            document_id = created_file[\"id\"]\n\n            time.sleep(2)  # Wait for file to be available  # noqa: ASYNC251\n\n            # Add content to document\n            requests = [{\"insertText\": {\"location\": {\"index\": 1}, \"text\": content}}]\n            docs_service.documents().batchUpdate(documentId=document_id, body={\"requests\": requests}).execute()\n            file_url = f\"https://docs.google.com/document/d/{document_id}/edit\"\n\n        return Message(text=f\"File successfully created in Google {app_type.title()}: {file_url}\")\n\n    def _extract_content_for_upload(self) -> str:\n        \"\"\"Extract content from input for upload to cloud services.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return self.input.to_csv(index=False)\n        if self._get_input_type() == \"Data\":\n            if hasattr(self.input, \"data\") and self.input.data:\n                if isinstance(self.input.data, dict):\n                    import json\n\n                    return json.dumps(self.input.data, indent=2, ensure_ascii=False)\n                return str(self.input.data)\n            return str(self.input)\n        if self._get_input_type() == \"Message\":\n            return str(self.input.text) if self.input.text else str(self.input)\n        return str(self.input)\n"
+                "value": "import json\nfrom collections.abc import AsyncIterator, Iterator\nfrom pathlib import Path\n\nimport orjson\nimport pandas as pd\nfrom fastapi import UploadFile\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.custom import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DropdownInput, HandleInput, SecretStrInput, StrInput\nfrom lfx.schema import Data, DataFrame, Message\nfrom lfx.services.deps import get_settings_service, get_storage_service, session_scope\nfrom lfx.template.field.base import Output\n\n\nclass SaveToFileComponent(Component):\n    display_name = \"Write File\"\n    description = \"Save data to local file, AWS S3, or Google Drive in the selected format.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#save-file\"\n    icon = \"file-text\"\n    name = \"SaveToFile\"\n\n    # File format options for different storage types\n    LOCAL_DATA_FORMAT_CHOICES = [\"csv\", \"excel\", \"json\", \"markdown\"]\n    LOCAL_MESSAGE_FORMAT_CHOICES = [\"txt\", \"json\", \"markdown\"]\n    AWS_FORMAT_CHOICES = [\n        \"txt\",\n        \"json\",\n        \"csv\",\n        \"xml\",\n        \"html\",\n        \"md\",\n        \"yaml\",\n        \"log\",\n        \"tsv\",\n        \"jsonl\",\n        \"parquet\",\n        \"xlsx\",\n        \"zip\",\n    ]\n    GDRIVE_FORMAT_CHOICES = [\"txt\", \"json\", \"csv\", \"xlsx\", \"slides\", \"docs\", \"jpg\", \"mp3\"]\n\n    inputs = [\n        # Storage location selection\n        SortableListInput(\n            name=\"storage_location\",\n            display_name=\"Storage Location\",\n            placeholder=\"Select Location\",\n            info=\"Choose where to save the file.\",\n            options=[\n                {\"name\": \"Local\", \"icon\": \"hard-drive\"},\n                {\"name\": \"AWS\", \"icon\": \"Amazon\"},\n                {\"name\": \"Google Drive\", \"icon\": \"google\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        # Common inputs\n        HandleInput(\n            name=\"input\",\n            display_name=\"File Content\",\n            info=\"The input to save.\",\n            dynamic=True,\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        StrInput(\n            name=\"file_name\",\n            display_name=\"File Name\",\n            info=\"Name file will be saved as (without extension).\",\n            required=True,\n            show=False,\n            tool_mode=True,\n        ),\n        BoolInput(\n            name=\"append_mode\",\n            display_name=\"Append\",\n            info=\"Append to file if it exists (only for plain text formats). Disabled for binary formats like Excel.\",\n            value=False,\n            show=False,\n        ),\n        # Format inputs (dynamic based on storage location)\n        DropdownInput(\n            name=\"local_format\",\n            display_name=\"File Format\",\n            options=list(dict.fromkeys(LOCAL_DATA_FORMAT_CHOICES + LOCAL_MESSAGE_FORMAT_CHOICES)),\n            info=\"Select the file format for local storage.\",\n            value=\"json\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"aws_format\",\n            display_name=\"File Format\",\n            options=AWS_FORMAT_CHOICES,\n            info=\"Select the file format for AWS S3 storage.\",\n            value=\"txt\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"gdrive_format\",\n            display_name=\"File Format\",\n            options=GDRIVE_FORMAT_CHOICES,\n            info=\"Select the file format for Google Drive storage.\",\n            value=\"txt\",\n            show=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=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=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=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=True,\n        ),\n        StrInput(\n            name=\"s3_prefix\",\n            display_name=\"S3 Prefix\",\n            info=\"Prefix for all files in S3.\",\n            show=False,\n            advanced=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=True,\n        ),\n        StrInput(\n            name=\"folder_id\",\n            display_name=\"Google Drive Folder ID\",\n            info=(\n                \"The Google Drive folder ID where the file will be uploaded. \"\n                \"The folder must be shared with the service account email.\"\n            ),\n            show=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [Output(display_name=\"File Path\", name=\"message\", method=\"save_to_file\")]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        \"\"\"Update build configuration to show/hide fields based on storage location selection.\"\"\"\n        if field_name != \"storage_location\":\n            return build_config\n\n        # Extract selected storage location\n        selected = [location[\"name\"] for location in field_value] if isinstance(field_value, list) else []\n\n        # Hide all dynamic fields first\n        dynamic_fields = [\n            \"file_name\",  # Common fields (input is always visible)\n            \"append_mode\",\n            \"local_format\",\n            \"aws_format\",\n            \"gdrive_format\",\n            \"aws_access_key_id\",\n            \"aws_secret_access_key\",\n            \"bucket_name\",\n            \"aws_region\",\n            \"s3_prefix\",\n            \"service_account_key\",\n            \"folder_id\",\n        ]\n\n        for f_name in dynamic_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            # Show file_name and append_mode when any storage location is selected\n            if \"file_name\" in build_config:\n                build_config[\"file_name\"][\"show\"] = True\n            if \"append_mode\" in build_config:\n                build_config[\"append_mode\"][\"show\"] = True\n\n            if location == \"Local\":\n                if \"local_format\" in build_config:\n                    build_config[\"local_format\"][\"show\"] = True\n\n            elif location == \"AWS\":\n                aws_fields = [\n                    \"aws_format\",\n                    \"aws_access_key_id\",\n                    \"aws_secret_access_key\",\n                    \"bucket_name\",\n                    \"aws_region\",\n                    \"s3_prefix\",\n                ]\n                for f_name in aws_fields:\n                    if f_name in build_config:\n                        build_config[f_name][\"show\"] = True\n\n            elif location == \"Google Drive\":\n                gdrive_fields = [\"gdrive_format\", \"service_account_key\", \"folder_id\"]\n                for f_name in gdrive_fields:\n                    if f_name in build_config:\n                        build_config[f_name][\"show\"] = True\n\n        return build_config\n\n    async def save_to_file(self) -> Message:\n        \"\"\"Save the input to a file and upload it, returning a confirmation message.\"\"\"\n        # Validate inputs\n        if not self.file_name:\n            msg = \"File name must be provided.\"\n            raise ValueError(msg)\n        if not self._get_input_type():\n            msg = \"Input type is not set.\"\n            raise ValueError(msg)\n\n        # Get selected storage location\n        storage_location = self._get_selected_storage_location()\n        if not storage_location:\n            msg = \"Storage location must be selected.\"\n            raise ValueError(msg)\n\n        # Route to appropriate save method based on storage location\n        if storage_location == \"Local\":\n            return await self._save_to_local()\n        if storage_location == \"AWS\":\n            return await self._save_to_aws()\n        if storage_location == \"Google Drive\":\n            return await self._save_to_google_drive()\n        msg = f\"Unsupported storage location: {storage_location}\"\n        raise ValueError(msg)\n\n    def _get_input_type(self) -> str:\n        \"\"\"Determine the input type based on the provided input.\"\"\"\n        # Use exact type checking (type() is) instead of isinstance() to avoid inheritance issues.\n        # Since Message inherits from Data, isinstance(message, Data) would return True for Message objects,\n        # causing Message inputs to be incorrectly identified as Data type.\n        if type(self.input) is DataFrame:\n            return \"DataFrame\"\n        if type(self.input) is Message:\n            return \"Message\"\n        if type(self.input) is Data:\n            return \"Data\"\n        msg = f\"Unsupported input type: {type(self.input)}\"\n        raise ValueError(msg)\n\n    def _get_default_format(self) -> str:\n        \"\"\"Return the default file format based on input type.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return \"csv\"\n        if self._get_input_type() == \"Data\":\n            return \"json\"\n        if self._get_input_type() == \"Message\":\n            return \"json\"\n        return \"json\"  # Fallback\n\n    def _adjust_file_path_with_format(self, path: Path, fmt: str) -> Path:\n        \"\"\"Adjust the file path to include the correct extension.\"\"\"\n        file_extension = path.suffix.lower().lstrip(\".\")\n        if fmt == \"excel\":\n            return Path(f\"{path}.xlsx\").expanduser() if file_extension not in [\"xlsx\", \"xls\"] else path\n        return Path(f\"{path}.{fmt}\").expanduser() if file_extension != fmt else path\n\n    def _is_plain_text_format(self, fmt: str) -> bool:\n        \"\"\"Check if a file format is plain text (supports appending).\"\"\"\n        plain_text_formats = [\"txt\", \"json\", \"markdown\", \"md\", \"csv\", \"xml\", \"html\", \"yaml\", \"log\", \"tsv\", \"jsonl\"]\n        return fmt.lower() in plain_text_formats\n\n    async def _upload_file(self, file_path: Path) -> None:\n        \"\"\"Upload the saved file using the upload_user_file service.\"\"\"\n        from langflow.api.v2.files import upload_user_file\n        from langflow.services.database.models.user.crud import get_user_by_id\n\n        # Ensure the file exists\n        if not file_path.exists():\n            msg = f\"File not found: {file_path}\"\n            raise FileNotFoundError(msg)\n\n        # Upload the file - always use append=False because the local file already contains\n        # the correct content (either new or appended locally)\n        with file_path.open(\"rb\") as f:\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for file saving.\"\n                    raise ValueError(msg)\n                current_user = await get_user_by_id(db, self.user_id)\n\n                await upload_user_file(\n                    file=UploadFile(filename=file_path.name, file=f, size=file_path.stat().st_size),\n                    session=db,\n                    current_user=current_user,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                    append=False,\n                )\n\n    def _save_dataframe(self, dataframe: DataFrame, path: Path, fmt: str) -> str:\n        \"\"\"Save a DataFrame to the specified file format.\"\"\"\n        append_mode = getattr(self, \"append_mode\", False)\n        should_append = append_mode and path.exists() and self._is_plain_text_format(fmt)\n\n        if fmt == \"csv\":\n            dataframe.to_csv(path, index=False, mode=\"a\" if should_append else \"w\", header=not should_append)\n        elif fmt == \"excel\":\n            dataframe.to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            if should_append:\n                # Read and parse existing JSON\n                existing_data = []\n                try:\n                    existing_content = path.read_text(encoding=\"utf-8\").strip()\n                    if existing_content:\n                        parsed = json.loads(existing_content)\n                        # Handle case where existing content is a single object\n                        if isinstance(parsed, dict):\n                            existing_data = [parsed]\n                        elif isinstance(parsed, list):\n                            existing_data = parsed\n                except (json.JSONDecodeError, FileNotFoundError):\n                    # Treat parse errors or missing file as empty array\n                    existing_data = []\n\n                # Append new data\n                new_records = json.loads(dataframe.to_json(orient=\"records\"))\n                existing_data.extend(new_records)\n\n                # Write back as a single JSON array\n                path.write_text(json.dumps(existing_data, indent=2), encoding=\"utf-8\")\n            else:\n                dataframe.to_json(path, orient=\"records\", indent=2)\n        elif fmt == \"markdown\":\n            content = dataframe.to_markdown(index=False)\n            if should_append:\n                path.write_text(path.read_text(encoding=\"utf-8\") + \"\\n\\n\" + content, encoding=\"utf-8\")\n            else:\n                path.write_text(content, encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported DataFrame format: {fmt}\"\n            raise ValueError(msg)\n        action = \"appended to\" if should_append else \"saved successfully as\"\n        return f\"DataFrame {action} '{path}'\"\n\n    def _save_data(self, data: Data, path: Path, fmt: str) -> str:\n        \"\"\"Save a Data object to the specified file format.\"\"\"\n        append_mode = getattr(self, \"append_mode\", False)\n        should_append = append_mode and path.exists() and self._is_plain_text_format(fmt)\n\n        if fmt == \"csv\":\n            pd.DataFrame(data.data).to_csv(\n                path,\n                index=False,\n                mode=\"a\" if should_append else \"w\",\n                header=not should_append,\n            )\n        elif fmt == \"excel\":\n            pd.DataFrame(data.data).to_excel(path, index=False, engine=\"openpyxl\")\n        elif fmt == \"json\":\n            new_data = jsonable_encoder(data.data)\n            if should_append:\n                # Read and parse existing JSON\n                existing_data = []\n                try:\n                    existing_content = path.read_text(encoding=\"utf-8\").strip()\n                    if existing_content:\n                        parsed = json.loads(existing_content)\n                        # Handle case where existing content is a single object\n                        if isinstance(parsed, dict):\n                            existing_data = [parsed]\n                        elif isinstance(parsed, list):\n                            existing_data = parsed\n                except (json.JSONDecodeError, FileNotFoundError):\n                    # Treat parse errors or missing file as empty array\n                    existing_data = []\n\n                # Append new data\n                if isinstance(new_data, list):\n                    existing_data.extend(new_data)\n                else:\n                    existing_data.append(new_data)\n\n                # Write back as a single JSON array\n                path.write_text(json.dumps(existing_data, indent=2), encoding=\"utf-8\")\n            else:\n                content = orjson.dumps(new_data, option=orjson.OPT_INDENT_2).decode(\"utf-8\")\n                path.write_text(content, encoding=\"utf-8\")\n        elif fmt == \"markdown\":\n            content = pd.DataFrame(data.data).to_markdown(index=False)\n            if should_append:\n                path.write_text(path.read_text(encoding=\"utf-8\") + \"\\n\\n\" + content, encoding=\"utf-8\")\n            else:\n                path.write_text(content, encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Data format: {fmt}\"\n            raise ValueError(msg)\n        action = \"appended to\" if should_append else \"saved successfully as\"\n        return f\"Data {action} '{path}'\"\n\n    async def _save_message(self, message: Message, path: Path, fmt: str) -> str:\n        \"\"\"Save a Message to the specified file format, handling async iterators.\"\"\"\n        content = \"\"\n        if message.text is None:\n            content = \"\"\n        elif isinstance(message.text, AsyncIterator):\n            async for item in message.text:\n                content += str(item) + \" \"\n            content = content.strip()\n        elif isinstance(message.text, Iterator):\n            content = \" \".join(str(item) for item in message.text)\n        else:\n            content = str(message.text)\n\n        append_mode = getattr(self, \"append_mode\", False)\n        should_append = append_mode and path.exists() and self._is_plain_text_format(fmt)\n\n        if fmt == \"txt\":\n            if should_append:\n                path.write_text(path.read_text(encoding=\"utf-8\") + \"\\n\" + content, encoding=\"utf-8\")\n            else:\n                path.write_text(content, encoding=\"utf-8\")\n        elif fmt == \"json\":\n            new_message = {\"message\": content}\n            if should_append:\n                # Read and parse existing JSON\n                existing_data = []\n                try:\n                    existing_content = path.read_text(encoding=\"utf-8\").strip()\n                    if existing_content:\n                        parsed = json.loads(existing_content)\n                        # Handle case where existing content is a single object\n                        if isinstance(parsed, dict):\n                            existing_data = [parsed]\n                        elif isinstance(parsed, list):\n                            existing_data = parsed\n                except (json.JSONDecodeError, FileNotFoundError):\n                    # Treat parse errors or missing file as empty array\n                    existing_data = []\n\n                # Append new message\n                existing_data.append(new_message)\n\n                # Write back as a single JSON array\n                path.write_text(json.dumps(existing_data, indent=2), encoding=\"utf-8\")\n            else:\n                path.write_text(json.dumps(new_message, indent=2), encoding=\"utf-8\")\n        elif fmt == \"markdown\":\n            md_content = f\"**Message:**\\n\\n{content}\"\n            if should_append:\n                path.write_text(path.read_text(encoding=\"utf-8\") + \"\\n\\n\" + md_content, encoding=\"utf-8\")\n            else:\n                path.write_text(md_content, encoding=\"utf-8\")\n        else:\n            msg = f\"Unsupported Message format: {fmt}\"\n            raise ValueError(msg)\n        action = \"appended to\" if should_append else \"saved successfully as\"\n        return f\"Message {action} '{path}'\"\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 \"\"\n\n    def _get_file_format_for_location(self, location: str) -> str:\n        \"\"\"Get the appropriate file format based on storage location.\"\"\"\n        if location == \"Local\":\n            return getattr(self, \"local_format\", None) or self._get_default_format()\n        if location == \"AWS\":\n            return getattr(self, \"aws_format\", \"txt\")\n        if location == \"Google Drive\":\n            return getattr(self, \"gdrive_format\", \"txt\")\n        return self._get_default_format()\n\n    async def _save_to_local(self) -> Message:\n        \"\"\"Save file to local storage (original functionality).\"\"\"\n        file_format = self._get_file_format_for_location(\"Local\")\n\n        # Validate file format based on input type\n        allowed_formats = (\n            self.LOCAL_MESSAGE_FORMAT_CHOICES if self._get_input_type() == \"Message\" else self.LOCAL_DATA_FORMAT_CHOICES\n        )\n        if file_format not in allowed_formats:\n            msg = f\"Invalid file format '{file_format}' for {self._get_input_type()}. Allowed: {allowed_formats}\"\n            raise ValueError(msg)\n\n        # Prepare file path\n        file_path = Path(self.file_name).expanduser()\n        if not file_path.parent.exists():\n            file_path.parent.mkdir(parents=True, exist_ok=True)\n        file_path = self._adjust_file_path_with_format(file_path, file_format)\n\n        # Save the input to file based on type\n        if self._get_input_type() == \"DataFrame\":\n            confirmation = self._save_dataframe(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Data\":\n            confirmation = self._save_data(self.input, file_path, file_format)\n        elif self._get_input_type() == \"Message\":\n            confirmation = await self._save_message(self.input, file_path, file_format)\n        else:\n            msg = f\"Unsupported input type: {self._get_input_type()}\"\n            raise ValueError(msg)\n\n        # Upload the saved file\n        await self._upload_file(file_path)\n\n        # Return the final file path and confirmation message\n        final_path = Path.cwd() / file_path if not file_path.is_absolute() else file_path\n        return Message(text=f\"{confirmation} at {final_path}\")\n\n    async def _save_to_aws(self) -> Message:\n        \"\"\"Save file to AWS S3 using S3 functionality.\"\"\"\n        # Validate AWS credentials\n        if not getattr(self, \"aws_access_key_id\", None):\n            msg = \"AWS Access Key ID is required for S3 storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"aws_secret_access_key\", None):\n            msg = \"AWS Secret Key is required for S3 storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"bucket_name\", None):\n            msg = \"S3 Bucket Name is required for S3 storage\"\n            raise ValueError(msg)\n\n        # Use S3 upload functionality\n        try:\n            import boto3\n        except ImportError as e:\n            msg = \"boto3 is not installed. Please install it using `uv pip install boto3`.\"\n            raise ImportError(msg) from e\n\n        # Create S3 client\n        client_config = {\n            \"aws_access_key_id\": self.aws_access_key_id,\n            \"aws_secret_access_key\": self.aws_secret_access_key,\n        }\n\n        if hasattr(self, \"aws_region\") and self.aws_region:\n            client_config[\"region_name\"] = self.aws_region\n\n        s3_client = boto3.client(\"s3\", **client_config)\n\n        # Extract content\n        content = self._extract_content_for_upload()\n        file_format = self._get_file_format_for_location(\"AWS\")\n\n        # Generate file path\n        file_path = f\"{self.file_name}.{file_format}\"\n        if hasattr(self, \"s3_prefix\") and self.s3_prefix:\n            file_path = f\"{self.s3_prefix.rstrip('/')}/{file_path}\"\n\n        # Create temporary file\n        import tempfile\n\n        with tempfile.NamedTemporaryFile(mode=\"w\", suffix=f\".{file_format}\", delete=False) as temp_file:\n            temp_file.write(content)\n            temp_file_path = temp_file.name\n\n        try:\n            # Upload to S3\n            s3_client.upload_file(temp_file_path, self.bucket_name, file_path)\n            s3_url = f\"s3://{self.bucket_name}/{file_path}\"\n            return Message(text=f\"File successfully uploaded to {s3_url}\")\n        finally:\n            # Clean up temp file\n            if Path(temp_file_path).exists():\n                Path(temp_file_path).unlink()\n\n    async def _save_to_google_drive(self) -> Message:\n        \"\"\"Save file to Google Drive using Google Drive functionality.\"\"\"\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, \"folder_id\", None):\n            msg = \"Google Drive Folder ID is required for Google Drive storage\"\n            raise ValueError(msg)\n\n        # Use Google Drive upload functionality\n        try:\n            import json\n            import tempfile\n\n            from google.oauth2 import service_account\n            from googleapiclient.discovery import build\n            from googleapiclient.http import MediaFileUpload\n        except ImportError as e:\n            msg = \"Google API client libraries are not installed. Please install them.\"\n            raise ImportError(msg) from e\n\n        # Parse credentials\n        try:\n            credentials_dict = json.loads(self.service_account_key)\n        except json.JSONDecodeError as e:\n            msg = f\"Invalid JSON in service account key: {e!s}\"\n            raise ValueError(msg) from e\n\n        # Create Google Drive service\n        credentials = service_account.Credentials.from_service_account_info(\n            credentials_dict, scopes=[\"https://www.googleapis.com/auth/drive.file\"]\n        )\n        drive_service = build(\"drive\", \"v3\", credentials=credentials)\n\n        # Extract content and format\n        content = self._extract_content_for_upload()\n        file_format = self._get_file_format_for_location(\"Google Drive\")\n\n        # Handle special Google Drive formats\n        if file_format in [\"slides\", \"docs\"]:\n            return await self._save_to_google_apps(drive_service, credentials, content, file_format)\n\n        # Create temporary file\n        file_path = f\"{self.file_name}.{file_format}\"\n        with tempfile.NamedTemporaryFile(mode=\"w\", suffix=f\".{file_format}\", delete=False) as temp_file:\n            temp_file.write(content)\n            temp_file_path = temp_file.name\n\n        try:\n            # Upload to Google Drive\n            file_metadata = {\"name\": file_path, \"parents\": [self.folder_id]}\n            media = MediaFileUpload(temp_file_path, resumable=True)\n\n            uploaded_file = drive_service.files().create(body=file_metadata, media_body=media, fields=\"id\").execute()\n\n            file_id = uploaded_file.get(\"id\")\n            file_url = f\"https://drive.google.com/file/d/{file_id}/view\"\n            return Message(text=f\"File successfully uploaded to Google Drive: {file_url}\")\n        finally:\n            # Clean up temp file\n            if Path(temp_file_path).exists():\n                Path(temp_file_path).unlink()\n\n    async def _save_to_google_apps(self, drive_service, credentials, content: str, app_type: str) -> Message:\n        \"\"\"Save content to Google Apps (Slides or Docs).\"\"\"\n        import time\n\n        if app_type == \"slides\":\n            from googleapiclient.discovery import build\n\n            slides_service = build(\"slides\", \"v1\", credentials=credentials)\n\n            file_metadata = {\n                \"name\": self.file_name,\n                \"mimeType\": \"application/vnd.google-apps.presentation\",\n                \"parents\": [self.folder_id],\n            }\n\n            created_file = drive_service.files().create(body=file_metadata, fields=\"id\").execute()\n            presentation_id = created_file[\"id\"]\n\n            time.sleep(2)  # Wait for file to be available  # noqa: ASYNC251\n\n            presentation = slides_service.presentations().get(presentationId=presentation_id).execute()\n            slide_id = presentation[\"slides\"][0][\"objectId\"]\n\n            # Add content to slide\n            requests = [\n                {\n                    \"createShape\": {\n                        \"objectId\": \"TextBox_01\",\n                        \"shapeType\": \"TEXT_BOX\",\n                        \"elementProperties\": {\n                            \"pageObjectId\": slide_id,\n                            \"size\": {\n                                \"height\": {\"magnitude\": 3000000, \"unit\": \"EMU\"},\n                                \"width\": {\"magnitude\": 6000000, \"unit\": \"EMU\"},\n                            },\n                            \"transform\": {\n                                \"scaleX\": 1,\n                                \"scaleY\": 1,\n                                \"translateX\": 1000000,\n                                \"translateY\": 1000000,\n                                \"unit\": \"EMU\",\n                            },\n                        },\n                    }\n                },\n                {\"insertText\": {\"objectId\": \"TextBox_01\", \"insertionIndex\": 0, \"text\": content}},\n            ]\n\n            slides_service.presentations().batchUpdate(\n                presentationId=presentation_id, body={\"requests\": requests}\n            ).execute()\n            file_url = f\"https://docs.google.com/presentation/d/{presentation_id}/edit\"\n\n        elif app_type == \"docs\":\n            from googleapiclient.discovery import build\n\n            docs_service = build(\"docs\", \"v1\", credentials=credentials)\n\n            file_metadata = {\n                \"name\": self.file_name,\n                \"mimeType\": \"application/vnd.google-apps.document\",\n                \"parents\": [self.folder_id],\n            }\n\n            created_file = drive_service.files().create(body=file_metadata, fields=\"id\").execute()\n            document_id = created_file[\"id\"]\n\n            time.sleep(2)  # Wait for file to be available  # noqa: ASYNC251\n\n            # Add content to document\n            requests = [{\"insertText\": {\"location\": {\"index\": 1}, \"text\": content}}]\n            docs_service.documents().batchUpdate(documentId=document_id, body={\"requests\": requests}).execute()\n            file_url = f\"https://docs.google.com/document/d/{document_id}/edit\"\n\n        return Message(text=f\"File successfully created in Google {app_type.title()}: {file_url}\")\n\n    def _extract_content_for_upload(self) -> str:\n        \"\"\"Extract content from input for upload to cloud services.\"\"\"\n        if self._get_input_type() == \"DataFrame\":\n            return self.input.to_csv(index=False)\n        if self._get_input_type() == \"Data\":\n            if hasattr(self.input, \"data\") and self.input.data:\n                if isinstance(self.input.data, dict):\n                    import json\n\n                    return json.dumps(self.input.data, indent=2, ensure_ascii=False)\n                return str(self.input.data)\n            return str(self.input)\n        if self._get_input_type() == \"Message\":\n            return str(self.input.text) if self.input.text else str(self.input)\n        return str(self.input)\n"
               },
               "file_name": {
                 "_input_type": "StrInput",

langflow/initial_setup/starter_projects/Nvidia Remix.json

@@ -819,7 +819,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -2645,7 +2645,7 @@
             "legacy": false,
             "lf_version": "1.4.2",
             "metadata": {
-              "code_hash": "24a7838f06c9",
+              "code_hash": "7ed97e9f206c",
               "dependencies": {
                 "dependencies": [
                   {
@@ -2705,7 +2705,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from __future__ import annotations\n\nimport asyncio\nimport json\nimport uuid\n\nfrom langchain_core.tools import StructuredTool  # noqa: TC002\n\nfrom lfx.base.agents.utils import maybe_unflatten_dict, safe_cache_get, safe_cache_set\nfrom lfx.base.mcp.util import (\n    MCPStdioClient,\n    MCPStreamableHttpClient,\n    create_input_schema_from_json_schema,\n    update_tools,\n)\nfrom lfx.custom.custom_component.component_with_cache import ComponentWithCache\nfrom lfx.inputs.inputs import InputTypes  # noqa: TC001\nfrom lfx.io import BoolInput, DropdownInput, McpInput, MessageTextInput, Output\nfrom lfx.io.schema import flatten_schema, schema_to_langflow_inputs\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_settings_service, get_storage_service, session_scope\n\n\nclass MCPToolsComponent(ComponentWithCache):\n    schema_inputs: list = []\n    tools: list[StructuredTool] = []\n    _not_load_actions: bool = False\n    _tool_cache: dict = {}\n    _last_selected_server: str | None = None  # Cache for the last selected server\n\n    def __init__(self, **data) -> None:\n        super().__init__(**data)\n        # Initialize cache keys to avoid CacheMiss when accessing them\n        self._ensure_cache_structure()\n\n        # Initialize clients with access to the component cache\n        self.stdio_client: MCPStdioClient = MCPStdioClient(component_cache=self._shared_component_cache)\n        self.streamable_http_client: MCPStreamableHttpClient = MCPStreamableHttpClient(\n            component_cache=self._shared_component_cache\n        )\n\n    def _ensure_cache_structure(self):\n        \"\"\"Ensure the cache has the required structure.\"\"\"\n        # Check if servers key exists and is not CacheMiss\n        servers_value = safe_cache_get(self._shared_component_cache, \"servers\")\n        if servers_value is None:\n            safe_cache_set(self._shared_component_cache, \"servers\", {})\n\n        # Check if last_selected_server key exists and is not CacheMiss\n        last_server_value = safe_cache_get(self._shared_component_cache, \"last_selected_server\")\n        if last_server_value is None:\n            safe_cache_set(self._shared_component_cache, \"last_selected_server\", \"\")\n\n    default_keys: list[str] = [\n        \"code\",\n        \"_type\",\n        \"tool_mode\",\n        \"tool_placeholder\",\n        \"mcp_server\",\n        \"tool\",\n        \"use_cache\",\n        \"verify_ssl\",\n    ]\n\n    display_name = \"MCP Tools\"\n    description = \"Connect to an MCP server to use its tools.\"\n    documentation: str = \"https://docs.langflow.org/mcp-client\"\n    icon = \"Mcp\"\n    name = \"MCPTools\"\n\n    inputs = [\n        McpInput(\n            name=\"mcp_server\",\n            display_name=\"MCP Server\",\n            info=\"Select the MCP Server that will be used by this component\",\n            real_time_refresh=True,\n        ),\n        BoolInput(\n            name=\"use_cache\",\n            display_name=\"Use Cached Server\",\n            info=(\n                \"Enable caching of MCP Server and tools to improve performance. \"\n                \"Disable to always fetch fresh tools and server updates.\"\n            ),\n            value=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"verify_ssl\",\n            display_name=\"Verify SSL Certificate\",\n            info=(\n                \"Enable SSL certificate verification for HTTPS connections. \"\n                \"Disable only for development/testing with self-signed certificates.\"\n            ),\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"tool\",\n            display_name=\"Tool\",\n            options=[],\n            value=\"\",\n            info=\"Select the tool to execute\",\n            show=False,\n            required=True,\n            real_time_refresh=True,\n        ),\n        MessageTextInput(\n            name=\"tool_placeholder\",\n            display_name=\"Tool Placeholder\",\n            info=\"Placeholder for the tool\",\n            value=\"\",\n            show=False,\n            tool_mode=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Response\", name=\"response\", method=\"build_output\"),\n    ]\n\n    async def _validate_schema_inputs(self, tool_obj) -> list[InputTypes]:\n        \"\"\"Validate and process schema inputs for a tool.\"\"\"\n        try:\n            if not tool_obj or not hasattr(tool_obj, \"args_schema\"):\n                msg = \"Invalid tool object or missing input schema\"\n                raise ValueError(msg)\n\n            flat_schema = flatten_schema(tool_obj.args_schema.schema())\n            input_schema = create_input_schema_from_json_schema(flat_schema)\n            if not input_schema:\n                msg = f\"Empty input schema for tool '{tool_obj.name}'\"\n                raise ValueError(msg)\n\n            schema_inputs = schema_to_langflow_inputs(input_schema)\n            if not schema_inputs:\n                msg = f\"No input parameters defined for tool '{tool_obj.name}'\"\n                await logger.awarning(msg)\n                return []\n\n        except Exception as e:\n            msg = f\"Error validating schema inputs: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return schema_inputs\n\n    async def update_tool_list(self, mcp_server_value=None):\n        # Accepts mcp_server_value as dict {name, config} or uses self.mcp_server\n        mcp_server = mcp_server_value if mcp_server_value is not None else getattr(self, \"mcp_server\", None)\n        server_name = None\n        server_config_from_value = None\n        if isinstance(mcp_server, dict):\n            server_name = mcp_server.get(\"name\")\n            server_config_from_value = mcp_server.get(\"config\")\n        else:\n            server_name = mcp_server\n        if not server_name:\n            self.tools = []\n            return [], {\"name\": server_name, \"config\": server_config_from_value}\n\n        # Check if caching is enabled, default to False\n        use_cache = getattr(self, \"use_cache\", False)\n\n        # Use shared cache if available and caching is enabled\n        cached = None\n        if use_cache:\n            servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n            cached = servers_cache.get(server_name) if isinstance(servers_cache, dict) else None\n\n        if cached is not None:\n            try:\n                self.tools = cached[\"tools\"]\n                self.tool_names = cached[\"tool_names\"]\n                self._tool_cache = cached[\"tool_cache\"]\n                server_config_from_value = cached[\"config\"]\n            except (TypeError, KeyError, AttributeError) as e:\n                # Handle corrupted cache data by clearing it and continuing to fetch fresh tools\n                msg = f\"Unable to use cached data for MCP Server{server_name}: {e}\"\n                await logger.awarning(msg)\n                # Clear the corrupted cache entry\n                current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                if isinstance(current_servers_cache, dict) and server_name in current_servers_cache:\n                    current_servers_cache.pop(server_name)\n                    safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n            else:\n                return self.tools, {\"name\": server_name, \"config\": server_config_from_value}\n\n        try:\n            try:\n                from langflow.api.v2.mcp import get_server\n                from langflow.services.database.models.user.crud import get_user_by_id\n            except ImportError as e:\n                msg = (\n                    \"Langflow MCP server functionality is not available. \"\n                    \"This feature requires the full Langflow installation.\"\n                )\n                raise ImportError(msg) from e\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for fetching MCP tools.\"\n                    raise ValueError(msg)\n                current_user = await get_user_by_id(db, self.user_id)\n\n                # Try to get server config from DB/API\n                server_config = await get_server(\n                    server_name,\n                    current_user,\n                    db,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                )\n\n            # If get_server returns empty but we have a config, use it\n            if not server_config and server_config_from_value:\n                server_config = server_config_from_value\n\n            if not server_config:\n                self.tools = []\n                return [], {\"name\": server_name, \"config\": server_config}\n\n            # Add verify_ssl option to server config if not present\n            if \"verify_ssl\" not in server_config:\n                verify_ssl = getattr(self, \"verify_ssl\", True)\n                server_config[\"verify_ssl\"] = verify_ssl\n\n            _, tool_list, tool_cache = await update_tools(\n                server_name=server_name,\n                server_config=server_config,\n                mcp_stdio_client=self.stdio_client,\n                mcp_streamable_http_client=self.streamable_http_client,\n            )\n\n            self.tool_names = [tool.name for tool in tool_list if hasattr(tool, \"name\")]\n            self._tool_cache = tool_cache\n            self.tools = tool_list\n\n            # Cache the result only if caching is enabled\n            if use_cache:\n                cache_data = {\n                    \"tools\": tool_list,\n                    \"tool_names\": self.tool_names,\n                    \"tool_cache\": tool_cache,\n                    \"config\": server_config,\n                }\n\n                # Safely update the servers cache\n                current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                if isinstance(current_servers_cache, dict):\n                    current_servers_cache[server_name] = cache_data\n                    safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n\n        except (TimeoutError, asyncio.TimeoutError) as e:\n            msg = f\"Timeout updating tool list: {e!s}\"\n            await logger.aexception(msg)\n            raise TimeoutError(msg) from e\n        except Exception as e:\n            msg = f\"Error updating tool list: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return tool_list, {\"name\": server_name, \"config\": server_config}\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Toggle the visibility of connection-specific fields based on the selected mode.\"\"\"\n        try:\n            if field_name == \"tool\":\n                try:\n                    if len(self.tools) == 0:\n                        try:\n                            self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n                            build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n                            build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n                        except (TimeoutError, asyncio.TimeoutError) as e:\n                            msg = f\"Timeout updating tool list: {e!s}\"\n                            await logger.aexception(msg)\n                            if not build_config[\"tools_metadata\"][\"show\"]:\n                                build_config[\"tool\"][\"show\"] = True\n                                build_config[\"tool\"][\"options\"] = []\n                                build_config[\"tool\"][\"value\"] = \"\"\n                                build_config[\"tool\"][\"placeholder\"] = \"Timeout on MCP server\"\n                            else:\n                                build_config[\"tool\"][\"show\"] = False\n                        except ValueError:\n                            if not build_config[\"tools_metadata\"][\"show\"]:\n                                build_config[\"tool\"][\"show\"] = True\n                                build_config[\"tool\"][\"options\"] = []\n                                build_config[\"tool\"][\"value\"] = \"\"\n                                build_config[\"tool\"][\"placeholder\"] = \"Error on MCP Server\"\n                            else:\n                                build_config[\"tool\"][\"show\"] = False\n\n                    if field_value == \"\":\n                        return build_config\n                    tool_obj = None\n                    for tool in self.tools:\n                        if tool.name == field_value:\n                            tool_obj = tool\n                            break\n                    if tool_obj is None:\n                        msg = f\"Tool {field_value} not found in available tools: {self.tools}\"\n                        await logger.awarning(msg)\n                        return build_config\n                    await self._update_tool_config(build_config, field_value)\n                except Exception as e:\n                    build_config[\"tool\"][\"options\"] = []\n                    msg = f\"Failed to update tools: {e!s}\"\n                    raise ValueError(msg) from e\n                else:\n                    return build_config\n            elif field_name == \"mcp_server\":\n                if not field_value:\n                    build_config[\"tool\"][\"show\"] = False\n                    build_config[\"tool\"][\"options\"] = []\n                    build_config[\"tool\"][\"value\"] = \"\"\n                    build_config[\"tool\"][\"placeholder\"] = \"\"\n                    build_config[\"tool_placeholder\"][\"tool_mode\"] = False\n                    self.remove_non_default_keys(build_config)\n                    return build_config\n\n                build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n\n                current_server_name = field_value.get(\"name\") if isinstance(field_value, dict) else field_value\n                _last_selected_server = safe_cache_get(self._shared_component_cache, \"last_selected_server\", \"\")\n                server_changed = current_server_name != _last_selected_server\n\n                # Determine if \"Tool Mode\" is active by checking if the tool dropdown is hidden.\n                is_in_tool_mode = build_config[\"tools_metadata\"][\"show\"]\n\n                # Get use_cache setting to determine if we should use cached data\n                use_cache = getattr(self, \"use_cache\", False)\n\n                # Fast path: if server didn't change and we already have options, keep them as-is\n                # BUT only if caching is enabled or we're in tool mode\n                existing_options = build_config.get(\"tool\", {}).get(\"options\") or []\n                if not server_changed and existing_options:\n                    # In non-tool mode with cache disabled, skip the fast path to force refresh\n                    if not is_in_tool_mode and not use_cache:\n                        pass  # Continue to refresh logic below\n                    else:\n                        if not is_in_tool_mode:\n                            build_config[\"tool\"][\"show\"] = True\n                        return build_config\n\n                # To avoid unnecessary updates, only proceed if the server has actually changed\n                # OR if caching is disabled (to force refresh in non-tool mode)\n                if (_last_selected_server in (current_server_name, \"\")) and build_config[\"tool\"][\"show\"] and use_cache:\n                    if current_server_name:\n                        servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                        if isinstance(servers_cache, dict):\n                            cached = servers_cache.get(current_server_name)\n                            if cached is not None and cached.get(\"tool_names\"):\n                                cached_tools = cached[\"tool_names\"]\n                                current_tools = build_config[\"tool\"][\"options\"]\n                                if current_tools == cached_tools:\n                                    return build_config\n                    else:\n                        return build_config\n                safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n\n                # Check if tools are already cached for this server before clearing\n                cached_tools = None\n                if current_server_name and use_cache:\n                    servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                    if isinstance(servers_cache, dict):\n                        cached = servers_cache.get(current_server_name)\n                        if cached is not None:\n                            try:\n                                cached_tools = cached[\"tools\"]\n                                self.tools = cached_tools\n                                self.tool_names = cached[\"tool_names\"]\n                                self._tool_cache = cached[\"tool_cache\"]\n                            except (TypeError, KeyError, AttributeError) as e:\n                                # Handle corrupted cache data by ignoring it\n                                msg = f\"Unable to use cached data for MCP Server,{current_server_name}: {e}\"\n                                await logger.awarning(msg)\n                                cached_tools = None\n\n                # Only clear tools if we don't have cached tools for the current server\n                if not cached_tools:\n                    self.tools = []  # Clear previous tools only if no cache\n\n                # Clear previous tool inputs if:\n                # 1. Server actually changed\n                # 2. Cache is disabled (meaning tool list will be refreshed)\n                if server_changed or not use_cache:\n                    self.remove_non_default_keys(build_config)\n\n                # Only show the tool dropdown if not in tool_mode\n                if not is_in_tool_mode:\n                    build_config[\"tool\"][\"show\"] = True\n                    if cached_tools:\n                        # Use cached tools to populate options immediately\n                        build_config[\"tool\"][\"options\"] = [tool.name for tool in cached_tools]\n                        build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n                    else:\n                        # Show loading state only when we need to fetch tools\n                        build_config[\"tool\"][\"placeholder\"] = \"Loading tools...\"\n                        build_config[\"tool\"][\"options\"] = []\n                    # Force a value refresh when:\n                    # 1. Server changed\n                    # 2. We don't have cached tools\n                    # 3. Cache is disabled (to force refresh on config changes)\n                    if server_changed or not cached_tools or not use_cache:\n                        build_config[\"tool\"][\"value\"] = uuid.uuid4()\n                else:\n                    # Keep the tool dropdown hidden if in tool_mode\n                    self._not_load_actions = True\n                    build_config[\"tool\"][\"show\"] = False\n\n            elif field_name == \"tool_mode\":\n                build_config[\"tool\"][\"placeholder\"] = \"\"\n                build_config[\"tool\"][\"show\"] = not bool(field_value) and bool(build_config[\"mcp_server\"])\n                self.remove_non_default_keys(build_config)\n                self.tool = build_config[\"tool\"][\"value\"]\n                if field_value:\n                    self._not_load_actions = True\n                else:\n                    build_config[\"tool\"][\"value\"] = uuid.uuid4()\n                    build_config[\"tool\"][\"options\"] = []\n                    build_config[\"tool\"][\"show\"] = True\n                    build_config[\"tool\"][\"placeholder\"] = \"Loading tools...\"\n            elif field_name == \"tools_metadata\":\n                self._not_load_actions = False\n\n        except Exception as e:\n            msg = f\"Error in update_build_config: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return build_config\n\n    def get_inputs_for_all_tools(self, tools: list) -> dict:\n        \"\"\"Get input schemas for all tools.\"\"\"\n        inputs = {}\n        for tool in tools:\n            if not tool or not hasattr(tool, \"name\"):\n                continue\n            try:\n                flat_schema = flatten_schema(tool.args_schema.schema())\n                input_schema = create_input_schema_from_json_schema(flat_schema)\n                langflow_inputs = schema_to_langflow_inputs(input_schema)\n                inputs[tool.name] = langflow_inputs\n            except (AttributeError, ValueError, TypeError, KeyError) as e:\n                msg = f\"Error getting inputs for tool {getattr(tool, 'name', 'unknown')}: {e!s}\"\n                logger.exception(msg)\n                continue\n        return inputs\n\n    def remove_non_default_keys(self, build_config: dict) -> None:\n        \"\"\"Remove non-default keys from the build config.\"\"\"\n        for key in list(build_config.keys()):\n            if key not in self.default_keys:\n                build_config.pop(key)\n\n    async def _update_tool_config(self, build_config: dict, tool_name: str) -> None:\n        \"\"\"Update tool configuration with proper error handling.\"\"\"\n        if not self.tools:\n            self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n\n        if not tool_name:\n            return\n\n        tool_obj = next((tool for tool in self.tools if tool.name == tool_name), None)\n        if not tool_obj:\n            msg = f\"Tool {tool_name} not found in available tools: {self.tools}\"\n            self.remove_non_default_keys(build_config)\n            build_config[\"tool\"][\"value\"] = \"\"\n            await logger.awarning(msg)\n            return\n\n        try:\n            # Store current values before removing inputs (only for the current tool)\n            current_values = {}\n            for key, value in build_config.items():\n                if key not in self.default_keys and isinstance(value, dict) and \"value\" in value:\n                    current_values[key] = value[\"value\"]\n\n            # Remove ALL non-default keys (all previous tool inputs)\n            self.remove_non_default_keys(build_config)\n\n            # Get and validate new inputs for the selected tool\n            self.schema_inputs = await self._validate_schema_inputs(tool_obj)\n            if not self.schema_inputs:\n                msg = f\"No input parameters to configure for tool '{tool_name}'\"\n                await logger.ainfo(msg)\n                return\n\n            # Add new inputs to build config for the selected tool only\n            for schema_input in self.schema_inputs:\n                if not schema_input or not hasattr(schema_input, \"name\"):\n                    msg = \"Invalid schema input detected, skipping\"\n                    await logger.awarning(msg)\n                    continue\n\n                try:\n                    name = schema_input.name\n                    input_dict = schema_input.to_dict()\n                    input_dict.setdefault(\"value\", None)\n                    input_dict.setdefault(\"required\", True)\n\n                    build_config[name] = input_dict\n\n                    # Preserve existing value if the parameter name exists in current_values\n                    if name in current_values:\n                        build_config[name][\"value\"] = current_values[name]\n\n                except (AttributeError, KeyError, TypeError) as e:\n                    msg = f\"Error processing schema input {schema_input}: {e!s}\"\n                    await logger.aexception(msg)\n                    continue\n        except ValueError as e:\n            msg = f\"Schema validation error for tool {tool_name}: {e!s}\"\n            await logger.aexception(msg)\n            self.schema_inputs = []\n            return\n        except (AttributeError, KeyError, TypeError) as e:\n            msg = f\"Error updating tool config: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n\n    async def build_output(self) -> DataFrame:\n        \"\"\"Build output with improved error handling and validation.\"\"\"\n        try:\n            self.tools, _ = await self.update_tool_list()\n            if self.tool != \"\":\n                # Set session context for persistent MCP sessions using Langflow session ID\n                session_context = self._get_session_context()\n                if session_context:\n                    self.stdio_client.set_session_context(session_context)\n                    self.streamable_http_client.set_session_context(session_context)\n                exec_tool = self._tool_cache[self.tool]\n                tool_args = self.get_inputs_for_all_tools(self.tools)[self.tool]\n                kwargs = {}\n                for arg in tool_args:\n                    value = getattr(self, arg.name, None)\n                    if value is not None:\n                        if isinstance(value, Message):\n                            kwargs[arg.name] = value.text\n                        else:\n                            kwargs[arg.name] = value\n\n                unflattened_kwargs = maybe_unflatten_dict(kwargs)\n\n                output = await exec_tool.coroutine(**unflattened_kwargs)\n                tool_content = []\n                for item in output.content:\n                    item_dict = item.model_dump()\n                    item_dict = self.process_output_item(item_dict)\n                    tool_content.append(item_dict)\n\n                if isinstance(tool_content, list) and all(isinstance(x, dict) for x in tool_content):\n                    return DataFrame(tool_content)\n                return DataFrame(data=tool_content)\n            return DataFrame(data=[{\"error\": \"You must select a tool\"}])\n        except Exception as e:\n            msg = f\"Error in build_output: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n\n    def process_output_item(self, item_dict):\n        \"\"\"Process the output of a tool.\"\"\"\n        if item_dict.get(\"type\") == \"text\":\n            text = item_dict.get(\"text\")\n            try:\n                return json.loads(text)\n                # convert it to dict\n            except json.JSONDecodeError:\n                return item_dict\n        return item_dict\n\n    def _get_session_context(self) -> str | None:\n        \"\"\"Get the Langflow session ID for MCP session caching.\"\"\"\n        # Try to get session ID from the component's execution context\n        if hasattr(self, \"graph\") and hasattr(self.graph, \"session_id\"):\n            session_id = self.graph.session_id\n            # Include server name to ensure different servers get different sessions\n            server_name = \"\"\n            mcp_server = getattr(self, \"mcp_server\", None)\n            if isinstance(mcp_server, dict):\n                server_name = mcp_server.get(\"name\", \"\")\n            elif mcp_server:\n                server_name = str(mcp_server)\n            return f\"{session_id}_{server_name}\" if session_id else None\n        return None\n\n    async def _get_tools(self):\n        \"\"\"Get cached tools or update if necessary.\"\"\"\n        mcp_server = getattr(self, \"mcp_server\", None)\n        if not self._not_load_actions:\n            tools, _ = await self.update_tool_list(mcp_server)\n            return tools\n        return []\n"
+                "value": "from __future__ import annotations\n\nimport asyncio\nimport json\nimport uuid\n\nfrom langchain_core.tools import StructuredTool  # noqa: TC002\n\nfrom lfx.base.agents.utils import maybe_unflatten_dict, safe_cache_get, safe_cache_set\nfrom lfx.base.mcp.util import (\n    MCPStdioClient,\n    MCPStreamableHttpClient,\n    create_input_schema_from_json_schema,\n    update_tools,\n)\nfrom lfx.custom.custom_component.component_with_cache import ComponentWithCache\nfrom lfx.inputs.inputs import InputTypes  # noqa: TC001\nfrom lfx.io import BoolInput, DropdownInput, McpInput, MessageTextInput, Output\nfrom lfx.io.schema import flatten_schema, schema_to_langflow_inputs\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_settings_service, get_storage_service, session_scope\n\n\nclass MCPToolsComponent(ComponentWithCache):\n    schema_inputs: list = []\n    tools: list[StructuredTool] = []\n    _not_load_actions: bool = False\n    _tool_cache: dict = {}\n    _last_selected_server: str | None = None  # Cache for the last selected server\n\n    def __init__(self, **data) -> None:\n        super().__init__(**data)\n        # Initialize cache keys to avoid CacheMiss when accessing them\n        self._ensure_cache_structure()\n\n        # Initialize clients with access to the component cache\n        self.stdio_client: MCPStdioClient = MCPStdioClient(component_cache=self._shared_component_cache)\n        self.streamable_http_client: MCPStreamableHttpClient = MCPStreamableHttpClient(\n            component_cache=self._shared_component_cache\n        )\n\n    def _ensure_cache_structure(self):\n        \"\"\"Ensure the cache has the required structure.\"\"\"\n        # Check if servers key exists and is not CacheMiss\n        servers_value = safe_cache_get(self._shared_component_cache, \"servers\")\n        if servers_value is None:\n            safe_cache_set(self._shared_component_cache, \"servers\", {})\n\n        # Check if last_selected_server key exists and is not CacheMiss\n        last_server_value = safe_cache_get(self._shared_component_cache, \"last_selected_server\")\n        if last_server_value is None:\n            safe_cache_set(self._shared_component_cache, \"last_selected_server\", \"\")\n\n    default_keys: list[str] = [\n        \"code\",\n        \"_type\",\n        \"tool_mode\",\n        \"tool_placeholder\",\n        \"mcp_server\",\n        \"tool\",\n        \"use_cache\",\n        \"verify_ssl\",\n    ]\n\n    display_name = \"MCP Tools\"\n    description = \"Connect to an MCP server to use its tools.\"\n    documentation: str = \"https://docs.langflow.org/mcp-client\"\n    icon = \"Mcp\"\n    name = \"MCPTools\"\n\n    inputs = [\n        McpInput(\n            name=\"mcp_server\",\n            display_name=\"MCP Server\",\n            info=\"Select the MCP Server that will be used by this component\",\n            real_time_refresh=True,\n        ),\n        BoolInput(\n            name=\"use_cache\",\n            display_name=\"Use Cached Server\",\n            info=(\n                \"Enable caching of MCP Server and tools to improve performance. \"\n                \"Disable to always fetch fresh tools and server updates.\"\n            ),\n            value=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"verify_ssl\",\n            display_name=\"Verify SSL Certificate\",\n            info=(\n                \"Enable SSL certificate verification for HTTPS connections. \"\n                \"Disable only for development/testing with self-signed certificates.\"\n            ),\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"tool\",\n            display_name=\"Tool\",\n            options=[],\n            value=\"\",\n            info=\"Select the tool to execute\",\n            show=False,\n            required=True,\n            real_time_refresh=True,\n        ),\n        MessageTextInput(\n            name=\"tool_placeholder\",\n            display_name=\"Tool Placeholder\",\n            info=\"Placeholder for the tool\",\n            value=\"\",\n            show=False,\n            tool_mode=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Response\", name=\"response\", method=\"build_output\"),\n    ]\n\n    async def _validate_schema_inputs(self, tool_obj) -> list[InputTypes]:\n        \"\"\"Validate and process schema inputs for a tool.\"\"\"\n        try:\n            if not tool_obj or not hasattr(tool_obj, \"args_schema\"):\n                msg = \"Invalid tool object or missing input schema\"\n                raise ValueError(msg)\n\n            flat_schema = flatten_schema(tool_obj.args_schema.schema())\n            input_schema = create_input_schema_from_json_schema(flat_schema)\n            if not input_schema:\n                msg = f\"Empty input schema for tool '{tool_obj.name}'\"\n                raise ValueError(msg)\n\n            schema_inputs = schema_to_langflow_inputs(input_schema)\n            if not schema_inputs:\n                msg = f\"No input parameters defined for tool '{tool_obj.name}'\"\n                await logger.awarning(msg)\n                return []\n\n        except Exception as e:\n            msg = f\"Error validating schema inputs: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return schema_inputs\n\n    async def update_tool_list(self, mcp_server_value=None):\n        # Accepts mcp_server_value as dict {name, config} or uses self.mcp_server\n        mcp_server = mcp_server_value if mcp_server_value is not None else getattr(self, \"mcp_server\", None)\n        server_name = None\n        server_config_from_value = None\n        if isinstance(mcp_server, dict):\n            server_name = mcp_server.get(\"name\")\n            server_config_from_value = mcp_server.get(\"config\")\n        else:\n            server_name = mcp_server\n        if not server_name:\n            self.tools = []\n            return [], {\"name\": server_name, \"config\": server_config_from_value}\n\n        # Check if caching is enabled, default to False\n        use_cache = getattr(self, \"use_cache\", False)\n\n        # Use shared cache if available and caching is enabled\n        cached = None\n        if use_cache:\n            servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n            cached = servers_cache.get(server_name) if isinstance(servers_cache, dict) else None\n\n        if cached is not None:\n            try:\n                self.tools = cached[\"tools\"]\n                self.tool_names = cached[\"tool_names\"]\n                self._tool_cache = cached[\"tool_cache\"]\n                server_config_from_value = cached[\"config\"]\n            except (TypeError, KeyError, AttributeError) as e:\n                # Handle corrupted cache data by clearing it and continuing to fetch fresh tools\n                msg = f\"Unable to use cached data for MCP Server{server_name}: {e}\"\n                await logger.awarning(msg)\n                # Clear the corrupted cache entry\n                current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                if isinstance(current_servers_cache, dict) and server_name in current_servers_cache:\n                    current_servers_cache.pop(server_name)\n                    safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n            else:\n                return self.tools, {\"name\": server_name, \"config\": server_config_from_value}\n\n        try:\n            try:\n                from langflow.api.v2.mcp import get_server\n                from langflow.services.database.models.user.crud import get_user_by_id\n            except ImportError as e:\n                msg = (\n                    \"Langflow MCP server functionality is not available. \"\n                    \"This feature requires the full Langflow installation.\"\n                )\n                raise ImportError(msg) from e\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for fetching MCP tools.\"\n                    raise ValueError(msg)\n                current_user = await get_user_by_id(db, self.user_id)\n\n                # Try to get server config from DB/API\n                server_config = await get_server(\n                    server_name,\n                    current_user,\n                    db,\n                    storage_service=get_storage_service(),\n                    settings_service=get_settings_service(),\n                )\n\n            # If get_server returns empty but we have a config, use it\n            if not server_config and server_config_from_value:\n                server_config = server_config_from_value\n\n            if not server_config:\n                self.tools = []\n                return [], {\"name\": server_name, \"config\": server_config}\n\n            # Add verify_ssl option to server config if not present\n            if \"verify_ssl\" not in server_config:\n                verify_ssl = getattr(self, \"verify_ssl\", True)\n                server_config[\"verify_ssl\"] = verify_ssl\n\n            _, tool_list, tool_cache = await update_tools(\n                server_name=server_name,\n                server_config=server_config,\n                mcp_stdio_client=self.stdio_client,\n                mcp_streamable_http_client=self.streamable_http_client,\n            )\n\n            self.tool_names = [tool.name for tool in tool_list if hasattr(tool, \"name\")]\n            self._tool_cache = tool_cache\n            self.tools = tool_list\n\n            # Cache the result only if caching is enabled\n            if use_cache:\n                cache_data = {\n                    \"tools\": tool_list,\n                    \"tool_names\": self.tool_names,\n                    \"tool_cache\": tool_cache,\n                    \"config\": server_config,\n                }\n\n                # Safely update the servers cache\n                current_servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                if isinstance(current_servers_cache, dict):\n                    current_servers_cache[server_name] = cache_data\n                    safe_cache_set(self._shared_component_cache, \"servers\", current_servers_cache)\n\n        except (TimeoutError, asyncio.TimeoutError) as e:\n            msg = f\"Timeout updating tool list: {e!s}\"\n            await logger.aexception(msg)\n            raise TimeoutError(msg) from e\n        except Exception as e:\n            msg = f\"Error updating tool list: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return tool_list, {\"name\": server_name, \"config\": server_config}\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Toggle the visibility of connection-specific fields based on the selected mode.\"\"\"\n        try:\n            if field_name == \"tool\":\n                try:\n                    if len(self.tools) == 0:\n                        try:\n                            self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n                            build_config[\"tool\"][\"options\"] = [tool.name for tool in self.tools]\n                            build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n                        except (TimeoutError, asyncio.TimeoutError) as e:\n                            msg = f\"Timeout updating tool list: {e!s}\"\n                            await logger.aexception(msg)\n                            if not build_config[\"tools_metadata\"][\"show\"]:\n                                build_config[\"tool\"][\"show\"] = True\n                                build_config[\"tool\"][\"options\"] = []\n                                build_config[\"tool\"][\"value\"] = \"\"\n                                build_config[\"tool\"][\"placeholder\"] = \"Timeout on MCP server\"\n                            else:\n                                build_config[\"tool\"][\"show\"] = False\n                        except ValueError:\n                            if not build_config[\"tools_metadata\"][\"show\"]:\n                                build_config[\"tool\"][\"show\"] = True\n                                build_config[\"tool\"][\"options\"] = []\n                                build_config[\"tool\"][\"value\"] = \"\"\n                                build_config[\"tool\"][\"placeholder\"] = \"Error on MCP Server\"\n                            else:\n                                build_config[\"tool\"][\"show\"] = False\n\n                    if field_value == \"\":\n                        return build_config\n                    tool_obj = None\n                    for tool in self.tools:\n                        if tool.name == field_value:\n                            tool_obj = tool\n                            break\n                    if tool_obj is None:\n                        msg = f\"Tool {field_value} not found in available tools: {self.tools}\"\n                        await logger.awarning(msg)\n                        return build_config\n                    await self._update_tool_config(build_config, field_value)\n                except Exception as e:\n                    build_config[\"tool\"][\"options\"] = []\n                    msg = f\"Failed to update tools: {e!s}\"\n                    raise ValueError(msg) from e\n                else:\n                    return build_config\n            elif field_name == \"mcp_server\":\n                if not field_value:\n                    build_config[\"tool\"][\"show\"] = False\n                    build_config[\"tool\"][\"options\"] = []\n                    build_config[\"tool\"][\"value\"] = \"\"\n                    build_config[\"tool\"][\"placeholder\"] = \"\"\n                    build_config[\"tool_placeholder\"][\"tool_mode\"] = False\n                    self.remove_non_default_keys(build_config)\n                    return build_config\n\n                build_config[\"tool_placeholder\"][\"tool_mode\"] = True\n\n                current_server_name = field_value.get(\"name\") if isinstance(field_value, dict) else field_value\n                _last_selected_server = safe_cache_get(self._shared_component_cache, \"last_selected_server\", \"\")\n                server_changed = current_server_name != _last_selected_server\n\n                # Determine if \"Tool Mode\" is active by checking if the tool dropdown is hidden.\n                is_in_tool_mode = build_config[\"tools_metadata\"][\"show\"]\n\n                # Get use_cache setting to determine if we should use cached data\n                use_cache = getattr(self, \"use_cache\", False)\n\n                # Fast path: if server didn't change and we already have options, keep them as-is\n                # BUT only if caching is enabled or we're in tool mode\n                existing_options = build_config.get(\"tool\", {}).get(\"options\") or []\n                if not server_changed and existing_options:\n                    # In non-tool mode with cache disabled, skip the fast path to force refresh\n                    if not is_in_tool_mode and not use_cache:\n                        pass  # Continue to refresh logic below\n                    else:\n                        if not is_in_tool_mode:\n                            build_config[\"tool\"][\"show\"] = True\n                        return build_config\n\n                # To avoid unnecessary updates, only proceed if the server has actually changed\n                # OR if caching is disabled (to force refresh in non-tool mode)\n                if (_last_selected_server in (current_server_name, \"\")) and build_config[\"tool\"][\"show\"] and use_cache:\n                    if current_server_name:\n                        servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                        if isinstance(servers_cache, dict):\n                            cached = servers_cache.get(current_server_name)\n                            if cached is not None and cached.get(\"tool_names\"):\n                                cached_tools = cached[\"tool_names\"]\n                                current_tools = build_config[\"tool\"][\"options\"]\n                                if current_tools == cached_tools:\n                                    return build_config\n                    else:\n                        return build_config\n                safe_cache_set(self._shared_component_cache, \"last_selected_server\", current_server_name)\n\n                # Check if tools are already cached for this server before clearing\n                cached_tools = None\n                if current_server_name and use_cache:\n                    servers_cache = safe_cache_get(self._shared_component_cache, \"servers\", {})\n                    if isinstance(servers_cache, dict):\n                        cached = servers_cache.get(current_server_name)\n                        if cached is not None:\n                            try:\n                                cached_tools = cached[\"tools\"]\n                                self.tools = cached_tools\n                                self.tool_names = cached[\"tool_names\"]\n                                self._tool_cache = cached[\"tool_cache\"]\n                            except (TypeError, KeyError, AttributeError) as e:\n                                # Handle corrupted cache data by ignoring it\n                                msg = f\"Unable to use cached data for MCP Server,{current_server_name}: {e}\"\n                                await logger.awarning(msg)\n                                cached_tools = None\n\n                # Only clear tools if we don't have cached tools for the current server\n                if not cached_tools:\n                    self.tools = []  # Clear previous tools only if no cache\n\n                # Clear previous tool inputs if:\n                # 1. Server actually changed\n                # 2. Cache is disabled (meaning tool list will be refreshed)\n                if server_changed or not use_cache:\n                    self.remove_non_default_keys(build_config)\n\n                # Only show the tool dropdown if not in tool_mode\n                if not is_in_tool_mode:\n                    build_config[\"tool\"][\"show\"] = True\n                    if cached_tools:\n                        # Use cached tools to populate options immediately\n                        build_config[\"tool\"][\"options\"] = [tool.name for tool in cached_tools]\n                        build_config[\"tool\"][\"placeholder\"] = \"Select a tool\"\n                    else:\n                        # Show loading state only when we need to fetch tools\n                        build_config[\"tool\"][\"placeholder\"] = \"Loading tools...\"\n                        build_config[\"tool\"][\"options\"] = []\n                    # Force a value refresh when:\n                    # 1. Server changed\n                    # 2. We don't have cached tools\n                    # 3. Cache is disabled (to force refresh on config changes)\n                    if server_changed or not cached_tools or not use_cache:\n                        build_config[\"tool\"][\"value\"] = uuid.uuid4()\n                else:\n                    # Keep the tool dropdown hidden if in tool_mode\n                    self._not_load_actions = True\n                    build_config[\"tool\"][\"show\"] = False\n\n            elif field_name == \"tool_mode\":\n                build_config[\"tool\"][\"placeholder\"] = \"\"\n                build_config[\"tool\"][\"show\"] = not bool(field_value) and bool(build_config[\"mcp_server\"])\n                self.remove_non_default_keys(build_config)\n                self.tool = build_config[\"tool\"][\"value\"]\n                if field_value:\n                    self._not_load_actions = True\n                else:\n                    build_config[\"tool\"][\"value\"] = uuid.uuid4()\n                    build_config[\"tool\"][\"options\"] = []\n                    build_config[\"tool\"][\"show\"] = True\n                    build_config[\"tool\"][\"placeholder\"] = \"Loading tools...\"\n            elif field_name == \"tools_metadata\":\n                self._not_load_actions = False\n\n        except Exception as e:\n            msg = f\"Error in update_build_config: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n        else:\n            return build_config\n\n    def get_inputs_for_all_tools(self, tools: list) -> dict:\n        \"\"\"Get input schemas for all tools.\"\"\"\n        inputs = {}\n        for tool in tools:\n            if not tool or not hasattr(tool, \"name\"):\n                continue\n            try:\n                flat_schema = flatten_schema(tool.args_schema.schema())\n                input_schema = create_input_schema_from_json_schema(flat_schema)\n                langflow_inputs = schema_to_langflow_inputs(input_schema)\n                inputs[tool.name] = langflow_inputs\n            except (AttributeError, ValueError, TypeError, KeyError) as e:\n                msg = f\"Error getting inputs for tool {getattr(tool, 'name', 'unknown')}: {e!s}\"\n                logger.exception(msg)\n                continue\n        return inputs\n\n    def remove_non_default_keys(self, build_config: dict) -> None:\n        \"\"\"Remove non-default keys from the build config.\"\"\"\n        for key in list(build_config.keys()):\n            if key not in self.default_keys:\n                build_config.pop(key)\n\n    async def _update_tool_config(self, build_config: dict, tool_name: str) -> None:\n        \"\"\"Update tool configuration with proper error handling.\"\"\"\n        if not self.tools:\n            self.tools, build_config[\"mcp_server\"][\"value\"] = await self.update_tool_list()\n\n        if not tool_name:\n            return\n\n        tool_obj = next((tool for tool in self.tools if tool.name == tool_name), None)\n        if not tool_obj:\n            msg = f\"Tool {tool_name} not found in available tools: {self.tools}\"\n            self.remove_non_default_keys(build_config)\n            build_config[\"tool\"][\"value\"] = \"\"\n            await logger.awarning(msg)\n            return\n\n        try:\n            # Store current values before removing inputs (only for the current tool)\n            current_values = {}\n            for key, value in build_config.items():\n                if key not in self.default_keys and isinstance(value, dict) and \"value\" in value:\n                    current_values[key] = value[\"value\"]\n\n            # Remove ALL non-default keys (all previous tool inputs)\n            self.remove_non_default_keys(build_config)\n\n            # Get and validate new inputs for the selected tool\n            self.schema_inputs = await self._validate_schema_inputs(tool_obj)\n            if not self.schema_inputs:\n                msg = f\"No input parameters to configure for tool '{tool_name}'\"\n                await logger.ainfo(msg)\n                return\n\n            # Add new inputs to build config for the selected tool only\n            for schema_input in self.schema_inputs:\n                if not schema_input or not hasattr(schema_input, \"name\"):\n                    msg = \"Invalid schema input detected, skipping\"\n                    await logger.awarning(msg)\n                    continue\n\n                try:\n                    name = schema_input.name\n                    input_dict = schema_input.to_dict()\n                    input_dict.setdefault(\"value\", None)\n                    input_dict.setdefault(\"required\", True)\n\n                    build_config[name] = input_dict\n\n                    # Preserve existing value if the parameter name exists in current_values\n                    if name in current_values:\n                        build_config[name][\"value\"] = current_values[name]\n\n                except (AttributeError, KeyError, TypeError) as e:\n                    msg = f\"Error processing schema input {schema_input}: {e!s}\"\n                    await logger.aexception(msg)\n                    continue\n        except ValueError as e:\n            msg = f\"Schema validation error for tool {tool_name}: {e!s}\"\n            await logger.aexception(msg)\n            self.schema_inputs = []\n            return\n        except (AttributeError, KeyError, TypeError) as e:\n            msg = f\"Error updating tool config: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n\n    async def build_output(self) -> DataFrame:\n        \"\"\"Build output with improved error handling and validation.\"\"\"\n        try:\n            self.tools, _ = await self.update_tool_list()\n            if self.tool != \"\":\n                # Set session context for persistent MCP sessions using Langflow session ID\n                session_context = self._get_session_context()\n                if session_context:\n                    self.stdio_client.set_session_context(session_context)\n                    self.streamable_http_client.set_session_context(session_context)\n                exec_tool = self._tool_cache[self.tool]\n                tool_args = self.get_inputs_for_all_tools(self.tools)[self.tool]\n                kwargs = {}\n                for arg in tool_args:\n                    value = getattr(self, arg.name, None)\n                    if value is not None:\n                        if isinstance(value, Message):\n                            kwargs[arg.name] = value.text\n                        else:\n                            kwargs[arg.name] = value\n\n                unflattened_kwargs = maybe_unflatten_dict(kwargs)\n\n                output = await exec_tool.coroutine(**unflattened_kwargs)\n                tool_content = []\n                for item in output.content:\n                    item_dict = item.model_dump()\n                    item_dict = self.process_output_item(item_dict)\n                    tool_content.append(item_dict)\n\n                if isinstance(tool_content, list) and all(isinstance(x, dict) for x in tool_content):\n                    return DataFrame(tool_content)\n                return DataFrame(data=tool_content)\n            return DataFrame(data=[{\"error\": \"You must select a tool\"}])\n        except Exception as e:\n            msg = f\"Error in build_output: {e!s}\"\n            await logger.aexception(msg)\n            raise ValueError(msg) from e\n\n    def process_output_item(self, item_dict):\n        \"\"\"Process the output of a tool.\"\"\"\n        if item_dict.get(\"type\") == \"text\":\n            text = item_dict.get(\"text\")\n            try:\n                return json.loads(text)\n            except json.JSONDecodeError:\n                return item_dict\n        return item_dict\n\n    def _get_session_context(self) -> str | None:\n        \"\"\"Get the Langflow session ID for MCP session caching.\"\"\"\n        # Try to get session ID from the component's execution context\n        if hasattr(self, \"graph\") and hasattr(self.graph, \"session_id\"):\n            session_id = self.graph.session_id\n            # Include server name to ensure different servers get different sessions\n            server_name = \"\"\n            mcp_server = getattr(self, \"mcp_server\", None)\n            if isinstance(mcp_server, dict):\n                server_name = mcp_server.get(\"name\", \"\")\n            elif mcp_server:\n                server_name = str(mcp_server)\n            return f\"{session_id}_{server_name}\" if session_id else None\n        return None\n\n    async def _get_tools(self):\n        \"\"\"Get cached tools or update if necessary.\"\"\"\n        mcp_server = getattr(self, \"mcp_server\", None)\n        if not self._not_load_actions:\n            tools, _ = await self.update_tool_list(mcp_server)\n            return tools\n        return []\n"
               },
               "mcp_server": {
                 "_input_type": "McpInput",

langflow/initial_setup/starter_projects/Pok/303/251dex Agent.json"

@@ -1245,7 +1245,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json

@@ -931,7 +931,7 @@
             "legacy": false,
             "lf_version": "1.6.0",
             "metadata": {
-              "code_hash": "85abc1094130",
+              "code_hash": "6e78c258044c",
               "dependencies": {
                 "dependencies": [
                   {
@@ -999,7 +999,7 @@
                 "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 (and optional threading via `parallel_load_data`).\n\"\"\"\n\nfrom __future__ import annotations\n\nimport json\nimport subprocess\nimport sys\nimport textwrap\nfrom copy import deepcopy\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame  # noqa: TC001\nfrom lfx.schema.message import Message\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n    display_name = \"Read File\"\n    description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/components-data#file\"\n    icon = \"file-text\"\n    name = \"File\"\n\n    # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n    VALID_EXTENSIONS = [\n        *TEXT_FILE_TYPES,\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    # 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            break\n\n    inputs = [\n        *_base_inputs,\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            show=True,\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\"),\n    ]\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 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        if field_name == \"path\":\n            paths = self._path_value(build_config)\n\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                for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                    if f in build_config:\n                        build_config[f][\"show\"] = False\n\n        # Docling Processing\n        elif field_name == \"advanced_mode\":\n            for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                if f in build_config:\n                    build_config[f][\"show\"] = bool(field_value)\n                    if f == \"pipeline\":\n                        build_config[f][\"advanced\"] = not bool(field_value)\n\n        elif field_name == \"pipeline\":\n            if 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(display_name=\"Structured Content\", name=\"dataframe\", method=\"load_files_structured\"),\n                )\n            elif file_path.endswith(\".json\"):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"json\", method=\"load_files_json\"),\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(display_name=\"Structured Output\", name=\"advanced_dataframe\", method=\"load_files_dataframe\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Markdown\", name=\"advanced_markdown\", method=\"load_files_markdown\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n            else:\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n        else:\n            # Multiple files => DataFrame output; advanced parser disabled\n            frontend_node[\"outputs\"].append(Output(display_name=\"Files\", name=\"dataframe\", method=\"load_files\"))\n\n        return frontend_node\n\n    # ------------------------------ Core processing ----------------------------------\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    def _process_docling_in_subprocess(self, file_path: str) -> 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        if not file_path:\n            return None\n\n        args: dict[str, Any] = {\n            \"file_path\": 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        self.log(f\"Starting Docling subprocess for file: {file_path}\")\n        self.log(args)\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                    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        # Validate file_path to avoid command injection or unsafe input\n        if not isinstance(args[\"file_path\"], str) or any(c in args[\"file_path\"] for c in [\";\", \"|\", \"&\", \"$\", \"`\"]):\n            return Data(data={\"error\": \"Unsafe file path detected.\", \"file_path\": args[\"file_path\"]})\n\n        proc = subprocess.run(  # noqa: S603\n            [sys.executable, \"-u\", \"-c\", child_script],\n            input=json.dumps(args).encode(\"utf-8\"),\n            capture_output=True,\n            check=False,\n        )\n\n        if not proc.stdout:\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\") or \"no output from child process\"\n            return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": file_path})\n\n        try:\n            result = json.loads(proc.stdout.decode(\"utf-8\"))\n        except Exception as e:  # noqa: BLE001\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\")\n            return Data(\n                data={\"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\", \"file_path\": file_path},\n            )\n\n        if not result.get(\"ok\"):\n            return Data(data={\"error\": result.get(\"error\", \"Unknown Docling error\"), **result.get(\"meta\", {})})\n\n        meta = result.get(\"meta\", {})\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    def process_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 in current process (optionally threaded).\n        \"\"\"\n        if not file_list:\n            msg = \"No files to process.\"\n            raise ValueError(msg)\n\n        def process_file_standard(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            try:\n                return parse_text_file_to_data(file_path, silent_errors=silent_errors)\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\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                file_path = str(file.path)\n                advanced_data: Data | None = self._process_docling_in_subprocess(file_path)\n\n                # --- UNNEST: expand each element in `doc` to its own Data row\n                payload = getattr(advanced_data, \"data\", {}) or {}\n                doc_rows = payload.get(\"doc\")\n                if isinstance(doc_rows, list):\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                    final_return.extend(self.rollup_data(file_list, rows))\n                else:\n                    # If not structured, keep as-is (e.g., markdown export or error dict)\n                    final_return.extend(self.rollup_data(file_list, [advanced_data]))\n            return final_return\n\n        # Standard multi-file (or single non-advanced) path\n        concurrency = 1 if not self.use_multithreading else max(1, self.concurrency_multithreading)\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 = parallel_load_data(\n            file_paths,\n            silent_errors=self.silent_errors,\n            load_function=process_file_standard,\n            max_concurrency=concurrency,\n        )\n        return self.rollup_data(file_list, my_data)\n\n    # ------------------------------ Output helpers -----------------------------------\n\n    def load_files_helper(self) -> DataFrame:\n        result = self.load_files()\n\n        # Error condition - raise error if no text and an error is present\n        if not hasattr(result, \"text\"):\n            if hasattr(result, \"error\"):\n                raise ValueError(result.error[0])\n            msg = \"Could not extract content from the provided file(s).\"\n            raise ValueError(msg)\n\n        return result\n\n    def load_files_dataframe(self) -> DataFrame:\n        \"\"\"Load files using advanced Docling processing and export to DataFrame format.\"\"\"\n        self.markdown = False\n        return self.load_files_helper()\n\n    def load_files_markdown(self) -> Message:\n        \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n        self.markdown = True\n        result = self.load_files_helper()\n        return Message(text=str(result.text[0]))\n"
+                "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 (and optional threading via `parallel_load_data`).\n\"\"\"\n\nfrom __future__ import annotations\n\nimport json\nimport subprocess\nimport sys\nimport textwrap\nfrom copy import deepcopy\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame  # noqa: TC001\nfrom lfx.schema.message import Message\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n    display_name = \"Read File\"\n    description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/components-data#file\"\n    icon = \"file-text\"\n    name = \"File\"\n\n    # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n    VALID_EXTENSIONS = [\n        *TEXT_FILE_TYPES,\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    # 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        *_base_inputs,\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,\n            required=False,\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            show=True,\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    # ------------------------------ 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 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        if field_name == \"path\":\n            paths = self._path_value(build_config)\n\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                for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                    if f in build_config:\n                        build_config[f][\"show\"] = False\n\n        # Docling Processing\n        elif field_name == \"advanced_mode\":\n            for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                if f in build_config:\n                    build_config[f][\"show\"] = bool(field_value)\n                    if f == \"pipeline\":\n                        build_config[f][\"advanced\"] = not bool(field_value)\n\n        elif field_name == \"pipeline\":\n            if 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                        tool_mode=True,\n                    ),\n                )\n            elif file_path.endswith(\".json\"):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"json\", method=\"load_files_json\", tool_mode=True),\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                        tool_mode=True,\n                    ),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(\n                        display_name=\"Markdown\", name=\"advanced_markdown\", method=\"load_files_markdown\", tool_mode=True\n                    ),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\", tool_mode=True),\n                )\n            else:\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\", tool_mode=True),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\", tool_mode=True),\n                )\n        else:\n            # Multiple files => DataFrame output; advanced parser disabled\n            frontend_node[\"outputs\"].append(\n                Output(display_name=\"Files\", name=\"dataframe\", method=\"load_files\", tool_mode=True)\n            )\n\n        return frontend_node\n\n    # ------------------------------ Core processing ----------------------------------\n\n    def _validate_and_resolve_paths(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Override to handle file_path_str input from tool mode.\n\n        When called as a tool, the file_path_str parameter can be set.\n        If not provided, it will fall back to using the path FileInput (uploaded file).\n        Priority:\n        1. file_path_str (if provided by the tool call)\n        2. path (uploaded file from UI)\n        \"\"\"\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\n            resolved_path = Path(self.resolve_path(file_path_str))\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 _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    def _process_docling_in_subprocess(self, file_path: str) -> 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        if not file_path:\n            return None\n\n        args: dict[str, Any] = {\n            \"file_path\": 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        self.log(f\"Starting Docling subprocess for file: {file_path}\")\n        self.log(args)\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                    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        # Validate file_path to avoid command injection or unsafe input\n        if not isinstance(args[\"file_path\"], str) or any(c in args[\"file_path\"] for c in [\";\", \"|\", \"&\", \"$\", \"`\"]):\n            return Data(data={\"error\": \"Unsafe file path detected.\", \"file_path\": args[\"file_path\"]})\n\n        proc = subprocess.run(  # noqa: S603\n            [sys.executable, \"-u\", \"-c\", child_script],\n            input=json.dumps(args).encode(\"utf-8\"),\n            capture_output=True,\n            check=False,\n        )\n\n        if not proc.stdout:\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\") or \"no output from child process\"\n            return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": file_path})\n\n        try:\n            result = json.loads(proc.stdout.decode(\"utf-8\"))\n        except Exception as e:  # noqa: BLE001\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\")\n            return Data(\n                data={\"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\", \"file_path\": file_path},\n            )\n\n        if not result.get(\"ok\"):\n            return Data(data={\"error\": result.get(\"error\", \"Unknown Docling error\"), **result.get(\"meta\", {})})\n\n        meta = result.get(\"meta\", {})\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    def process_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 in current process (optionally threaded).\n        \"\"\"\n        if not file_list:\n            msg = \"No files to process.\"\n            raise ValueError(msg)\n\n        def process_file_standard(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            try:\n                return parse_text_file_to_data(file_path, silent_errors=silent_errors)\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\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                file_path = str(file.path)\n                advanced_data: Data | None = self._process_docling_in_subprocess(file_path)\n\n                # --- UNNEST: expand each element in `doc` to its own Data row\n                payload = getattr(advanced_data, \"data\", {}) or {}\n                doc_rows = payload.get(\"doc\")\n                if isinstance(doc_rows, list):\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                    final_return.extend(self.rollup_data(file_list, rows))\n                else:\n                    # If not structured, keep as-is (e.g., markdown export or error dict)\n                    final_return.extend(self.rollup_data(file_list, [advanced_data]))\n            return final_return\n\n        # Standard multi-file (or single non-advanced) path\n        concurrency = 1 if not self.use_multithreading else max(1, self.concurrency_multithreading)\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 = parallel_load_data(\n            file_paths,\n            silent_errors=self.silent_errors,\n            load_function=process_file_standard,\n            max_concurrency=concurrency,\n        )\n        return self.rollup_data(file_list, my_data)\n\n    # ------------------------------ Output helpers -----------------------------------\n\n    def load_files_helper(self) -> DataFrame:\n        result = self.load_files()\n\n        # Error condition - raise error if no text and an error is present\n        if not hasattr(result, \"text\"):\n            if hasattr(result, \"error\"):\n                raise ValueError(result.error[0])\n            msg = \"Could not extract content from the provided file(s).\"\n            raise ValueError(msg)\n\n        return result\n\n    def load_files_dataframe(self) -> DataFrame:\n        \"\"\"Load files using advanced Docling processing and export to DataFrame format.\"\"\"\n        self.markdown = False\n        return self.load_files_helper()\n\n    def load_files_markdown(self) -> Message:\n        \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n        self.markdown = True\n        result = self.load_files_helper()\n        return Message(text=str(result.text[0]))\n"
               },
               "concurrency_multithreading": {
                 "_input_type": "IntInput",
@@ -1081,6 +1081,26 @@
                 "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",
+                "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,
@@ -2077,7 +2097,7 @@
                 "dependencies": [
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "trustcall",

langflow/initial_setup/starter_projects/Price Deal Finder.json

@@ -1612,7 +1612,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Research Agent.json

@@ -2585,7 +2585,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",