langflow-base-nightly 1.7.0.dev19__py3-none-any.whl → 1.7.0.dev20__py3-none-any.whl

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",

langflow/initial_setup/starter_projects/Research Translation Loop.json

@@ -1156,7 +1156,7 @@
             "beta": false,
             "conditional_paths": [],
             "custom_fields": {},
-            "description": "Iterates over a list of Data objects, outputting one item at a time and aggregating results from loop inputs.",
+            "description": "Iterates over a list of Data or Message objects, outputting one item at a time and aggregating results from loop inputs. Message objects are automatically converted to Data objects for consistent processing.",
             "display_name": "Loop",
             "documentation": "",
             "edited": false,
@@ -1168,7 +1168,7 @@
             "legacy": false,
             "lf_version": "1.4.3",
             "metadata": {
-              "code_hash": "394284181e18",
+              "code_hash": "8e64e0e14d4d",
               "dependencies": {
                 "dependencies": [
                   {
@@ -1188,6 +1188,9 @@
                 "cache": true,
                 "display_name": "Item",
                 "group_outputs": true,
+                "loop_types": [
+                  "Message"
+                ],
                 "method": "item_output",
                 "name": "item",
                 "selected": "Data",
@@ -1231,14 +1234,14 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.custom.custom_component.component import Component\nfrom lfx.inputs.inputs import HandleInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.template.field.base import Output\n\n\nclass LoopComponent(Component):\n    display_name = \"Loop\"\n    description = (\n        \"Iterates over a list of Data objects, outputting one item at a time and aggregating results from loop inputs.\"\n    )\n    documentation: str = \"https://docs.langflow.org/components-logic#loop\"\n    icon = \"infinity\"\n\n    inputs = [\n        HandleInput(\n            name=\"data\",\n            display_name=\"Inputs\",\n            info=\"The initial list of Data objects or DataFrame to iterate over.\",\n            input_types=[\"DataFrame\"],\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Item\", name=\"item\", method=\"item_output\", allows_loop=True, group_outputs=True),\n        Output(display_name=\"Done\", name=\"done\", method=\"done_output\", group_outputs=True),\n    ]\n\n    def initialize_data(self) -> None:\n        \"\"\"Initialize the data list, context index, and aggregated list.\"\"\"\n        if self.ctx.get(f\"{self._id}_initialized\", False):\n            return\n\n        # Ensure data is a list of Data objects\n        data_list = self._validate_data(self.data)\n\n        # Store the initial data and context variables\n        self.update_ctx(\n            {\n                f\"{self._id}_data\": data_list,\n                f\"{self._id}_index\": 0,\n                f\"{self._id}_aggregated\": [],\n                f\"{self._id}_initialized\": True,\n            }\n        )\n\n    def _validate_data(self, data):\n        \"\"\"Validate and return a list of Data objects.\"\"\"\n        if isinstance(data, DataFrame):\n            return data.to_data_list()\n        if isinstance(data, Data):\n            return [data]\n        if isinstance(data, list) and all(isinstance(item, Data) for item in data):\n            return data\n        msg = \"The 'data' input must be a DataFrame, a list of Data objects, or a single Data object.\"\n        raise TypeError(msg)\n\n    def evaluate_stop_loop(self) -> bool:\n        \"\"\"Evaluate whether to stop item or done output.\"\"\"\n        current_index = self.ctx.get(f\"{self._id}_index\", 0)\n        data_length = len(self.ctx.get(f\"{self._id}_data\", []))\n        return current_index > data_length\n\n    def item_output(self) -> Data:\n        \"\"\"Output the next item in the list or stop if done.\"\"\"\n        self.initialize_data()\n        current_item = Data(text=\"\")\n\n        if self.evaluate_stop_loop():\n            self.stop(\"item\")\n        else:\n            # Get data list and current index\n            data_list, current_index = self.loop_variables()\n            if current_index < len(data_list):\n                # Output current item and increment index\n                try:\n                    current_item = data_list[current_index]\n                except IndexError:\n                    current_item = Data(text=\"\")\n            self.aggregated_output()\n            self.update_ctx({f\"{self._id}_index\": current_index + 1})\n\n        # Now we need to update the dependencies for the next run\n        self.update_dependency()\n        return current_item\n\n    def update_dependency(self):\n        item_dependency_id = self.get_incoming_edge_by_target_param(\"item\")\n        if item_dependency_id not in self.graph.run_manager.run_predecessors[self._id]:\n            self.graph.run_manager.run_predecessors[self._id].append(item_dependency_id)\n            # CRITICAL: Also update run_map so remove_from_predecessors() works correctly\n            # run_map[predecessor] = list of vertices that depend on predecessor\n            if self._id not in self.graph.run_manager.run_map[item_dependency_id]:\n                self.graph.run_manager.run_map[item_dependency_id].append(self._id)\n\n    def done_output(self) -> DataFrame:\n        \"\"\"Trigger the done output when iteration is complete.\"\"\"\n        self.initialize_data()\n\n        if self.evaluate_stop_loop():\n            self.stop(\"item\")\n            self.start(\"done\")\n\n            aggregated = self.ctx.get(f\"{self._id}_aggregated\", [])\n\n            return DataFrame(aggregated)\n        self.stop(\"done\")\n        return DataFrame([])\n\n    def loop_variables(self):\n        \"\"\"Retrieve loop variables from context.\"\"\"\n        return (\n            self.ctx.get(f\"{self._id}_data\", []),\n            self.ctx.get(f\"{self._id}_index\", 0),\n        )\n\n    def aggregated_output(self) -> list[Data]:\n        \"\"\"Return the aggregated list once all items are processed.\"\"\"\n        self.initialize_data()\n\n        # Get data list and aggregated list\n        data_list = self.ctx.get(f\"{self._id}_data\", [])\n        aggregated = self.ctx.get(f\"{self._id}_aggregated\", [])\n        loop_input = self.item\n        if loop_input is not None and not isinstance(loop_input, str) and len(aggregated) <= len(data_list):\n            aggregated.append(loop_input)\n            self.update_ctx({f\"{self._id}_aggregated\": aggregated})\n        return aggregated\n"
+                "value": "from lfx.components.processing.converter import convert_to_data\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs.inputs import HandleInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.template.field.base import Output\n\n\nclass LoopComponent(Component):\n    display_name = \"Loop\"\n    description = (\n        \"Iterates over a list of Data or Message objects, outputting one item at a time and \"\n        \"aggregating results from loop inputs. Message objects are automatically converted to \"\n        \"Data objects for consistent processing.\"\n    )\n    documentation: str = \"https://docs.langflow.org/components-logic#loop\"\n    icon = \"infinity\"\n\n    inputs = [\n        HandleInput(\n            name=\"data\",\n            display_name=\"Inputs\",\n            info=\"The initial DataFrame to iterate over.\",\n            input_types=[\"DataFrame\"],\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"Item\",\n            name=\"item\",\n            method=\"item_output\",\n            allows_loop=True,\n            loop_types=[\"Message\"],\n            group_outputs=True,\n        ),\n        Output(display_name=\"Done\", name=\"done\", method=\"done_output\", group_outputs=True),\n    ]\n\n    def initialize_data(self) -> None:\n        \"\"\"Initialize the data list, context index, and aggregated list.\"\"\"\n        if self.ctx.get(f\"{self._id}_initialized\", False):\n            return\n\n        # Ensure data is a list of Data objects\n        data_list = self._validate_data(self.data)\n\n        # Store the initial data and context variables\n        self.update_ctx(\n            {\n                f\"{self._id}_data\": data_list,\n                f\"{self._id}_index\": 0,\n                f\"{self._id}_aggregated\": [],\n                f\"{self._id}_initialized\": True,\n            }\n        )\n\n    def _convert_message_to_data(self, message: Message) -> Data:\n        \"\"\"Convert a Message object to a Data object using Type Convert logic.\"\"\"\n        return convert_to_data(message, auto_parse=False)\n\n    def _validate_data(self, data):\n        \"\"\"Validate and return a list of Data objects. Message objects are auto-converted to Data.\"\"\"\n        if isinstance(data, DataFrame):\n            return data.to_data_list()\n        if isinstance(data, Data):\n            return [data]\n        if isinstance(data, Message):\n            # Auto-convert Message to Data\n            converted_data = self._convert_message_to_data(data)\n            return [converted_data]\n        if isinstance(data, list) and all(isinstance(item, (Data, Message)) for item in data):\n            # Convert any Message objects in the list to Data objects\n            converted_list = []\n            for item in data:\n                if isinstance(item, Message):\n                    converted_list.append(self._convert_message_to_data(item))\n                else:\n                    converted_list.append(item)\n            return converted_list\n        msg = \"The 'data' input must be a DataFrame, a list of Data/Message objects, or a single Data/Message object.\"\n        raise TypeError(msg)\n\n    def evaluate_stop_loop(self) -> bool:\n        \"\"\"Evaluate whether to stop item or done output.\"\"\"\n        current_index = self.ctx.get(f\"{self._id}_index\", 0)\n        data_length = len(self.ctx.get(f\"{self._id}_data\", []))\n        return current_index > data_length\n\n    def item_output(self) -> Data:\n        \"\"\"Output the next item in the list or stop if done.\"\"\"\n        self.initialize_data()\n        current_item = Data(text=\"\")\n\n        if self.evaluate_stop_loop():\n            self.stop(\"item\")\n        else:\n            # Get data list and current index\n            data_list, current_index = self.loop_variables()\n            if current_index < len(data_list):\n                # Output current item and increment index\n                try:\n                    current_item = data_list[current_index]\n                except IndexError:\n                    current_item = Data(text=\"\")\n            self.aggregated_output()\n            self.update_ctx({f\"{self._id}_index\": current_index + 1})\n\n        # Now we need to update the dependencies for the next run\n        self.update_dependency()\n        return current_item\n\n    def update_dependency(self):\n        item_dependency_id = self.get_incoming_edge_by_target_param(\"item\")\n        if item_dependency_id not in self.graph.run_manager.run_predecessors[self._id]:\n            self.graph.run_manager.run_predecessors[self._id].append(item_dependency_id)\n            # CRITICAL: Also update run_map so remove_from_predecessors() works correctly\n            # run_map[predecessor] = list of vertices that depend on predecessor\n            if self._id not in self.graph.run_manager.run_map[item_dependency_id]:\n                self.graph.run_manager.run_map[item_dependency_id].append(self._id)\n\n    def done_output(self) -> DataFrame:\n        \"\"\"Trigger the done output when iteration is complete.\"\"\"\n        self.initialize_data()\n\n        if self.evaluate_stop_loop():\n            self.stop(\"item\")\n            self.start(\"done\")\n\n            aggregated = self.ctx.get(f\"{self._id}_aggregated\", [])\n\n            return DataFrame(aggregated)\n        self.stop(\"done\")\n        return DataFrame([])\n\n    def loop_variables(self):\n        \"\"\"Retrieve loop variables from context.\"\"\"\n        return (\n            self.ctx.get(f\"{self._id}_data\", []),\n            self.ctx.get(f\"{self._id}_index\", 0),\n        )\n\n    def aggregated_output(self) -> list[Data]:\n        \"\"\"Return the aggregated list once all items are processed.\n\n        Returns Data or Message objects depending on loop input types.\n        \"\"\"\n        self.initialize_data()\n\n        # Get data list and aggregated list\n        data_list = self.ctx.get(f\"{self._id}_data\", [])\n        aggregated = self.ctx.get(f\"{self._id}_aggregated\", [])\n        loop_input = self.item\n\n        # Append the current loop input to aggregated if it's not already included\n        if loop_input is not None and not isinstance(loop_input, str) and len(aggregated) <= len(data_list):\n            # If the loop input is a Message, convert it to Data for consistency\n            if isinstance(loop_input, Message):\n                loop_input = self._convert_message_to_data(loop_input)\n            aggregated.append(loop_input)\n            self.update_ctx({f\"{self._id}_aggregated\": aggregated})\n        return aggregated\n"
               },
               "data": {
                 "_input_type": "HandleInput",
                 "advanced": false,
                 "display_name": "Inputs",
                 "dynamic": false,
-                "info": "The initial list of Data objects or DataFrame to iterate over.",
+                "info": "The initial DataFrame to iterate over.",
                 "input_types": [
                   "DataFrame"
                 ],

langflow/initial_setup/starter_projects/SaaS Pricing.json

@@ -874,7 +874,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Search agent.json

@@ -951,7 +951,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Sequential Tasks Agents.json

@@ -366,7 +366,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -1099,7 +1099,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -2603,7 +2603,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -3325,7 +3325,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Simple Agent.json

@@ -939,7 +939,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Social Media Agent.json

@@ -161,7 +161,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -392,7 +392,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -1297,7 +1297,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",

langflow/initial_setup/starter_projects/Text Sentiment Analysis.json

@@ -2339,7 +2339,7 @@
             "icon": "file-text",
             "legacy": false,
             "metadata": {
-              "code_hash": "85abc1094130",
+              "code_hash": "6e78c258044c",
               "dependencies": {
                 "dependencies": [
                   {
@@ -2407,7 +2407,7 @@
                 "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",
@@ -2489,6 +2489,26 @@
                 "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,

langflow/initial_setup/starter_projects/Travel Planning Agents.json

@@ -1672,7 +1672,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -2398,7 +2398,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",
@@ -3124,7 +3124,7 @@
                   },
                   {
                     "name": "pydantic",
-                    "version": "2.10.6"
+                    "version": "2.11.10"
                   },
                   {
                     "name": "lfx",