langflow-base-nightly 1.7.1.dev0__py3-none-any.whl → 1.7.1.dev2__py3-none-any.whl

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

@@ -7,7 +7,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "parser",
-            "id": "parser-tsqQI",
+            "id": "parser-6caGE",
             "name": "parsed_text",
             "output_types": [
               "Message"
@@ -15,19 +15,19 @@
           },
           "targetHandle": {
             "fieldName": "input_value",
-            "id": "LanguageModelComponent-kiTPL",
+            "id": "LanguageModelComponent-DJzkZ",
             "inputTypes": [
               "Message"
             ],
             "type": "str"
           }
         },
-        "id": "reactflow__edge-parser-tsqQI{œdataTypeœ:œparserœ,œidœ:œparser-tsqQIœ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-kiTPL{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-kiTPLœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-parser-6caGE{œdataTypeœ:œparserœ,œidœ:œparser-6caGEœ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-DJzkZ{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-DJzkZœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "parser-tsqQI",
-        "sourceHandle": "{œdataTypeœ: œparserœ, œidœ: œparser-tsqQIœ, œnameœ: œparsed_textœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "LanguageModelComponent-kiTPL",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œLanguageModelComponent-kiTPLœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "source": "parser-6caGE",
+        "sourceHandle": "{œdataTypeœ: œparserœ, œidœ: œparser-6caGEœ, œnameœ: œparsed_textœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "LanguageModelComponent-DJzkZ",
+        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œLanguageModelComponent-DJzkZœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
@@ -35,7 +35,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "TextInput",
-            "id": "TextInput-y6Hxj",
+            "id": "TextInput-fQKUN",
             "name": "text",
             "output_types": [
               "Message"
@@ -43,19 +43,19 @@
           },
           "targetHandle": {
             "fieldName": "system_message",
-            "id": "LanguageModelComponent-kiTPL",
+            "id": "LanguageModelComponent-DJzkZ",
             "inputTypes": [
               "Message"
             ],
             "type": "str"
           }
         },
-        "id": "reactflow__edge-TextInput-y6Hxj{œdataTypeœ:œTextInputœ,œidœ:œTextInput-y6Hxjœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-kiTPL{œfieldNameœ:œsystem_messageœ,œidœ:œLanguageModelComponent-kiTPLœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-TextInput-fQKUN{œdataTypeœ:œTextInputœ,œidœ:œTextInput-fQKUNœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-DJzkZ{œfieldNameœ:œsystem_messageœ,œidœ:œLanguageModelComponent-DJzkZœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "TextInput-y6Hxj",
-        "sourceHandle": "{œdataTypeœ: œTextInputœ, œidœ: œTextInput-y6Hxjœ, œnameœ: œtextœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "LanguageModelComponent-kiTPL",
-        "targetHandle": "{œfieldNameœ: œsystem_messageœ, œidœ: œLanguageModelComponent-kiTPLœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "source": "TextInput-fQKUN",
+        "sourceHandle": "{œdataTypeœ: œTextInputœ, œidœ: œTextInput-fQKUNœ, œnameœ: œtextœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "LanguageModelComponent-DJzkZ",
+        "targetHandle": "{œfieldNameœ: œsystem_messageœ, œidœ: œLanguageModelComponent-DJzkZœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
@@ -63,7 +63,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "LanguageModelComponent",
-            "id": "LanguageModelComponent-kiTPL",
+            "id": "LanguageModelComponent-DJzkZ",
             "name": "text_output",
             "output_types": [
               "Message"
@@ -71,7 +71,7 @@
           },
           "targetHandle": {
             "fieldName": "input_value",
-            "id": "ChatOutput-KnHDm",
+            "id": "ChatOutput-q991L",
             "inputTypes": [
               "Data",
               "DataFrame",
@@ -80,75 +80,75 @@
             "type": "str"
           }
         },
-        "id": "reactflow__edge-LanguageModelComponent-kiTPL{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-kiTPLœ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-KnHDm{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-KnHDmœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-LanguageModelComponent-DJzkZ{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-DJzkZœ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-q991L{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-q991Lœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "LanguageModelComponent-kiTPL",
-        "sourceHandle": "{œdataTypeœ: œLanguageModelComponentœ, œidœ: œLanguageModelComponent-kiTPLœ, œnameœ: œtext_outputœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "ChatOutput-KnHDm",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-KnHDmœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œstrœ}"
+        "source": "LanguageModelComponent-DJzkZ",
+        "sourceHandle": "{œdataTypeœ: œLanguageModelComponentœ, œidœ: œLanguageModelComponent-DJzkZœ, œnameœ: œtext_outputœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "ChatOutput-q991L",
+        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-q991Lœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
         "className": "",
         "data": {
           "sourceHandle": {
-            "dataType": "StructuredOutput",
-            "id": "StructuredOutput-GJE9p",
-            "name": "dataframe_output",
+            "dataType": "File",
+            "id": "File-gVVqw",
+            "name": "message",
             "output_types": [
-              "DataFrame"
+              "Message"
             ]
           },
           "targetHandle": {
-            "fieldName": "input_data",
-            "id": "parser-tsqQI",
+            "fieldName": "input_value",
+            "id": "StructuredOutput-wsAT3",
             "inputTypes": [
-              "DataFrame",
-              "Data"
+              "Message"
             ],
-            "type": "other"
+            "type": "str"
           }
         },
-        "id": "reactflow__edge-StructuredOutput-GJE9p{œdataTypeœ:œStructuredOutputœ,œidœ:œStructuredOutput-GJE9pœ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œDataFrameœ]}-parser-tsqQI{œfieldNameœ:œinput_dataœ,œidœ:œparser-tsqQIœ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}",
+        "id": "xy-edge__File-gVVqw{œdataTypeœ:œFileœ,œidœ:œFile-gVVqwœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-StructuredOutput-wsAT3{œfieldNameœ:œinput_valueœ,œidœ:œStructuredOutput-wsAT3œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "StructuredOutput-GJE9p",
-        "sourceHandle": "{œdataTypeœ: œStructuredOutputœ, œidœ: œStructuredOutput-GJE9pœ, œnameœ: œdataframe_outputœ, œoutput_typesœ: [œDataFrameœ]}",
-        "target": "parser-tsqQI",
-        "targetHandle": "{œfieldNameœ: œinput_dataœ, œidœ: œparser-tsqQIœ, œinputTypesœ: [œDataFrameœ, œDataœ], œtypeœ: œotherœ}"
+        "source": "File-gVVqw",
+        "sourceHandle": "{œdataTypeœ: œFileœ, œidœ: œFile-gVVqwœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "StructuredOutput-wsAT3",
+        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œStructuredOutput-wsAT3œ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
         "className": "",
         "data": {
           "sourceHandle": {
-            "dataType": "File",
-            "id": "File-Ln2gO",
-            "name": "message",
+            "dataType": "StructuredOutput",
+            "id": "StructuredOutput-wsAT3",
+            "name": "dataframe_output",
             "output_types": [
-              "Message"
+              "DataFrame"
             ]
           },
           "targetHandle": {
-            "fieldName": "input_value",
-            "id": "StructuredOutput-GJE9p",
+            "fieldName": "input_data",
+            "id": "parser-6caGE",
             "inputTypes": [
-              "Message"
+              "DataFrame",
+              "Data"
             ],
-            "type": "str"
+            "type": "other"
           }
         },
-        "id": "reactflow__edge-File-Ln2gO{œdataTypeœ:œFileœ,œidœ:œFile-Ln2gOœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-StructuredOutput-GJE9p{œfieldNameœ:œinput_valueœ,œidœ:œStructuredOutput-GJE9pœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "id": "xy-edge__StructuredOutput-wsAT3{œdataTypeœ:œStructuredOutputœ,œidœ:œStructuredOutput-wsAT3œ,œnameœ:œdataframe_outputœ,œoutput_typesœ:[œDataFrameœ]}-parser-6caGE{œfieldNameœ:œinput_dataœ,œidœ:œparser-6caGEœ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}",
         "selected": false,
-        "source": "File-Ln2gO",
-        "sourceHandle": "{œdataTypeœ: œFileœ, œidœ: œFile-Ln2gOœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "StructuredOutput-GJE9p",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œStructuredOutput-GJE9pœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "source": "StructuredOutput-wsAT3",
+        "sourceHandle": "{œdataTypeœ: œStructuredOutputœ, œidœ: œStructuredOutput-wsAT3œ, œnameœ: œdataframe_outputœ, œoutput_typesœ: [œDataFrameœ]}",
+        "target": "parser-6caGE",
+        "targetHandle": "{œfieldNameœ: œinput_dataœ, œidœ: œparser-6caGEœ, œinputTypesœ: [œDataFrameœ, œDataœ], œtypeœ: œotherœ}"
       }
     ],
     "nodes": [
       {
         "data": {
-          "id": "TextInput-y6Hxj",
+          "id": "TextInput-fQKUN",
           "node": {
             "base_classes": [
               "Message"
@@ -254,7 +254,7 @@
           "type": "TextInput"
         },
         "dragging": false,
-        "id": "TextInput-y6Hxj",
+        "id": "TextInput-fQKUN",
         "measured": {
           "height": 204,
           "width": 320
@@ -268,7 +268,7 @@
       },
       {
         "data": {
-          "id": "ChatOutput-KnHDm",
+          "id": "ChatOutput-q991L",
           "node": {
             "base_classes": [
               "Message"
@@ -541,7 +541,7 @@
           "type": "ChatOutput"
         },
         "dragging": false,
-        "id": "ChatOutput-KnHDm",
+        "id": "ChatOutput-q991L",
         "measured": {
           "height": 48,
           "width": 192
@@ -555,7 +555,7 @@
       },
       {
         "data": {
-          "id": "note-MZGLD",
+          "id": "note-N5ILW",
           "node": {
             "description": "### 💡 Upload your resume here",
             "display_name": "",
@@ -568,7 +568,7 @@
         },
         "dragging": false,
         "height": 358,
-        "id": "note-MZGLD",
+        "id": "note-N5ILW",
         "measured": {
           "height": 358,
           "width": 346
@@ -584,7 +584,7 @@
       },
       {
         "data": {
-          "id": "note-8Zjd4",
+          "id": "note-bCQJm",
           "node": {
             "description": "## 📝 Portfolio Website Code Generator\n\nYour uploaded resume is parsed into a structured format, and output as HTML/CSS code for your own resume website!\n\n✅ **Accepted Formats:** PDF or TXT  \n✅ To ensure readability, provide clear headings, bullet points, and proper formatting. \n### 📌 Structured output fields:\n1. 🏷 **Full Name** - Candidate's full name  \n2. 📧 **Email** - A valid email address  \n3. 📞 **Phone Number** - Contact number  \n4. 🔗 **LinkedIn** - LinkedIn profile URL  \n5. 🖥 **GitHub** - GitHub profile URL (if applicable)  \n6. 🌐 **Portfolio** - Personal website or portfolio URL  \n7. 🛂 **Visa Status** - Work authorization details (if applicable)  \n8. 📝 **Summary** - A brief professional summary or objective statement  \n9. 💼 **Experience** - Work experience details (in dictionary format)  \n10. 🎓 **Education** - Education details (in dictionary format)  \n11. 🛠 **Skills** - Skills mentioned in the resume (comma-separated)  \n12. 🚀 **Projects** - Titles, descriptions, and details of projects.",
             "display_name": "",
@@ -595,7 +595,7 @@
         },
         "dragging": false,
         "height": 621,
-        "id": "note-8Zjd4",
+        "id": "note-bCQJm",
         "measured": {
           "height": 621,
           "width": 478
@@ -611,7 +611,7 @@
       },
       {
         "data": {
-          "id": "note-7jRmc",
+          "id": "note-wJ9Jw",
           "node": {
             "description": "### 💡 Click **Open table** to view the schema",
             "display_name": "",
@@ -624,7 +624,7 @@
         },
         "dragging": false,
         "height": 438,
-        "id": "note-7jRmc",
+        "id": "note-wJ9Jw",
         "measured": {
           "height": 438,
           "width": 359
@@ -640,7 +640,7 @@
       },
       {
         "data": {
-          "id": "note-PLSHf",
+          "id": "note-1mSYT",
           "node": {
             "description": "### 💡 Add your OpenAI API key here",
             "display_name": "",
@@ -653,7 +653,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-PLSHf",
+        "id": "note-1mSYT",
         "measured": {
           "height": 324,
           "width": 362
@@ -669,7 +669,7 @@
       },
       {
         "data": {
-          "id": "note-2qzrm",
+          "id": "note-tzsYo",
           "node": {
             "description": "### 💡 Add your Anthropic API key here",
             "display_name": "",
@@ -682,7 +682,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-2qzrm",
+        "id": "note-tzsYo",
         "measured": {
           "height": 324,
           "width": 344
@@ -698,7 +698,7 @@
       },
       {
         "data": {
-          "id": "parser-tsqQI",
+          "id": "parser-6caGE",
           "node": {
             "base_classes": [
               "Message"
@@ -860,7 +860,7 @@
           "type": "parser"
         },
         "dragging": false,
-        "id": "parser-tsqQI",
+        "id": "parser-6caGE",
         "measured": {
           "height": 278,
           "width": 320
@@ -874,53 +874,58 @@
       },
       {
         "data": {
-          "id": "LanguageModelComponent-kiTPL",
+          "id": "File-gVVqw",
           "node": {
             "base_classes": [
-              "LanguageModel",
               "Message"
             ],
             "beta": false,
             "conditional_paths": [],
             "custom_fields": {},
-            "description": "Runs a language model given a specified provider.",
-            "display_name": "Language Model",
-            "documentation": "https://docs.langflow.org/components-models",
+            "description": "Loads and returns the content from uploaded files.",
+            "display_name": "File",
+            "documentation": "",
             "edited": false,
             "field_order": [
-              "model",
-              "api_key",
-              "base_url_ibm_watsonx",
-              "project_id",
-              "ollama_base_url",
-              "input_value",
-              "system_message",
-              "stream",
-              "temperature"
+              "path",
+              "file_path",
+              "separator",
+              "silent_errors",
+              "delete_server_file_after_processing",
+              "ignore_unsupported_extensions",
+              "ignore_unspecified_files",
+              "use_multithreading",
+              "concurrency_multithreading"
             ],
             "frozen": false,
-            "icon": "brain-circuit",
-            "last_updated": "2025-12-20T16:49:42.272Z",
+            "icon": "file-text",
+            "last_updated": "2025-09-29T16:08:14.225Z",
             "legacy": false,
-            "lf_version": "1.7.0",
+            "lf_version": "1.6.0",
             "metadata": {
-              "code_hash": "7fe3257f2169",
+              "code_hash": "5008cc086d7f",
               "dependencies": {
                 "dependencies": [
                   {
                     "name": "lfx",
                     "version": null
+                  },
+                  {
+                    "name": "langchain_core",
+                    "version": "0.3.80"
+                  },
+                  {
+                    "name": "pydantic",
+                    "version": "2.11.10"
+                  },
+                  {
+                    "name": "googleapiclient",
+                    "version": "2.154.0"
                   }
                 ],
-                "total_dependencies": 1
+                "total_dependencies": 4
               },
-              "keywords": [
-                "model",
-                "llm",
-                "language model",
-                "large language model"
-              ],
-              "module": "lfx.components.models_and_agents.language_model.LanguageModelComponent"
+              "module": "lfx.components.files_and_knowledge.file.FileComponent"
             },
             "minimized": false,
             "output_types": [],
@@ -928,101 +933,119 @@
               {
                 "allows_loop": false,
                 "cache": true,
-                "display_name": "Model Response",
+                "display_name": "Raw Content",
                 "group_outputs": false,
-                "hidden": null,
-                "loop_types": null,
-                "method": "text_response",
-                "name": "text_output",
-                "options": null,
-                "required_inputs": null,
+                "method": "load_files_message",
+                "name": "message",
                 "selected": "Message",
                 "tool_mode": true,
                 "types": [
                   "Message"
                 ],
                 "value": "__UNDEFINED__"
-              },
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Language Model",
-                "group_outputs": false,
-                "hidden": null,
-                "loop_types": null,
-                "method": "build_model",
-                "name": "model_output",
-                "options": null,
-                "required_inputs": null,
-                "selected": "LanguageModel",
-                "tool_mode": true,
-                "types": [
-                  "LanguageModel"
-                ],
-                "value": "__UNDEFINED__"
               }
             ],
             "pinned": false,
-            "priority": 0,
             "template": {
-              "_frontend_node_flow_id": {
-                "value": "89c8132e-a746-460b-b091-24b7b9279147"
-              },
-              "_frontend_node_folder_id": {
-                "value": "34260300-cae1-43f3-8b14-1272b8cffe4c"
-              },
               "_type": "Component",
-              "api_key": {
+              "advanced_mode": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Advanced Parser",
+                "dynamic": false,
+                "info": "Enable advanced document processing and export with Docling for PDFs, images, and office documents. Note that advanced document processing can consume significant resources.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "advanced_mode",
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              },
+              "aws_access_key_id": {
                 "_input_type": "SecretStrInput",
-                "advanced": true,
-                "display_name": "API Key",
+                "advanced": false,
+                "display_name": "AWS Access Key ID",
                 "dynamic": false,
-                "info": "Model Provider API key",
+                "info": "AWS Access key ID.",
                 "input_types": [],
-                "load_from_db": false,
-                "name": "api_key",
+                "load_from_db": true,
+                "name": "aws_access_key_id",
                 "override_skip": false,
                 "password": true,
                 "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": true,
+                "required": true,
+                "show": false,
                 "title_case": false,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "base_url_ibm_watsonx": {
-                "_input_type": "DropdownInput",
+              "aws_region": {
+                "_input_type": "StrInput",
                 "advanced": false,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "watsonx API Endpoint",
+                "display_name": "AWS Region",
                 "dynamic": false,
-                "external_options": {},
-                "info": "The base URL of the API (IBM watsonx.ai only)",
-                "name": "base_url_ibm_watsonx",
-                "options": [
-                  "https://us-south.ml.cloud.ibm.com",
-                  "https://eu-de.ml.cloud.ibm.com",
-                  "https://eu-gb.ml.cloud.ibm.com",
-                  "https://au-syd.ml.cloud.ibm.com",
-                  "https://jp-tok.ml.cloud.ibm.com",
-                  "https://ca-tor.ml.cloud.ibm.com"
-                ],
-                "options_metadata": [],
+                "info": "AWS region (e.g., us-east-1, eu-west-1).",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "aws_region",
                 "override_skip": false,
                 "placeholder": "",
-                "real_time_refresh": true,
                 "required": false,
                 "show": false,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
+                "track_in_telemetry": false,
                 "type": "str",
-                "value": "https://us-south.ml.cloud.ibm.com"
+                "value": ""
+              },
+              "aws_secret_access_key": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "AWS Secret Key",
+                "dynamic": false,
+                "info": "AWS Secret Key.",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "aws_secret_access_key",
+                "override_skip": false,
+                "password": true,
+                "placeholder": "",
+                "required": true,
+                "show": false,
+                "title_case": false,
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
+              },
+              "bucket_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "S3 Bucket Name",
+                "dynamic": false,
+                "info": "Enter the name of the S3 bucket.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "bucket_name",
+                "override_skip": false,
+                "placeholder": "",
+                "required": true,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
               },
               "code": {
                 "advanced": true,
@@ -1040,1043 +1063,349 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        return update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\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 contextlib\nimport json\nimport subprocess\nimport sys\nimport textwrap\nfrom copy import deepcopy\nfrom pathlib import Path\nfrom tempfile import NamedTemporaryFile\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.storage_utils import parse_storage_path, read_file_bytes, validate_image_content_type\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom lfx.inputs import SortableListInput\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output, SecretStrInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame  # noqa: TC001\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_settings_service, get_storage_service\nfrom lfx.utils.async_helpers import run_until_complete\nfrom lfx.utils.validate_cloud import is_astra_cloud_environment\n\n\ndef _get_storage_location_options():\n    \"\"\"Get storage location options, filtering out Local if in Astra cloud environment.\"\"\"\n    all_options = [{\"name\": \"AWS\", \"icon\": \"Amazon\"}, {\"name\": \"Google Drive\", \"icon\": \"google\"}]\n    if is_astra_cloud_environment():\n        return all_options\n    return [{\"name\": \"Local\", \"icon\": \"hard-drive\"}, *all_options]\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n    display_name = \"Read File\"\n    # description is now a dynamic property - see get_tool_description()\n    _base_description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/read-file\"\n    icon = \"file-text\"\n    name = \"File\"\n    add_tool_output = True  # Enable tool mode toggle without requiring tool_mode inputs\n\n    # Extensions that can be processed without Docling (using standard text parsing)\n    TEXT_EXTENSIONS = TEXT_FILE_TYPES\n\n    # Extensions that require Docling for processing (images, advanced office formats, etc.)\n    DOCLING_ONLY_EXTENSIONS = [\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"jpg\",\n        \"jpeg\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"webp\",\n    ]\n\n    # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n    VALID_EXTENSIONS = [\n        *TEXT_EXTENSIONS,\n        *DOCLING_ONLY_EXTENSIONS,\n    ]\n\n    # Fixed export settings used when markdown export is requested.\n    EXPORT_FORMAT = \"Markdown\"\n    IMAGE_MODE = \"placeholder\"\n\n    _base_inputs = deepcopy(BaseFileComponent.get_base_inputs())\n\n    for input_item in _base_inputs:\n        if isinstance(input_item, FileInput) and input_item.name == \"path\":\n            input_item.real_time_refresh = True\n            input_item.tool_mode = False  # Disable tool mode for file upload input\n            input_item.required = False  # Make it optional so it doesn't error in tool mode\n            break\n\n    inputs = [\n        SortableListInput(\n            name=\"storage_location\",\n            display_name=\"Storage Location\",\n            placeholder=\"Select Location\",\n            info=\"Choose where to read the file from.\",\n            options=_get_storage_location_options(),\n            real_time_refresh=True,\n            limit=1,\n        ),\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,  # Required for Toolset toggle, but _get_tools() ignores this parameter\n            required=False,\n        ),\n        # AWS S3 specific inputs\n        SecretStrInput(\n            name=\"aws_access_key_id\",\n            display_name=\"AWS Access Key ID\",\n            info=\"AWS Access key ID.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"aws_secret_access_key\",\n            display_name=\"AWS Secret Key\",\n            info=\"AWS Secret Key.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"bucket_name\",\n            display_name=\"S3 Bucket Name\",\n            info=\"Enter the name of the S3 bucket.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"aws_region\",\n            display_name=\"AWS Region\",\n            info=\"AWS region (e.g., us-east-1, eu-west-1).\",\n            show=False,\n            advanced=False,\n        ),\n        StrInput(\n            name=\"s3_file_key\",\n            display_name=\"S3 File Key\",\n            info=\"The key (path) of the file in S3 bucket.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        # Google Drive specific inputs\n        SecretStrInput(\n            name=\"service_account_key\",\n            display_name=\"GCP Credentials Secret Key\",\n            info=\"Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"file_id\",\n            display_name=\"Google Drive File ID\",\n            info=(\"The Google Drive file ID to read. The file must be shared with the service account email.\"),\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        BoolInput(\n            name=\"advanced_mode\",\n            display_name=\"Advanced Parser\",\n            value=False,\n            real_time_refresh=True,\n            info=(\n                \"Enable advanced document processing and export with Docling for PDFs, images, and office documents. \"\n                \"Note that advanced document processing can consume significant resources.\"\n            ),\n            # Disabled in cloud\n            show=not is_astra_cloud_environment(),\n        ),\n        DropdownInput(\n            name=\"pipeline\",\n            display_name=\"Pipeline\",\n            info=\"Docling pipeline to use\",\n            options=[\"standard\", \"vlm\"],\n            value=\"standard\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"ocr_engine\",\n            display_name=\"OCR Engine\",\n            info=\"OCR engine to use. Only available when pipeline is set to 'standard'.\",\n            options=[\"None\", \"easyocr\"],\n            value=\"easyocr\",\n            show=False,\n            advanced=True,\n        ),\n        StrInput(\n            name=\"md_image_placeholder\",\n            display_name=\"Image placeholder\",\n            info=\"Specify the image placeholder for markdown exports.\",\n            value=\"<!-- image -->\",\n            advanced=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"md_page_break_placeholder\",\n            display_name=\"Page break placeholder\",\n            info=\"Add this placeholder between pages in the markdown output.\",\n            value=\"\",\n            advanced=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"doc_key\",\n            display_name=\"Doc Key\",\n            info=\"The key to use for the DoclingDocument column.\",\n            value=\"doc\",\n            advanced=True,\n            show=False,\n        ),\n        # Deprecated input retained for backward-compatibility.\n        BoolInput(\n            name=\"use_multithreading\",\n            display_name=\"[Deprecated] Use Multithreading\",\n            advanced=True,\n            value=True,\n            info=\"Set 'Processing Concurrency' greater than 1 to enable multithreading.\",\n        ),\n        IntInput(\n            name=\"concurrency_multithreading\",\n            display_name=\"Processing Concurrency\",\n            advanced=True,\n            info=\"When multiple files are being processed, the number of files to process concurrently.\",\n            value=1,\n        ),\n        BoolInput(\n            name=\"markdown\",\n            display_name=\"Markdown Export\",\n            info=\"Export processed documents to Markdown format. Only available when advanced mode is enabled.\",\n            value=False,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\", tool_mode=True),\n    ]\n\n    # ------------------------------ Tool description with file names --------------\n\n    def get_tool_description(self) -> str:\n        \"\"\"Return a dynamic description that includes the names of uploaded files.\n\n        This helps the Agent understand which files are available to read.\n        \"\"\"\n        base_description = \"Loads and returns the content from uploaded files.\"\n\n        # Get the list of uploaded file paths\n        file_paths = getattr(self, \"path\", None)\n        if not file_paths:\n            return base_description\n\n        # Ensure it's a list\n        if not isinstance(file_paths, list):\n            file_paths = [file_paths]\n\n        # Extract just the file names from the paths\n        file_names = []\n        for fp in file_paths:\n            if fp:\n                name = Path(fp).name\n                file_names.append(name)\n\n        if file_names:\n            files_str = \", \".join(file_names)\n            return f\"{base_description} Available files: {files_str}. Call this tool to read these files.\"\n\n        return base_description\n\n    @property\n    def description(self) -> str:\n        \"\"\"Dynamic description property that includes uploaded file names.\"\"\"\n        return self.get_tool_description()\n\n    async def _get_tools(self) -> list:\n        \"\"\"Override to create a tool without parameters.\n\n        The Read File component should use the files already uploaded via UI,\n        not accept file paths from the Agent (which wouldn't know the internal paths).\n        \"\"\"\n        from langchain_core.tools import StructuredTool\n        from pydantic import BaseModel\n\n        # Empty schema - no parameters needed\n        class EmptySchema(BaseModel):\n            \"\"\"No parameters required - uses pre-uploaded files.\"\"\"\n\n        async def read_files_tool() -> str:\n            \"\"\"Read the content of uploaded files.\"\"\"\n            try:\n                result = self.load_files_message()\n                if hasattr(result, \"get_text\"):\n                    return result.get_text()\n                if hasattr(result, \"text\"):\n                    return result.text\n                return str(result)\n            except (FileNotFoundError, ValueError, OSError, RuntimeError) as e:\n                return f\"Error reading files: {e}\"\n\n        description = self.get_tool_description()\n\n        tool = StructuredTool(\n            name=\"load_files_message\",\n            description=description,\n            coroutine=read_files_tool,\n            args_schema=EmptySchema,\n            handle_tool_error=True,\n            tags=[\"load_files_message\"],\n            metadata={\n                \"display_name\": \"Read File\",\n                \"display_description\": description,\n            },\n        )\n\n        return [tool]\n\n    # ------------------------------ UI helpers --------------------------------------\n\n    def _path_value(self, template: dict) -> list[str]:\n        \"\"\"Return the list of currently selected file paths from the template.\"\"\"\n        return template.get(\"path\", {}).get(\"file_path\", [])\n\n    def _disable_docling_fields_in_cloud(self, build_config: dict[str, Any]) -> None:\n        \"\"\"Disable all Docling-related fields in cloud environments.\"\"\"\n        if \"advanced_mode\" in build_config:\n            build_config[\"advanced_mode\"][\"show\"] = False\n            build_config[\"advanced_mode\"][\"value\"] = False\n        # Hide all Docling-related fields\n        docling_fields = (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\")\n        for field in docling_fields:\n            if field in build_config:\n                build_config[field][\"show\"] = False\n        # Also disable OCR engine specifically\n        if \"ocr_engine\" in build_config:\n            build_config[\"ocr_engine\"][\"value\"] = \"None\"\n\n    def update_build_config(\n        self,\n        build_config: dict[str, Any],\n        field_value: Any,\n        field_name: str | None = None,\n    ) -> dict[str, Any]:\n        \"\"\"Show/hide Advanced Parser and related fields based on selection context.\"\"\"\n        # Update storage location options dynamically based on cloud environment\n        if \"storage_location\" in build_config:\n            updated_options = _get_storage_location_options()\n            build_config[\"storage_location\"][\"options\"] = updated_options\n\n        # Handle storage location selection\n        if field_name == \"storage_location\":\n            # Extract selected storage location\n            selected = [location[\"name\"] for location in field_value] if isinstance(field_value, list) else []\n\n            # Hide all storage-specific fields first\n            storage_fields = [\n                \"aws_access_key_id\",\n                \"aws_secret_access_key\",\n                \"bucket_name\",\n                \"aws_region\",\n                \"s3_file_key\",\n                \"service_account_key\",\n                \"file_id\",\n            ]\n\n            for f_name in storage_fields:\n                if f_name in build_config:\n                    build_config[f_name][\"show\"] = False\n\n            # Show fields based on selected storage location\n            if len(selected) == 1:\n                location = selected[0]\n\n                if location == \"Local\":\n                    # Show file upload input for local storage\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = True\n\n                elif location == \"AWS\":\n                    # Hide file upload input, show AWS fields\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = False\n\n                    aws_fields = [\n                        \"aws_access_key_id\",\n                        \"aws_secret_access_key\",\n                        \"bucket_name\",\n                        \"aws_region\",\n                        \"s3_file_key\",\n                    ]\n                    for f_name in aws_fields:\n                        if f_name in build_config:\n                            build_config[f_name][\"show\"] = True\n                            build_config[f_name][\"advanced\"] = False\n\n                elif location == \"Google Drive\":\n                    # Hide file upload input, show Google Drive fields\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = False\n\n                    gdrive_fields = [\"service_account_key\", \"file_id\"]\n                    for f_name in gdrive_fields:\n                        if f_name in build_config:\n                            build_config[f_name][\"show\"] = True\n                            build_config[f_name][\"advanced\"] = False\n            # No storage location selected - show file upload by default\n            elif \"path\" in build_config:\n                build_config[\"path\"][\"show\"] = True\n\n            return build_config\n\n        if field_name == \"path\":\n            paths = self._path_value(build_config)\n\n            # Disable in cloud environments\n            if is_astra_cloud_environment():\n                self._disable_docling_fields_in_cloud(build_config)\n            else:\n                # If all files can be processed by docling, do so\n                allow_advanced = all(not file_path.endswith((\".csv\", \".xlsx\", \".parquet\")) for file_path in paths)\n                build_config[\"advanced_mode\"][\"show\"] = allow_advanced\n                if not allow_advanced:\n                    build_config[\"advanced_mode\"][\"value\"] = False\n                    docling_fields = (\n                        \"pipeline\",\n                        \"ocr_engine\",\n                        \"doc_key\",\n                        \"md_image_placeholder\",\n                        \"md_page_break_placeholder\",\n                    )\n                    for field in docling_fields:\n                        if field in build_config:\n                            build_config[field][\"show\"] = False\n\n        # Docling Processing\n        elif field_name == \"advanced_mode\":\n            # Disable in cloud environments - don't show Docling fields even if advanced_mode is toggled\n            if is_astra_cloud_environment():\n                self._disable_docling_fields_in_cloud(build_config)\n            else:\n                docling_fields = (\n                    \"pipeline\",\n                    \"ocr_engine\",\n                    \"doc_key\",\n                    \"md_image_placeholder\",\n                    \"md_page_break_placeholder\",\n                )\n                for field in docling_fields:\n                    if field in build_config:\n                        build_config[field][\"show\"] = bool(field_value)\n                        if field == \"pipeline\":\n                            build_config[field][\"advanced\"] = not bool(field_value)\n\n        elif field_name == \"pipeline\":\n            # Disable in cloud environments - don't show OCR engine even if pipeline is changed\n            if is_astra_cloud_environment():\n                self._disable_docling_fields_in_cloud(build_config)\n            elif field_value == \"standard\":\n                build_config[\"ocr_engine\"][\"show\"] = True\n                build_config[\"ocr_engine\"][\"value\"] = \"easyocr\"\n            else:\n                build_config[\"ocr_engine\"][\"show\"] = False\n                build_config[\"ocr_engine\"][\"value\"] = \"None\"\n\n        return build_config\n\n    def update_outputs(self, frontend_node: dict[str, Any], field_name: str, field_value: Any) -> dict[str, Any]:  # noqa: ARG002\n        \"\"\"Dynamically show outputs based on file count/type and advanced mode.\"\"\"\n        if field_name not in [\"path\", \"advanced_mode\", \"pipeline\"]:\n            return frontend_node\n\n        template = frontend_node.get(\"template\", {})\n        paths = self._path_value(template)\n        if not paths:\n            return frontend_node\n\n        frontend_node[\"outputs\"] = []\n        if len(paths) == 1:\n            file_path = paths[0] if field_name == \"path\" else frontend_node[\"template\"][\"path\"][\"file_path\"][0]\n            if file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n                frontend_node[\"outputs\"].append(\n                    Output(\n                        display_name=\"Structured Content\",\n                        name=\"dataframe\",\n                        method=\"load_files_structured\",\n                        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 _get_selected_storage_location(self) -> str:\n        \"\"\"Get the selected storage location from the SortableListInput.\"\"\"\n        if hasattr(self, \"storage_location\") and self.storage_location:\n            if isinstance(self.storage_location, list) and len(self.storage_location) > 0:\n                return self.storage_location[0].get(\"name\", \"\")\n            if isinstance(self.storage_location, dict):\n                return self.storage_location.get(\"name\", \"\")\n        return \"Local\"  # Default to Local if not specified\n\n    def _validate_and_resolve_paths(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Override to handle file_path_str input from tool mode and cloud storage.\n\n        Priority:\n        1. Cloud storage (AWS/Google Drive) if selected\n        2. file_path_str (if provided by the tool call)\n        3. path (uploaded file from UI)\n        \"\"\"\n        storage_location = self._get_selected_storage_location()\n\n        # Handle AWS S3\n        if storage_location == \"AWS\":\n            return self._read_from_aws_s3()\n\n        # Handle Google Drive\n        if storage_location == \"Google Drive\":\n            return self._read_from_google_drive()\n\n        # Handle Local storage\n        # Check if file_path_str is provided (from tool mode)\n        file_path_str = getattr(self, \"file_path_str\", None)\n        if file_path_str:\n            # Use the string path from tool mode\n            from pathlib import Path\n\n            from lfx.schema.data import Data\n\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 _read_from_aws_s3(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Read file from AWS S3.\"\"\"\n        from lfx.base.data.cloud_storage_utils import create_s3_client, validate_aws_credentials\n\n        # Validate AWS credentials\n        validate_aws_credentials(self)\n        if not getattr(self, \"s3_file_key\", None):\n            msg = \"S3 File Key is required\"\n            raise ValueError(msg)\n\n        # Create S3 client\n        s3_client = create_s3_client(self)\n\n        # Download file to temp location\n        import tempfile\n\n        # Get file extension from S3 key\n        file_extension = Path(self.s3_file_key).suffix or \"\"\n\n        with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n            temp_file_path = temp_file.name\n            try:\n                s3_client.download_fileobj(self.bucket_name, self.s3_file_key, temp_file)\n            except Exception as e:\n                # Clean up temp file on failure\n                with contextlib.suppress(OSError):\n                    Path(temp_file_path).unlink()\n                msg = f\"Failed to download file from S3: {e}\"\n                raise RuntimeError(msg) from e\n\n        # Create BaseFile object\n        from lfx.schema.data import Data\n\n        temp_path = Path(temp_file_path)\n        data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n        return [BaseFileComponent.BaseFile(data_obj, temp_path, delete_after_processing=True)]\n\n    def _read_from_google_drive(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Read file from Google Drive.\"\"\"\n        import tempfile\n\n        from googleapiclient.http import MediaIoBaseDownload\n\n        from lfx.base.data.cloud_storage_utils import create_google_drive_service\n\n        # Validate Google Drive credentials\n        if not getattr(self, \"service_account_key\", None):\n            msg = \"GCP Credentials Secret Key is required for Google Drive storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"file_id\", None):\n            msg = \"Google Drive File ID is required\"\n            raise ValueError(msg)\n\n        # Create Google Drive service with read-only scope\n        drive_service = create_google_drive_service(\n            self.service_account_key, scopes=[\"https://www.googleapis.com/auth/drive.readonly\"]\n        )\n\n        # Get file metadata to determine file name and extension\n        try:\n            file_metadata = drive_service.files().get(fileId=self.file_id, fields=\"name,mimeType\").execute()\n            file_name = file_metadata.get(\"name\", \"download\")\n        except Exception as e:\n            msg = (\n                f\"Unable to access file with ID '{self.file_id}'. \"\n                f\"Error: {e!s}. \"\n                \"Please ensure: 1) The file ID is correct, 2) The file exists, \"\n                \"3) The service account has been granted access to this file.\"\n            )\n            raise ValueError(msg) from e\n\n        # Download file to temp location\n        file_extension = Path(file_name).suffix or \"\"\n        with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n            temp_file_path = temp_file.name\n            try:\n                request = drive_service.files().get_media(fileId=self.file_id)\n                downloader = MediaIoBaseDownload(temp_file, request)\n                done = False\n                while not done:\n                    _status, done = downloader.next_chunk()\n            except Exception as e:\n                # Clean up temp file on failure\n                with contextlib.suppress(OSError):\n                    Path(temp_file_path).unlink()\n                msg = f\"Failed to download file from Google Drive: {e}\"\n                raise RuntimeError(msg) from e\n\n        # Create BaseFile object\n        from lfx.schema.data import Data\n\n        temp_path = Path(temp_file_path)\n        data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n        return [BaseFileComponent.BaseFile(data_obj, temp_path, delete_after_processing=True)]\n\n    def _is_docling_compatible(self, file_path: str) -> bool:\n        \"\"\"Lightweight extension gate for Docling-compatible types.\"\"\"\n        docling_exts = (\n            \".adoc\",\n            \".asciidoc\",\n            \".asc\",\n            \".bmp\",\n            \".csv\",\n            \".dotx\",\n            \".dotm\",\n            \".docm\",\n            \".docx\",\n            \".htm\",\n            \".html\",\n            \".jpg\",\n            \".jpeg\",\n            \".json\",\n            \".md\",\n            \".pdf\",\n            \".png\",\n            \".potx\",\n            \".ppsx\",\n            \".pptm\",\n            \".potm\",\n            \".ppsm\",\n            \".pptx\",\n            \".tiff\",\n            \".txt\",\n            \".xls\",\n            \".xlsx\",\n            \".xhtml\",\n            \".xml\",\n            \".webp\",\n        )\n        return file_path.lower().endswith(docling_exts)\n\n    async def _get_local_file_for_docling(self, file_path: str) -> tuple[str, bool]:\n        \"\"\"Get a local file path for Docling processing, downloading from S3 if needed.\n\n        Args:\n            file_path: Either a local path or S3 key (format \"flow_id/filename\")\n\n        Returns:\n            tuple[str, bool]: (local_path, should_delete) where should_delete indicates\n                              if this is a temporary file that should be cleaned up\n        \"\"\"\n        settings = get_settings_service().settings\n        if settings.storage_type == \"local\":\n            return file_path, False\n\n        # S3 storage - download to temp file\n        parsed = parse_storage_path(file_path)\n        if not parsed:\n            msg = f\"Invalid S3 path format: {file_path}. Expected 'flow_id/filename'\"\n            raise ValueError(msg)\n\n        storage_service = get_storage_service()\n        flow_id, filename = parsed\n\n        # Get file content from S3\n        content = await storage_service.get_file(flow_id, filename)\n\n        suffix = Path(filename).suffix\n        with NamedTemporaryFile(mode=\"wb\", suffix=suffix, delete=False) as tmp_file:\n            tmp_file.write(content)\n            temp_path = tmp_file.name\n\n        return temp_path, True\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        For S3 storage, the file is downloaded to a temp file first.\n        \"\"\"\n        if not file_path:\n            return None\n\n        settings = get_settings_service().settings\n        if settings.storage_type == \"s3\":\n            local_path, should_delete = run_until_complete(self._get_local_file_for_docling(file_path))\n        else:\n            local_path = file_path\n            should_delete = False\n\n        try:\n            return self._process_docling_subprocess_impl(local_path, file_path)\n        finally:\n            # Clean up temp file if we created one\n            if should_delete:\n                with contextlib.suppress(Exception):\n                    Path(local_path).unlink()  # Ignore cleanup errors\n\n    def _process_docling_subprocess_impl(self, local_file_path: str, original_file_path: str) -> Data | None:\n        \"\"\"Implementation of Docling subprocess processing.\n\n        Args:\n            local_file_path: Path to local file to process\n            original_file_path: Original file path to include in metadata\n        Returns:\n            Data object with processed content\n        \"\"\"\n        args: dict[str, Any] = {\n            \"file_path\": local_file_path,\n            \"markdown\": bool(self.markdown),\n            \"image_mode\": str(self.IMAGE_MODE),\n            \"md_image_placeholder\": str(self.md_image_placeholder),\n            \"md_page_break_placeholder\": str(self.md_page_break_placeholder),\n            \"pipeline\": str(self.pipeline),\n            \"ocr_engine\": (\n                self.ocr_engine if self.ocr_engine and self.ocr_engine != \"None\" and self.pipeline != \"vlm\" else None\n            ),\n        }\n\n        # Child script for isolating the docling processing\n        child_script = textwrap.dedent(\n            r\"\"\"\n            import json, sys\n\n            def try_imports():\n                try:\n                    from docling.datamodel.base_models import ConversionStatus, InputFormat  # type: ignore\n                    from docling.document_converter import DocumentConverter  # type: ignore\n                    from docling_core.types.doc import ImageRefMode  # type: ignore\n                    return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"latest\"\n                except Exception as e:\n                    raise e\n\n            def create_converter(strategy, input_format, DocumentConverter, pipeline, ocr_engine):\n                # --- Standard PDF/IMAGE pipeline (your existing behavior), with optional OCR ---\n                if pipeline == \"standard\":\n                    try:\n                        from docling.datamodel.pipeline_options import PdfPipelineOptions  # type: ignore\n                        from docling.document_converter import PdfFormatOption  # type: ignore\n\n                        pipe = PdfPipelineOptions()\n                        pipe.do_ocr = False\n\n                        if ocr_engine:\n                            try:\n                                from docling.models.factories import get_ocr_factory  # type: ignore\n                                pipe.do_ocr = True\n                                fac = get_ocr_factory(allow_external_plugins=False)\n                                pipe.ocr_options = fac.create_options(kind=ocr_engine)\n                            except Exception:\n                                # If OCR setup fails, disable it\n                                pipe.do_ocr = False\n\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(pipeline_options=pipe)\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(pipeline_options=pipe)\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception:\n                        return DocumentConverter()\n\n                # --- Vision-Language Model (VLM) pipeline ---\n                if pipeline == \"vlm\":\n                    try:\n                        from docling.datamodel.pipeline_options import VlmPipelineOptions\n                        from docling.datamodel.vlm_model_specs import GRANITEDOCLING_MLX, GRANITEDOCLING_TRANSFORMERS\n                        from docling.document_converter import PdfFormatOption\n                        from docling.pipeline.vlm_pipeline import VlmPipeline\n\n                        vl_pipe = VlmPipelineOptions(\n                            vlm_options=GRANITEDOCLING_TRANSFORMERS,\n                        )\n\n                        if sys.platform == \"darwin\":\n                            try:\n                                import mlx_vlm\n                                vl_pipe.vlm_options = GRANITEDOCLING_MLX\n                            except ImportError as e:\n                                raise e\n\n                        # VLM paths generally don't need OCR; keep OCR off by default here.\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(\n                            pipeline_cls=VlmPipeline,\n                            pipeline_options=vl_pipe\n                        )\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(\n                            pipeline_cls=VlmPipeline,\n                            pipeline_options=vl_pipe\n                        )\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception as e:\n                        raise e\n\n                # --- Fallback: default converter with no special options ---\n                return DocumentConverter()\n\n            def export_markdown(document, ImageRefMode, image_mode, img_ph, pg_ph):\n                try:\n                    mode = getattr(ImageRefMode, image_mode.upper(), image_mode)\n                    return document.export_to_markdown(\n                        image_mode=mode,\n                        image_placeholder=img_ph,\n                        page_break_placeholder=pg_ph,\n                    )\n                except Exception:\n                    try:\n                        return document.export_to_text()\n                    except Exception:\n                        return str(document)\n\n            def to_rows(doc_dict):\n                rows = []\n                for t in doc_dict.get(\"texts\", []):\n                    prov = t.get(\"prov\") or []\n                    page_no = None\n                    if prov and isinstance(prov, list) and isinstance(prov[0], dict):\n                        page_no = prov[0].get(\"page_no\")\n                    rows.append({\n                        \"page_no\": page_no,\n                        \"label\": t.get(\"label\"),\n                        \"text\": t.get(\"text\"),\n                        \"level\": t.get(\"level\"),\n                    })\n                return rows\n\n            def main():\n                cfg = json.loads(sys.stdin.read())\n                file_path = cfg[\"file_path\"]\n                markdown = cfg[\"markdown\"]\n                image_mode = cfg[\"image_mode\"]\n                img_ph = cfg[\"md_image_placeholder\"]\n                pg_ph = cfg[\"md_page_break_placeholder\"]\n                pipeline = cfg[\"pipeline\"]\n                ocr_engine = cfg.get(\"ocr_engine\")\n                meta = {\"file_path\": file_path}\n\n                try:\n                    ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, strategy = try_imports()\n                    converter = create_converter(strategy, InputFormat, DocumentConverter, pipeline, ocr_engine)\n                    try:\n                        res = converter.convert(file_path)\n                    except Exception as e:\n                        print(json.dumps({\"ok\": False, \"error\": f\"Docling conversion error: {e}\", \"meta\": meta}))\n                        return\n\n                    ok = False\n                    if hasattr(res, \"status\"):\n                        try:\n                            ok = (res.status == ConversionStatus.SUCCESS) or (str(res.status).lower() == \"success\")\n                        except Exception:\n                            ok = (str(res.status).lower() == \"success\")\n                    if not ok and hasattr(res, \"document\"):\n                        ok = getattr(res, \"document\", None) is not None\n                    if not ok:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling conversion failed\", \"meta\": meta}))\n                        return\n\n                    doc = getattr(res, \"document\", None)\n                    if doc is None:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling produced no document\", \"meta\": meta}))\n                        return\n\n                    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\") if proc.stderr else \"no output from child process\"\n            return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": original_file_path})\n\n        try:\n            result = json.loads(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={\n                    \"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\",\n                    \"file_path\": original_file_path,\n                },\n            )\n\n        if not result.get(\"ok\"):\n            error_msg = result.get(\"error\", \"Unknown Docling error\")\n            # Override meta file_path with original_file_path to ensure correct path matching\n            meta = result.get(\"meta\", {})\n            meta[\"file_path\"] = original_file_path\n            return Data(data={\"error\": error_msg, **meta})\n\n        meta = result.get(\"meta\", {})\n        # Override meta file_path with original_file_path to ensure correct path matching\n        # The subprocess returns the temp file path, but we need the original S3/local path for rollup_data\n        meta[\"file_path\"] = original_file_path\n        if result.get(\"mode\") == \"markdown\":\n            exported_content = str(result.get(\"text\", \"\"))\n            return Data(\n                text=exported_content,\n                data={\"exported_content\": exported_content, \"export_format\": self.EXPORT_FORMAT, **meta},\n            )\n\n        rows = list(result.get(\"doc\", []))\n        return Data(data={\"doc\": rows, \"export_format\": self.EXPORT_FORMAT, **meta})\n\n    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        # Validate image files to detect content/extension mismatches\n        # This prevents API errors like \"Image does not match the provided media type\"\n        image_extensions = {\"jpeg\", \"jpg\", \"png\", \"gif\", \"webp\", \"bmp\", \"tiff\"}\n        settings = get_settings_service().settings\n        for file in file_list:\n            extension = file.path.suffix[1:].lower()\n            if extension in image_extensions:\n                # Read bytes based on storage type\n                try:\n                    if settings.storage_type == \"s3\":\n                        # For S3 storage, use storage service to read file bytes\n                        file_path_str = str(file.path)\n                        content = run_until_complete(read_file_bytes(file_path_str))\n                    else:\n                        # For local storage, read bytes directly from filesystem\n                        content = file.path.read_bytes()\n\n                    is_valid, error_msg = validate_image_content_type(\n                        str(file.path),\n                        content=content,\n                    )\n                    if not is_valid:\n                        self.log(error_msg)\n                        if not self.silent_errors:\n                            raise ValueError(error_msg)\n                except (OSError, FileNotFoundError) as e:\n                    self.log(f\"Could not read file for validation: {e}\")\n                    # Continue - let it fail later with better error\n\n        # Validate that files requiring Docling are only processed when advanced mode is enabled\n        if not self.advanced_mode:\n            for file in file_list:\n                extension = file.path.suffix[1:].lower()\n                if extension in self.DOCLING_ONLY_EXTENSIONS:\n                    if is_astra_cloud_environment():\n                        msg = (\n                            f\"File '{file.path.name}' has extension '.{extension}' which requires \"\n                            f\"Advanced Parser mode. Advanced Parser is not available in cloud environments.\"\n                        )\n                    else:\n                        msg = (\n                            f\"File '{file.path.name}' has extension '.{extension}' which requires \"\n                            f\"Advanced Parser mode. Please enable 'Advanced Parser' to process this file.\"\n                        )\n                    self.log(msg)\n                    raise ValueError(msg)\n\n        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                # Handle None case - Docling processing failed or returned None\n                if advanced_data is None:\n                    error_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"error\": \"Docling processing returned no result. Check logs for details.\",\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [error_data]))\n                    continue\n\n                # --- UNNEST: expand each element in `doc` to its own Data row\n                payload = getattr(advanced_data, \"data\", {}) or {}\n\n                # Check for errors first\n                if \"error\" in payload:\n                    error_msg = payload.get(\"error\", \"Unknown error\")\n                    error_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"error\": error_msg,\n                            **{k: v for k, v in payload.items() if k not in (\"error\", \"file_path\")},\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [error_data]))\n                    continue\n\n                doc_rows = payload.get(\"doc\")\n                if isinstance(doc_rows, list) and doc_rows:\n                    # Non-empty list of structured rows\n                    rows: list[Data | None] = [\n                        Data(\n                            data={\n                                \"file_path\": file_path,\n                                **(item if isinstance(item, dict) else {\"value\": item}),\n                            },\n                        )\n                        for item in doc_rows\n                    ]\n                    final_return.extend(self.rollup_data([file], rows))\n                elif isinstance(doc_rows, list) and not doc_rows:\n                    # Empty list - file was processed but no text content found\n                    # Create a Data object indicating no content was extracted\n                    self.log(f\"No text extracted from '{file_path}', creating placeholder data\")\n                    empty_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"text\": \"(No text content extracted from image)\",\n                            \"info\": \"Image processed successfully but contained no extractable text\",\n                            **{k: v for k, v in payload.items() if k != \"doc\"},\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [empty_data]))\n                else:\n                    # If not structured, keep as-is (e.g., markdown export or error dict)\n                    # Ensure file_path is set for proper rollup matching\n                    if not payload.get(\"file_path\"):\n                        payload[\"file_path\"] = file_path\n                        # Create new Data with file_path\n                        advanced_data = Data(\n                            data=payload,\n                            text=getattr(advanced_data, \"text\", None),\n                        )\n                    final_return.extend(self.rollup_data([file], [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\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        # Result is a DataFrame - check if it has any rows\n        if result.empty:\n            msg = \"Could not extract content from the provided file(s).\"\n            raise ValueError(msg)\n\n        # Check for error column with error messages\n        if \"error\" in result.columns:\n            errors = result[\"error\"].dropna().tolist()\n            if errors and not any(col in result.columns for col in [\"text\", \"doc\", \"exported_content\"]):\n                raise ValueError(errors[0])\n\n        return result\n\n    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\n        # Result is a DataFrame - check for text or exported_content columns\n        if \"text\" in result.columns and not result[\"text\"].isna().all():\n            text_values = result[\"text\"].dropna().tolist()\n            if text_values:\n                return Message(text=str(text_values[0]))\n\n        if \"exported_content\" in result.columns and not result[\"exported_content\"].isna().all():\n            content_values = result[\"exported_content\"].dropna().tolist()\n            if content_values:\n                return Message(text=str(content_values[0]))\n\n        # Return empty message with info that no text was found\n        return Message(text=\"(No text content extracted from file)\")\n"
               },
-              "input_value": {
-                "_input_type": "MessageInput",
-                "advanced": false,
-                "display_name": "Input",
+              "concurrency_multithreading": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Processing Concurrency",
                 "dynamic": false,
-                "info": "The input text to send to the model",
-                "input_types": [
-                  "Message"
-                ],
+                "info": "When multiple files are being processed, the number of files to process concurrently.",
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "input_value",
-                "override_skip": false,
+                "name": "concurrency_multithreading",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": ""
+                "type": "int",
+                "value": 1
               },
-              "is_refresh": true,
-              "model": {
-                "_input_type": "ModelInput",
-                "advanced": false,
-                "display_name": "Language Model",
+              "delete_server_file_after_processing": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Delete Server File After Processing",
                 "dynamic": false,
-                "external_options": {
-                  "fields": {
-                    "data": {
-                      "node": {
-                        "display_name": "Connect other models",
-                        "icon": "CornerDownLeft",
-                        "name": "connect_other_models"
-                      }
-                    }
-                  }
-                },
-                "info": "Select your model provider",
-                "input_types": [],
+                "info": "If true, the Server File Path will be deleted after processing.",
                 "list": false,
                 "list_add_label": "Add More",
-                "model_type": "language",
-                "name": "model",
-                "options": [
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5"
-                      ]
-                    },
-                    "name": "gpt-5",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5-mini"
-                      ]
-                    },
-                    "name": "gpt-5-mini",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5-nano"
-                      ]
-                    },
-                    "name": "gpt-5-nano",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model"
-                    },
-                    "name": "gpt-4o-mini",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model"
-                    },
-                    "name": "gpt-4o",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "Google Generative AI",
-                    "icon": "GoogleGenerativeAI",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "GOOGLE_API_KEY"
-                    },
-                    "name": "__enable_provider_Google Generative AI__",
-                    "provider": "Google Generative AI"
-                  },
-                  {
-                    "category": "Ollama",
-                    "icon": "Ollama",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "OLLAMA_BASE_URL"
-                    },
-                    "name": "__enable_provider_Ollama__",
-                    "provider": "Ollama"
-                  },
-                  {
-                    "category": "IBM Watsonx",
-                    "icon": "WatsonxAI",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "WATSONX_APIKEY"
-                    },
-                    "name": "__enable_provider_IBM Watsonx__",
-                    "provider": "IBM Watsonx"
-                  }
-                ],
-                "override_skip": false,
-                "placeholder": "Setup Provider",
-                "real_time_refresh": true,
-                "refresh_button": true,
-                "required": true,
+                "name": "delete_server_file_after_processing",
+                "placeholder": "",
+                "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
-                "trace_as_input": true,
-                "track_in_telemetry": false,
-                "type": "model",
-                "value": [
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5"
-                      ]
-                    },
-                    "name": "gpt-5",
-                    "provider": "OpenAI"
-                  }
-                ]
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
               },
-              "ollama_base_url": {
-                "_input_type": "MessageInput",
-                "advanced": false,
-                "display_name": "Ollama API URL",
+              "doc_key": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Doc Key",
                 "dynamic": false,
-                "info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
+                "info": "The key to use for the DoclingDocument column.",
                 "input_types": [
                   "Message"
                 ],
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "ollama_base_url",
-                "override_skip": false,
+                "name": "doc_key",
                 "placeholder": "",
-                "real_time_refresh": true,
                 "required": false,
                 "show": false,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_input": true,
                 "trace_as_metadata": true,
+                "type": "str",
+                "value": "doc"
+              },
+              "file_id": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Google Drive File ID",
+                "dynamic": false,
+                "info": "The Google Drive file ID to read. The file must be shared with the service account email.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "file_id",
+                "override_skip": false,
+                "placeholder": "",
+                "required": true,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "project_id": {
+              "file_path": {
+                "_input_type": "HandleInput",
+                "advanced": true,
+                "display_name": "Server File Path",
+                "dynamic": false,
+                "info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
+                "input_types": [
+                  "Data",
+                  "Message"
+                ],
+                "list": true,
+                "list_add_label": "Add More",
+                "name": "file_path",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "file_path_str": {
                 "_input_type": "StrInput",
-                "advanced": false,
-                "display_name": "watsonx Project ID",
+                "advanced": true,
+                "display_name": "File Path",
                 "dynamic": false,
-                "info": "The project ID associated with the foundation model (IBM watsonx.ai only)",
+                "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": "project_id",
+                "name": "file_path_str",
                 "override_skip": false,
                 "placeholder": "",
                 "required": false,
                 "show": false,
                 "title_case": false,
-                "tool_mode": false,
+                "tool_mode": true,
                 "trace_as_metadata": true,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "stream": {
+              "ignore_unspecified_files": {
                 "_input_type": "BoolInput",
                 "advanced": true,
-                "display_name": "Stream",
+                "display_name": "Ignore Unspecified Files",
                 "dynamic": false,
-                "info": "Whether to stream the response",
+                "info": "If true, Data with no 'file_path' property will be ignored.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "stream",
-                "override_skip": false,
+                "name": "ignore_unspecified_files",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
                 "type": "bool",
                 "value": false
               },
-              "system_message": {
-                "_input_type": "MultilineInput",
+              "ignore_unsupported_extensions": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Ignore Unsupported Extensions",
+                "dynamic": false,
+                "info": "If true, files with unsupported extensions will not be processed.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ignore_unsupported_extensions",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "markdown": {
+                "_input_type": "BoolInput",
                 "advanced": false,
-                "ai_enabled": false,
-                "copy_field": false,
-                "display_name": "System Message",
+                "display_name": "Markdown Export",
                 "dynamic": false,
-                "info": "A system message that helps set the behavior of the assistant",
-                "input_types": [
-                  "Message"
-                ],
+                "info": "Export processed documents to Markdown format. Only available when advanced mode is enabled.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "markdown",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              },
+              "md_image_placeholder": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Image placeholder",
+                "dynamic": false,
+                "info": "Specify the image placeholder for markdown exports.",
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "multiline": true,
-                "name": "system_message",
-                "override_skip": false,
+                "name": "md_image_placeholder",
                 "placeholder": "",
                 "required": false,
-                "show": true,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "<!-- image -->"
+              },
+              "md_page_break_placeholder": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Page break placeholder",
+                "dynamic": false,
+                "info": "Add this placeholder between pages in the markdown output.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "md_page_break_placeholder",
+                "placeholder": "",
+                "required": false,
+                "show": false,
                 "title_case": false,
                 "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "temperature": {
-                "_input_type": "SliderInput",
+              "ocr_engine": {
+                "_input_type": "DropdownInput",
                 "advanced": true,
-                "display_name": "Temperature",
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "OCR Engine",
                 "dynamic": false,
-                "info": "Controls randomness in responses",
-                "max_label": "",
-                "max_label_icon": "",
-                "min_label": "",
-                "min_label_icon": "",
-                "name": "temperature",
-                "override_skip": false,
+                "external_options": {},
+                "info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
+                "name": "ocr_engine",
+                "options": [
+                  "None",
+                  "easyocr"
+                ],
+                "options_metadata": [],
                 "placeholder": "",
-                "range_spec": {
-                  "max": 1,
-                  "min": 0,
-                  "step": 0.01,
-                  "step_type": "float"
-                },
                 "required": false,
-                "show": true,
-                "slider_buttons": false,
-                "slider_buttons_options": [],
-                "slider_input": false,
+                "show": false,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
-                "track_in_telemetry": false,
-                "type": "slider",
-                "value": 0.1
-              }
-            },
-            "tool_mode": false
-          },
-          "selected_output": "text_output",
-          "showNode": true,
-          "type": "LanguageModelComponent"
-        },
-        "dragging": false,
-        "id": "LanguageModelComponent-kiTPL",
-        "measured": {
-          "height": 369,
-          "width": 320
-        },
-        "position": {
-          "x": 2174.626510909065,
-          "y": 439.5147119393939
-        },
-        "selected": false,
-        "type": "genericNode"
-      },
-      {
-        "data": {
-          "id": "note-s01cs",
-          "node": {
-            "description": "### 💡 Add your OpenAI API key here",
-            "display_name": "",
-            "documentation": "",
-            "template": {
-              "backgroundColor": "transparent"
-            }
-          },
-          "type": "note"
-        },
-        "dragging": false,
-        "id": "note-s01cs",
-        "measured": {
-          "height": 324,
-          "width": 324
-        },
-        "position": {
-          "x": 2177.24956539088,
-          "y": 384.73691533198325
-        },
-        "selected": false,
-        "type": "noteNode"
-      },
-      {
-        "data": {
-          "id": "StructuredOutput-GJE9p",
-          "node": {
-            "base_classes": [
-              "Data",
-              "DataFrame"
-            ],
-            "beta": false,
-            "conditional_paths": [],
-            "custom_fields": {},
-            "description": "Uses an LLM to generate structured data. Ideal for extraction and consistency.",
-            "display_name": "Structured Output",
-            "documentation": "https://docs.langflow.org/components-processing#structured-output",
-            "edited": false,
-            "field_order": [
-              "llm",
-              "input_value",
-              "system_prompt",
-              "schema_name",
-              "output_schema"
-            ],
-            "frozen": false,
-            "icon": "braces",
-            "last_updated": "2025-12-20T16:49:42.272Z",
-            "legacy": false,
-            "lf_version": "1.6.0",
-            "metadata": {
-              "code_hash": "058ca1f51e9f",
-              "dependencies": {
-                "dependencies": [
-                  {
-                    "name": "pydantic",
-                    "version": "2.11.10"
-                  },
-                  {
-                    "name": "trustcall",
-                    "version": "0.0.39"
-                  },
-                  {
-                    "name": "lfx",
-                    "version": null
-                  }
-                ],
-                "total_dependencies": 3
-              },
-              "module": "lfx.components.llm_operations.structured_output.StructuredOutputComponent"
-            },
-            "minimized": false,
-            "output_types": [],
-            "outputs": [
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Structured Output",
-                "group_outputs": false,
-                "method": "build_structured_output",
-                "name": "structured_output",
-                "selected": "Data",
-                "tool_mode": true,
-                "types": [
-                  "Data"
-                ],
-                "value": "__UNDEFINED__"
-              },
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Structured Output",
-                "group_outputs": false,
-                "method": "build_structured_dataframe",
-                "name": "dataframe_output",
-                "selected": "DataFrame",
-                "tool_mode": true,
-                "types": [
-                  "DataFrame"
-                ],
-                "value": "__UNDEFINED__"
-              }
-            ],
-            "pinned": false,
-            "template": {
-              "_type": "Component",
-              "api_key": {
-                "_input_type": "SecretStrInput",
-                "advanced": true,
-                "display_name": "API Key",
-                "dynamic": false,
-                "info": "Model Provider API key",
-                "input_types": [],
-                "load_from_db": false,
-                "name": "api_key",
-                "override_skip": false,
-                "password": true,
-                "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": ""
-              },
-              "code": {
-                "advanced": true,
-                "dynamic": true,
-                "fileTypes": [],
-                "file_path": "",
-                "info": "",
-                "list": false,
-                "load_from_db": false,
-                "multiline": true,
-                "name": "code",
-                "password": false,
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "type": "code",
-                "value": "from pydantic import BaseModel, Field, create_model\nfrom trustcall import create_extractor\n\nfrom lfx.base.models.chat_result import get_chat_result\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.helpers.base_model import build_model_from_schema\nfrom lfx.io import (\n    MessageTextInput,\n    ModelInput,\n    MultilineInput,\n    Output,\n    SecretStrInput,\n    TableInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.table import EditMode\n\n\nclass StructuredOutputComponent(Component):\n    display_name = \"Structured Output\"\n    description = \"Uses an LLM to generate structured data. Ideal for extraction and consistency.\"\n    documentation: str = \"https://docs.langflow.org/structured-output\"\n    name = \"StructuredOutput\"\n    icon = \"braces\"\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        MultilineInput(\n            name=\"input_value\",\n            display_name=\"Input Message\",\n            info=\"The input message to the language model.\",\n            tool_mode=True,\n            required=True,\n        ),\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Format Instructions\",\n            info=\"The instructions to the language model for formatting the output.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            required=True,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"schema_name\",\n            display_name=\"Schema Name\",\n            info=\"Provide a name for the output data schema.\",\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=\"Define the structure and data types for the model's output.\",\n            required=True,\n            # TODO: remove deault value\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"name\": \"field\",\n                    \"description\": \"description of field\",\n                    \"type\": \"str\",\n                    \"multiple\": \"False\",\n                }\n            ],\n        ),\n    ]\n\n    outputs = [\n        Output(\n            name=\"structured_output\",\n            display_name=\"Structured Output\",\n            method=\"build_structured_output\",\n        ),\n        Output(\n            name=\"dataframe_output\",\n            display_name=\"Structured Output\",\n            method=\"build_structured_dataframe\",\n        ),\n    ]\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        return update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n    def build_structured_output_base(self):\n        schema_name = self.schema_name or \"OutputModel\"\n\n        llm = get_llm(model=self.model, user_id=self.user_id, api_key=self.api_key)\n\n        if not hasattr(llm, \"with_structured_output\"):\n            msg = \"Language model does not support structured output.\"\n            raise TypeError(msg)\n        if not self.output_schema:\n            msg = \"Output schema cannot be empty\"\n            raise ValueError(msg)\n\n        output_model_ = build_model_from_schema(self.output_schema)\n        output_model = create_model(\n            schema_name,\n            __doc__=f\"A list of {schema_name}.\",\n            objects=(\n                list[output_model_],\n                Field(\n                    description=f\"A list of {schema_name}.\",  # type: ignore[valid-type]\n                    min_length=1,  # help ensure non-empty output\n                ),\n            ),\n        )\n        # Tracing config\n        config_dict = {\n            \"run_name\": self.display_name,\n            \"project_name\": self.get_project_name(),\n            \"callbacks\": self.get_langchain_callbacks(),\n        }\n        # Generate structured output using Trustcall first, then fallback to Langchain if it fails\n        result = self._extract_output_with_trustcall(llm, output_model, config_dict)\n        if result is None:\n            result = self._extract_output_with_langchain(llm, output_model, config_dict)\n\n        # OPTIMIZATION NOTE: Simplified processing based on trustcall response structure\n        # Handle non-dict responses (shouldn't happen with trustcall, but defensive)\n        if not isinstance(result, dict):\n            return result\n\n        # Extract first response and convert BaseModel to dict\n        responses = result.get(\"responses\", [])\n        if not responses:\n            return result\n\n        # Convert BaseModel to dict (creates the \"objects\" key)\n        first_response = responses[0]\n        structured_data = first_response\n        if isinstance(first_response, BaseModel):\n            structured_data = first_response.model_dump()\n        # Extract the objects array (guaranteed to exist due to our Pydantic model structure)\n        return structured_data.get(\"objects\", structured_data)\n\n    def build_structured_output(self) -> Data:\n        output = self.build_structured_output_base()\n        if not isinstance(output, list) or not output:\n            # handle empty or unexpected type case\n            msg = \"No structured output returned\"\n            raise ValueError(msg)\n        if len(output) == 1:\n            return Data(data=output[0])\n        if len(output) > 1:\n            # Multiple outputs - wrap them in a results container\n            return Data(data={\"results\": output})\n        return Data()\n\n    def build_structured_dataframe(self) -> DataFrame:\n        output = self.build_structured_output_base()\n        if not isinstance(output, list) or not output:\n            # handle empty or unexpected type case\n            msg = \"No structured output returned\"\n            raise ValueError(msg)\n        if len(output) == 1:\n            # For single dictionary, wrap in a list to create DataFrame with one row\n            return DataFrame([output[0]])\n        if len(output) > 1:\n            # Multiple outputs - convert to DataFrame directly\n            return DataFrame(output)\n        return DataFrame()\n\n    def _extract_output_with_trustcall(self, llm, schema: BaseModel, config_dict: dict) -> list[BaseModel] | None:\n        try:\n            llm_with_structured_output = create_extractor(llm, tools=[schema], tool_choice=schema.__name__)\n            result = get_chat_result(\n                runnable=llm_with_structured_output,\n                system_message=self.system_prompt,\n                input_value=self.input_value,\n                config=config_dict,\n            )\n        except Exception as e:  # noqa: BLE001\n            logger.warning(\n                f\"Trustcall extraction failed, falling back to Langchain: {e} \"\n                \"(Note: This may not be an error—some models or configurations do not support tool calling. \"\n                \"Falling back is normal in such cases.)\"\n            )\n            return None\n        return result or None  # langchain fallback is used if error occurs or the result is empty\n\n    def _extract_output_with_langchain(self, llm, schema: BaseModel, config_dict: dict) -> list[BaseModel] | None:\n        try:\n            llm_with_structured_output = llm.with_structured_output(schema)\n            result = get_chat_result(\n                runnable=llm_with_structured_output,\n                system_message=self.system_prompt,\n                input_value=self.input_value,\n                config=config_dict,\n            )\n            if isinstance(result, BaseModel):\n                result = result.model_dump()\n                result = result.get(\"objects\", result)\n        except Exception as fallback_error:\n            msg = (\n                f\"Model does not support tool calling (trustcall failed) \"\n                f\"and fallback with_structured_output also failed: {fallback_error}\"\n            )\n            raise ValueError(msg) from fallback_error\n\n        return result or None\n"
-              },
-              "input_value": {
-                "_input_type": "MultilineInput",
-                "advanced": false,
-                "copy_field": false,
-                "display_name": "Input Message",
-                "dynamic": false,
-                "info": "The input message to the language model.",
-                "input_types": [
-                  "Message"
-                ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "multiline": true,
-                "name": "input_value",
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "tool_mode": true,
-                "trace_as_input": true,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "model": {
-                "_input_type": "ModelInput",
-                "advanced": false,
-                "display_name": "Language Model",
-                "dynamic": false,
-                "external_options": {
-                  "fields": {
-                    "data": {
-                      "node": {
-                        "display_name": "Connect other models",
-                        "icon": "CornerDownLeft",
-                        "name": "connect_other_models"
-                      }
-                    }
-                  }
-                },
-                "info": "Select your model provider",
-                "input_types": [],
-                "list": false,
-                "list_add_label": "Add More",
-                "model_type": "language",
-                "name": "model",
-                "options": [
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5"
-                      ]
-                    },
-                    "name": "gpt-5",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5-mini"
-                      ]
-                    },
-                    "name": "gpt-5-mini",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5-nano"
-                      ]
-                    },
-                    "name": "gpt-5-nano",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model"
-                    },
-                    "name": "gpt-4o-mini",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model"
-                    },
-                    "name": "gpt-4o",
-                    "provider": "OpenAI"
-                  },
-                  {
-                    "category": "Google Generative AI",
-                    "icon": "GoogleGenerativeAI",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "GOOGLE_API_KEY"
-                    },
-                    "name": "__enable_provider_Google Generative AI__",
-                    "provider": "Google Generative AI"
-                  },
-                  {
-                    "category": "Ollama",
-                    "icon": "Ollama",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "OLLAMA_BASE_URL"
-                    },
-                    "name": "__enable_provider_Ollama__",
-                    "provider": "Ollama"
-                  },
-                  {
-                    "category": "IBM Watsonx",
-                    "icon": "WatsonxAI",
-                    "metadata": {
-                      "is_disabled_provider": true,
-                      "variable_name": "WATSONX_APIKEY"
-                    },
-                    "name": "__enable_provider_IBM Watsonx__",
-                    "provider": "IBM Watsonx"
-                  }
-                ],
-                "override_skip": false,
-                "placeholder": "Setup Provider",
-                "real_time_refresh": true,
-                "refresh_button": true,
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
-                "track_in_telemetry": false,
-                "type": "model",
-                "value": [
-                  {
-                    "category": "OpenAI",
-                    "icon": "OpenAI",
-                    "metadata": {
-                      "api_key_param": "api_key",
-                      "context_length": 128000,
-                      "model_class": "ChatOpenAI",
-                      "model_name_param": "model",
-                      "reasoning_models": [
-                        "gpt-5"
-                      ]
-                    },
-                    "name": "gpt-5",
-                    "provider": "OpenAI"
-                  }
-                ]
-              },
-              "output_schema": {
-                "_input_type": "TableInput",
-                "advanced": false,
-                "display_name": "Output Schema",
-                "dynamic": false,
-                "info": "Define the structure and data types for the model's output.",
-                "is_list": true,
-                "list_add_label": "Add More",
-                "name": "output_schema",
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "table_icon": "Table",
-                "table_schema": [
-                  {
-                    "default": "field",
-                    "description": "Specify the name of the output field.",
-                    "display_name": "Name",
-                    "edit_mode": "inline",
-                    "formatter": "text",
-                    "name": "name",
-                    "type": "str"
-                  },
-                  {
-                    "default": "description of field",
-                    "description": "Describe the purpose of the output field.",
-                    "display_name": "Description",
-                    "edit_mode": "popover",
-                    "formatter": "text",
-                    "name": "description",
-                    "type": "str"
-                  },
-                  {
-                    "default": "str",
-                    "description": "Indicate the data type of the output field (e.g., str, int, float, bool, dict).",
-                    "display_name": "Type",
-                    "edit_mode": "inline",
-                    "formatter": "text",
-                    "name": "type",
-                    "options": [
-                      "str",
-                      "int",
-                      "float",
-                      "bool",
-                      "dict"
-                    ],
-                    "type": "str"
-                  },
-                  {
-                    "default": "False",
-                    "description": "Set to True if this output field should be a list of the specified type.",
-                    "display_name": "As List",
-                    "edit_mode": "inline",
-                    "formatter": "text",
-                    "name": "multiple",
-                    "type": "boolean"
-                  }
-                ],
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "trigger_icon": "Table",
-                "trigger_text": "Open table",
-                "type": "table",
-                "value": [
-                  {
-                    "description": "Full name of the candidate",
-                    "multiple": "False",
-                    "name": "full_name",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Email ID",
-                    "multiple": "False",
-                    "name": "email",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Contact Number",
-                    "multiple": "False",
-                    "name": "phone_number",
-                    "type": "str"
-                  },
-                  {
-                    "description": "LinkedIn URL",
-                    "multiple": "False",
-                    "name": "linkedin",
-                    "type": "str"
-                  },
-                  {
-                    "description": "GitHub profile URL (if applicable)",
-                    "multiple": "False",
-                    "name": "github",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Personal website or portfolio URL",
-                    "multiple": "False",
-                    "name": "portfolio",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Visa/work authorization details (if applicable)",
-                    "multiple": "False",
-                    "name": "visa_status",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Short professional summary or objective statement",
-                    "multiple": "False",
-                    "name": "summary",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Dictionaries of experience details with following keys:\\n    \\\"job_title\\\": Job position/title,\\n\\t\\\"company_name\\\": Employer or organization\\n\\t\\\"location\\\": Job location (remote/in-office)\\n\\t\\\"start_date\\\": Start date (YYYY-MM)\\n\\t\\\"end_date\\\": End date or \\\"Present\\\"\\n\\t\\\"responsibilities\\\": List of responsibilities and tasks\\n\\t\\\"achievements\\\": List of key achievements and contributions",
-                    "multiple": "True",
-                    "name": "experience",
-                    "type": "dict"
-                  },
-                  {
-                    "description": "Dictionaries of Education details with following keys:\\n\\\"degree\\\": Degree obtained (e.g., B.Sc., M.Sc., Ph.D.),\\n\\\"field_of_study\\\": Major or specialization,\\n\\\"institution\\\": University/college name,\\n\\\"location\\\": Location of institution,\\n\\\"start_date\\\": Start date (YYYY-MM),\\n\\\"end_date\\\": Graduation/completion date (YYYY-MM),\\n\\\"gpa\\\": GPA/grade (if available),\\n\\\"relevant_courses\\\": List of relevant coursework (if applicable)",
-                    "multiple": "True",
-                    "name": "education",
-                    "type": "dict"
-                  },
-                  {
-                    "description": "Skills mentioned in the resume. Comma separated.",
-                    "multiple": "True",
-                    "name": "skills",
-                    "type": "str"
-                  },
-                  {
-                    "description": "Title and description and details of the project. Including the skills and technologies used.",
-                    "multiple": "False",
-                    "name": "projects",
-                    "type": "str"
-                  }
-                ]
-              },
-              "schema_name": {
-                "_input_type": "MessageTextInput",
-                "advanced": true,
-                "display_name": "Schema Name",
-                "dynamic": false,
-                "info": "Provide a name for the output data schema.",
-                "input_types": [
-                  "Message"
-                ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "schema_name",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "system_prompt": {
-                "_input_type": "MultilineInput",
-                "advanced": true,
-                "copy_field": false,
-                "display_name": "Format Instructions",
-                "dynamic": false,
-                "info": "The instructions to the language model for formatting the output.",
-                "input_types": [
-                  "Message"
-                ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "multiline": true,
-                "name": "system_prompt",
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
                 "type": "str",
-                "value": "You are an AI that extracts structured JSON objects from unstructured text. Use a predefined schema with expected types (str, int, float, bool, dict). Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. Fill missing or ambiguous values with defaults: null for missing values. Remove exact duplicates but keep variations that have different field values. Always return valid JSON in the expected format, never throw errors. If multiple objects can be extracted, return them all in the structured format."
-              }
-            },
-            "tool_mode": false
-          },
-          "selected_output": "dataframe_output",
-          "showNode": true,
-          "type": "StructuredOutput"
-        },
-        "dragging": false,
-        "id": "StructuredOutput-GJE9p",
-        "measured": {
-          "height": 387,
-          "width": 320
-        },
-        "position": {
-          "x": 1308.5338025647359,
-          "y": 651.6998573907567
-        },
-        "selected": false,
-        "type": "genericNode"
-      },
-      {
-        "data": {
-          "id": "File-Ln2gO",
-          "node": {
-            "base_classes": [
-              "Message"
-            ],
-            "beta": false,
-            "conditional_paths": [],
-            "custom_fields": {},
-            "description": "Loads and returns the content from uploaded files.",
-            "display_name": "Read File",
-            "documentation": "https://docs.langflow.org/read-file",
-            "edited": false,
-            "field_order": [
-              "storage_location",
-              "path",
-              "file_path",
-              "separator",
-              "silent_errors",
-              "delete_server_file_after_processing",
-              "ignore_unsupported_extensions",
-              "ignore_unspecified_files",
-              "file_path_str",
-              "aws_access_key_id",
-              "aws_secret_access_key",
-              "bucket_name",
-              "aws_region",
-              "s3_file_key",
-              "service_account_key",
-              "file_id",
-              "advanced_mode",
-              "pipeline",
-              "ocr_engine",
-              "md_image_placeholder",
-              "md_page_break_placeholder",
-              "doc_key",
-              "use_multithreading",
-              "concurrency_multithreading",
-              "markdown"
-            ],
-            "frozen": false,
-            "icon": "file-text",
-            "last_updated": "2025-12-20T17:34:46.873Z",
-            "legacy": false,
-            "metadata": {
-              "code_hash": "9d57e0bfda44",
-              "dependencies": {
-                "dependencies": [
-                  {
-                    "name": "lfx",
-                    "version": null
-                  },
-                  {
-                    "name": "langchain_core",
-                    "version": "0.3.80"
-                  },
-                  {
-                    "name": "pydantic",
-                    "version": "2.11.10"
-                  },
-                  {
-                    "name": "googleapiclient",
-                    "version": "2.154.0"
-                  }
-                ],
-                "total_dependencies": 4
+                "value": "easyocr"
               },
-              "module": "lfx.components.files_and_knowledge.file.FileComponent"
-            },
-            "minimized": false,
-            "output_types": [],
-            "outputs": [
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Raw Content",
-                "group_outputs": false,
-                "method": "load_files_message",
-                "name": "message",
-                "selected": "Message",
-                "tool_mode": true,
-                "types": [
-                  "Message"
-                ],
-                "value": "__UNDEFINED__"
-              }
-            ],
-            "pinned": false,
-            "template": {
-              "_type": "Component",
-              "advanced_mode": {
-                "_input_type": "BoolInput",
+              "path": {
+                "_input_type": "FileInput",
                 "advanced": false,
-                "display_name": "Advanced Parser",
+                "display_name": "Files",
                 "dynamic": false,
-                "info": "Enable advanced document processing and export with Docling for PDFs, images, and office documents. Note that advanced document processing can consume significant resources.",
-                "list": false,
+                "fileTypes": [
+                  "csv",
+                  "json",
+                  "pdf",
+                  "txt",
+                  "md",
+                  "mdx",
+                  "yaml",
+                  "yml",
+                  "xml",
+                  "html",
+                  "htm",
+                  "docx",
+                  "py",
+                  "sh",
+                  "sql",
+                  "js",
+                  "ts",
+                  "tsx",
+                  "adoc",
+                  "asciidoc",
+                  "asc",
+                  "bmp",
+                  "dotx",
+                  "dotm",
+                  "docm",
+                  "jpg",
+                  "jpeg",
+                  "png",
+                  "potx",
+                  "ppsx",
+                  "pptm",
+                  "potm",
+                  "ppsm",
+                  "pptx",
+                  "tiff",
+                  "xls",
+                  "xlsx",
+                  "xhtml",
+                  "webp",
+                  "zip",
+                  "tar",
+                  "tgz",
+                  "bz2",
+                  "gz"
+                ],
+                "file_path": [],
+                "info": "Supported file extensions: csv, json, pdf, txt, md, mdx, yaml, yml, xml, html, htm, docx, py, sh, sql, js, ts, tsx, adoc, asciidoc, asc, bmp, dotx, dotm, docm, jpg, jpeg, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, xls, xlsx, xhtml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
+                "list": true,
                 "list_add_label": "Add More",
-                "name": "advanced_mode",
-                "override_skip": false,
+                "name": "path",
                 "placeholder": "",
                 "real_time_refresh": true,
                 "required": false,
                 "show": true,
+                "temp_file": false,
                 "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
-              },
-              "aws_access_key_id": {
-                "_input_type": "SecretStrInput",
-                "advanced": false,
-                "display_name": "AWS Access Key ID",
-                "dynamic": false,
-                "info": "AWS Access key ID.",
-                "input_types": [],
-                "load_from_db": true,
-                "name": "aws_access_key_id",
-                "override_skip": false,
-                "password": true,
-                "placeholder": "",
-                "required": true,
-                "show": false,
-                "title_case": false,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": ""
-              },
-              "aws_region": {
-                "_input_type": "StrInput",
-                "advanced": false,
-                "display_name": "AWS Region",
-                "dynamic": false,
-                "info": "AWS region (e.g., us-east-1, eu-west-1).",
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "aws_region",
-                "override_skip": false,
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
+                "type": "file",
                 "value": ""
               },
-              "aws_secret_access_key": {
-                "_input_type": "SecretStrInput",
-                "advanced": false,
-                "display_name": "AWS Secret Key",
+              "pipeline": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Pipeline",
                 "dynamic": false,
-                "info": "AWS Secret Key.",
-                "input_types": [],
-                "load_from_db": true,
-                "name": "aws_secret_access_key",
-                "override_skip": false,
-                "password": true,
+                "external_options": {},
+                "info": "Docling pipeline to use",
+                "name": "pipeline",
+                "options": [
+                  "standard",
+                  "vlm"
+                ],
+                "options_metadata": [],
                 "placeholder": "",
-                "required": true,
+                "real_time_refresh": true,
+                "required": false,
                 "show": false,
                 "title_case": false,
-                "track_in_telemetry": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
                 "type": "str",
-                "value": ""
+                "value": "standard"
               },
-              "bucket_name": {
+              "s3_file_key": {
                 "_input_type": "StrInput",
                 "advanced": false,
-                "display_name": "S3 Bucket Name",
+                "display_name": "S3 File Key",
                 "dynamic": false,
-                "info": "Enter the name of the S3 bucket.",
+                "info": "The key (path) of the file in S3 bucket.",
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "bucket_name",
+                "name": "s3_file_key",
                 "override_skip": false,
                 "placeholder": "",
                 "required": true,
@@ -2088,547 +1417,937 @@
                 "type": "str",
                 "value": ""
               },
-              "code": {
+              "separator": {
+                "_input_type": "StrInput",
                 "advanced": true,
-                "dynamic": true,
-                "fileTypes": [],
-                "file_path": "",
-                "info": "",
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "Specify the separator to use between multiple outputs in Message format.",
                 "list": false,
+                "list_add_label": "Add More",
                 "load_from_db": false,
-                "multiline": true,
-                "name": "code",
-                "password": false,
+                "name": "separator",
                 "placeholder": "",
-                "required": true,
+                "required": false,
                 "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 contextlib\nimport json\nimport subprocess\nimport sys\nimport textwrap\nfrom copy import deepcopy\nfrom pathlib import Path\nfrom tempfile import NamedTemporaryFile\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.storage_utils import parse_storage_path, read_file_bytes, validate_image_content_type\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom lfx.inputs import SortableListInput\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output, SecretStrInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame  # noqa: TC001\nfrom lfx.schema.message import Message\nfrom lfx.services.deps import get_settings_service, get_storage_service\nfrom lfx.utils.async_helpers import run_until_complete\nfrom lfx.utils.validate_cloud import is_astra_cloud_environment\n\n\ndef _get_storage_location_options():\n    \"\"\"Get storage location options, filtering out Local if in Astra cloud environment.\"\"\"\n    all_options = [{\"name\": \"AWS\", \"icon\": \"Amazon\"}, {\"name\": \"Google Drive\", \"icon\": \"google\"}]\n    if is_astra_cloud_environment():\n        return all_options\n    return [{\"name\": \"Local\", \"icon\": \"hard-drive\"}, *all_options]\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n    display_name = \"Read File\"\n    # description is now a dynamic property - see get_tool_description()\n    _base_description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/read-file\"\n    icon = \"file-text\"\n    name = \"File\"\n    add_tool_output = True  # Enable tool mode toggle without requiring tool_mode inputs\n\n    # Extensions that can be processed without Docling (using standard text parsing)\n    TEXT_EXTENSIONS = TEXT_FILE_TYPES\n\n    # Extensions that require Docling for processing (images, advanced office formats, etc.)\n    DOCLING_ONLY_EXTENSIONS = [\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"jpg\",\n        \"jpeg\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"webp\",\n    ]\n\n    # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n    VALID_EXTENSIONS = [\n        *TEXT_EXTENSIONS,\n        *DOCLING_ONLY_EXTENSIONS,\n    ]\n\n    # Fixed export settings used when markdown export is requested.\n    EXPORT_FORMAT = \"Markdown\"\n    IMAGE_MODE = \"placeholder\"\n\n    _base_inputs = deepcopy(BaseFileComponent.get_base_inputs())\n\n    for input_item in _base_inputs:\n        if isinstance(input_item, FileInput) and input_item.name == \"path\":\n            input_item.real_time_refresh = True\n            input_item.tool_mode = False  # Disable tool mode for file upload input\n            input_item.required = False  # Make it optional so it doesn't error in tool mode\n            break\n\n    inputs = [\n        SortableListInput(\n            name=\"storage_location\",\n            display_name=\"Storage Location\",\n            placeholder=\"Select Location\",\n            info=\"Choose where to read the file from.\",\n            options=_get_storage_location_options(),\n            real_time_refresh=True,\n            limit=1,\n        ),\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,  # Required for Toolset toggle, but _get_tools() ignores this parameter\n            required=False,\n        ),\n        # AWS S3 specific inputs\n        SecretStrInput(\n            name=\"aws_access_key_id\",\n            display_name=\"AWS Access Key ID\",\n            info=\"AWS Access key ID.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"aws_secret_access_key\",\n            display_name=\"AWS Secret Key\",\n            info=\"AWS Secret Key.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"bucket_name\",\n            display_name=\"S3 Bucket Name\",\n            info=\"Enter the name of the S3 bucket.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"aws_region\",\n            display_name=\"AWS Region\",\n            info=\"AWS region (e.g., us-east-1, eu-west-1).\",\n            show=False,\n            advanced=False,\n        ),\n        StrInput(\n            name=\"s3_file_key\",\n            display_name=\"S3 File Key\",\n            info=\"The key (path) of the file in S3 bucket.\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        # Google Drive specific inputs\n        SecretStrInput(\n            name=\"service_account_key\",\n            display_name=\"GCP Credentials Secret Key\",\n            info=\"Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).\",\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        StrInput(\n            name=\"file_id\",\n            display_name=\"Google Drive File ID\",\n            info=(\"The Google Drive file ID to read. The file must be shared with the service account email.\"),\n            show=False,\n            advanced=False,\n            required=True,\n        ),\n        BoolInput(\n            name=\"advanced_mode\",\n            display_name=\"Advanced Parser\",\n            value=False,\n            real_time_refresh=True,\n            info=(\n                \"Enable advanced document processing and export with Docling for PDFs, images, and office documents. \"\n                \"Note that advanced document processing can consume significant resources.\"\n            ),\n            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    # ------------------------------ Tool description with file names --------------\n\n    def get_tool_description(self) -> str:\n        \"\"\"Return a dynamic description that includes the names of uploaded files.\n\n        This helps the Agent understand which files are available to read.\n        \"\"\"\n        base_description = \"Loads and returns the content from uploaded files.\"\n\n        # Get the list of uploaded file paths\n        file_paths = getattr(self, \"path\", None)\n        if not file_paths:\n            return base_description\n\n        # Ensure it's a list\n        if not isinstance(file_paths, list):\n            file_paths = [file_paths]\n\n        # Extract just the file names from the paths\n        file_names = []\n        for fp in file_paths:\n            if fp:\n                name = Path(fp).name\n                file_names.append(name)\n\n        if file_names:\n            files_str = \", \".join(file_names)\n            return f\"{base_description} Available files: {files_str}. Call this tool to read these files.\"\n\n        return base_description\n\n    @property\n    def description(self) -> str:\n        \"\"\"Dynamic description property that includes uploaded file names.\"\"\"\n        return self.get_tool_description()\n\n    async def _get_tools(self) -> list:\n        \"\"\"Override to create a tool without parameters.\n\n        The Read File component should use the files already uploaded via UI,\n        not accept file paths from the Agent (which wouldn't know the internal paths).\n        \"\"\"\n        from langchain_core.tools import StructuredTool\n        from pydantic import BaseModel\n\n        # Empty schema - no parameters needed\n        class EmptySchema(BaseModel):\n            \"\"\"No parameters required - uses pre-uploaded files.\"\"\"\n\n        async def read_files_tool() -> str:\n            \"\"\"Read the content of uploaded files.\"\"\"\n            try:\n                result = self.load_files_message()\n                if hasattr(result, \"get_text\"):\n                    return result.get_text()\n                if hasattr(result, \"text\"):\n                    return result.text\n                return str(result)\n            except (FileNotFoundError, ValueError, OSError, RuntimeError) as e:\n                return f\"Error reading files: {e}\"\n\n        description = self.get_tool_description()\n\n        tool = StructuredTool(\n            name=\"load_files_message\",\n            description=description,\n            coroutine=read_files_tool,\n            args_schema=EmptySchema,\n            handle_tool_error=True,\n            tags=[\"load_files_message\"],\n            metadata={\n                \"display_name\": \"Read File\",\n                \"display_description\": description,\n            },\n        )\n\n        return [tool]\n\n    # ------------------------------ UI helpers --------------------------------------\n\n    def _path_value(self, template: dict) -> list[str]:\n        \"\"\"Return the list of currently selected file paths from the template.\"\"\"\n        return template.get(\"path\", {}).get(\"file_path\", [])\n\n    def update_build_config(\n        self,\n        build_config: dict[str, Any],\n        field_value: Any,\n        field_name: str | None = None,\n    ) -> dict[str, Any]:\n        \"\"\"Show/hide Advanced Parser and related fields based on selection context.\"\"\"\n        # Update storage location options dynamically based on cloud environment\n        if \"storage_location\" in build_config:\n            updated_options = _get_storage_location_options()\n            build_config[\"storage_location\"][\"options\"] = updated_options\n\n        # Handle storage location selection\n        if field_name == \"storage_location\":\n            # Extract selected storage location\n            selected = [location[\"name\"] for location in field_value] if isinstance(field_value, list) else []\n\n            # Hide all storage-specific fields first\n            storage_fields = [\n                \"aws_access_key_id\",\n                \"aws_secret_access_key\",\n                \"bucket_name\",\n                \"aws_region\",\n                \"s3_file_key\",\n                \"service_account_key\",\n                \"file_id\",\n            ]\n\n            for f_name in storage_fields:\n                if f_name in build_config:\n                    build_config[f_name][\"show\"] = False\n\n            # Show fields based on selected storage location\n            if len(selected) == 1:\n                location = selected[0]\n\n                if location == \"Local\":\n                    # Show file upload input for local storage\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = True\n\n                elif location == \"AWS\":\n                    # Hide file upload input, show AWS fields\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = False\n\n                    aws_fields = [\n                        \"aws_access_key_id\",\n                        \"aws_secret_access_key\",\n                        \"bucket_name\",\n                        \"aws_region\",\n                        \"s3_file_key\",\n                    ]\n                    for f_name in aws_fields:\n                        if f_name in build_config:\n                            build_config[f_name][\"show\"] = True\n                            build_config[f_name][\"advanced\"] = False\n\n                elif location == \"Google Drive\":\n                    # Hide file upload input, show Google Drive fields\n                    if \"path\" in build_config:\n                        build_config[\"path\"][\"show\"] = False\n\n                    gdrive_fields = [\"service_account_key\", \"file_id\"]\n                    for f_name in gdrive_fields:\n                        if f_name in build_config:\n                            build_config[f_name][\"show\"] = True\n                            build_config[f_name][\"advanced\"] = False\n            # No storage location selected - show file upload by default\n            elif \"path\" in build_config:\n                build_config[\"path\"][\"show\"] = True\n\n            return build_config\n\n        if field_name == \"path\":\n            paths = self._path_value(build_config)\n\n            # 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 _get_selected_storage_location(self) -> str:\n        \"\"\"Get the selected storage location from the SortableListInput.\"\"\"\n        if hasattr(self, \"storage_location\") and self.storage_location:\n            if isinstance(self.storage_location, list) and len(self.storage_location) > 0:\n                return self.storage_location[0].get(\"name\", \"\")\n            if isinstance(self.storage_location, dict):\n                return self.storage_location.get(\"name\", \"\")\n        return \"Local\"  # Default to Local if not specified\n\n    def _validate_and_resolve_paths(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Override to handle file_path_str input from tool mode and cloud storage.\n\n        Priority:\n        1. Cloud storage (AWS/Google Drive) if selected\n        2. file_path_str (if provided by the tool call)\n        3. path (uploaded file from UI)\n        \"\"\"\n        storage_location = self._get_selected_storage_location()\n\n        # Handle AWS S3\n        if storage_location == \"AWS\":\n            return self._read_from_aws_s3()\n\n        # Handle Google Drive\n        if storage_location == \"Google Drive\":\n            return self._read_from_google_drive()\n\n        # Handle Local storage\n        # Check if file_path_str is provided (from tool mode)\n        file_path_str = getattr(self, \"file_path_str\", None)\n        if file_path_str:\n            # Use the string path from tool mode\n            from pathlib import Path\n\n            from lfx.schema.data import Data\n\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 _read_from_aws_s3(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Read file from AWS S3.\"\"\"\n        from lfx.base.data.cloud_storage_utils import create_s3_client, validate_aws_credentials\n\n        # Validate AWS credentials\n        validate_aws_credentials(self)\n        if not getattr(self, \"s3_file_key\", None):\n            msg = \"S3 File Key is required\"\n            raise ValueError(msg)\n\n        # Create S3 client\n        s3_client = create_s3_client(self)\n\n        # Download file to temp location\n        import tempfile\n\n        # Get file extension from S3 key\n        file_extension = Path(self.s3_file_key).suffix or \"\"\n\n        with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n            temp_file_path = temp_file.name\n            try:\n                s3_client.download_fileobj(self.bucket_name, self.s3_file_key, temp_file)\n            except Exception as e:\n                # Clean up temp file on failure\n                with contextlib.suppress(OSError):\n                    Path(temp_file_path).unlink()\n                msg = f\"Failed to download file from S3: {e}\"\n                raise RuntimeError(msg) from e\n\n        # Create BaseFile object\n        from lfx.schema.data import Data\n\n        temp_path = Path(temp_file_path)\n        data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n        return [BaseFileComponent.BaseFile(data_obj, temp_path, delete_after_processing=True)]\n\n    def _read_from_google_drive(self) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Read file from Google Drive.\"\"\"\n        import tempfile\n\n        from googleapiclient.http import MediaIoBaseDownload\n\n        from lfx.base.data.cloud_storage_utils import create_google_drive_service\n\n        # Validate Google Drive credentials\n        if not getattr(self, \"service_account_key\", None):\n            msg = \"GCP Credentials Secret Key is required for Google Drive storage\"\n            raise ValueError(msg)\n        if not getattr(self, \"file_id\", None):\n            msg = \"Google Drive File ID is required\"\n            raise ValueError(msg)\n\n        # Create Google Drive service with read-only scope\n        drive_service = create_google_drive_service(\n            self.service_account_key, scopes=[\"https://www.googleapis.com/auth/drive.readonly\"]\n        )\n\n        # Get file metadata to determine file name and extension\n        try:\n            file_metadata = drive_service.files().get(fileId=self.file_id, fields=\"name,mimeType\").execute()\n            file_name = file_metadata.get(\"name\", \"download\")\n        except Exception as e:\n            msg = (\n                f\"Unable to access file with ID '{self.file_id}'. \"\n                f\"Error: {e!s}. \"\n                \"Please ensure: 1) The file ID is correct, 2) The file exists, \"\n                \"3) The service account has been granted access to this file.\"\n            )\n            raise ValueError(msg) from e\n\n        # Download file to temp location\n        file_extension = Path(file_name).suffix or \"\"\n        with tempfile.NamedTemporaryFile(mode=\"wb\", suffix=file_extension, delete=False) as temp_file:\n            temp_file_path = temp_file.name\n            try:\n                request = drive_service.files().get_media(fileId=self.file_id)\n                downloader = MediaIoBaseDownload(temp_file, request)\n                done = False\n                while not done:\n                    _status, done = downloader.next_chunk()\n            except Exception as e:\n                # Clean up temp file on failure\n                with contextlib.suppress(OSError):\n                    Path(temp_file_path).unlink()\n                msg = f\"Failed to download file from Google Drive: {e}\"\n                raise RuntimeError(msg) from e\n\n        # Create BaseFile object\n        from lfx.schema.data import Data\n\n        temp_path = Path(temp_file_path)\n        data_obj = Data(data={self.SERVER_FILE_PATH_FIELDNAME: str(temp_path)})\n        return [BaseFileComponent.BaseFile(data_obj, temp_path, delete_after_processing=True)]\n\n    def _is_docling_compatible(self, file_path: str) -> bool:\n        \"\"\"Lightweight extension gate for Docling-compatible types.\"\"\"\n        docling_exts = (\n            \".adoc\",\n            \".asciidoc\",\n            \".asc\",\n            \".bmp\",\n            \".csv\",\n            \".dotx\",\n            \".dotm\",\n            \".docm\",\n            \".docx\",\n            \".htm\",\n            \".html\",\n            \".jpg\",\n            \".jpeg\",\n            \".json\",\n            \".md\",\n            \".pdf\",\n            \".png\",\n            \".potx\",\n            \".ppsx\",\n            \".pptm\",\n            \".potm\",\n            \".ppsm\",\n            \".pptx\",\n            \".tiff\",\n            \".txt\",\n            \".xls\",\n            \".xlsx\",\n            \".xhtml\",\n            \".xml\",\n            \".webp\",\n        )\n        return file_path.lower().endswith(docling_exts)\n\n    async def _get_local_file_for_docling(self, file_path: str) -> tuple[str, bool]:\n        \"\"\"Get a local file path for Docling processing, downloading from S3 if needed.\n\n        Args:\n            file_path: Either a local path or S3 key (format \"flow_id/filename\")\n\n        Returns:\n            tuple[str, bool]: (local_path, should_delete) where should_delete indicates\n                              if this is a temporary file that should be cleaned up\n        \"\"\"\n        settings = get_settings_service().settings\n        if settings.storage_type == \"local\":\n            return file_path, False\n\n        # S3 storage - download to temp file\n        parsed = parse_storage_path(file_path)\n        if not parsed:\n            msg = f\"Invalid S3 path format: {file_path}. Expected 'flow_id/filename'\"\n            raise ValueError(msg)\n\n        storage_service = get_storage_service()\n        flow_id, filename = parsed\n\n        # Get file content from S3\n        content = await storage_service.get_file(flow_id, filename)\n\n        suffix = Path(filename).suffix\n        with NamedTemporaryFile(mode=\"wb\", suffix=suffix, delete=False) as tmp_file:\n            tmp_file.write(content)\n            temp_path = tmp_file.name\n\n        return temp_path, True\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        For S3 storage, the file is downloaded to a temp file first.\n        \"\"\"\n        if not file_path:\n            return None\n\n        settings = get_settings_service().settings\n        if settings.storage_type == \"s3\":\n            local_path, should_delete = run_until_complete(self._get_local_file_for_docling(file_path))\n        else:\n            local_path = file_path\n            should_delete = False\n\n        try:\n            return self._process_docling_subprocess_impl(local_path, file_path)\n        finally:\n            # Clean up temp file if we created one\n            if should_delete:\n                with contextlib.suppress(Exception):\n                    Path(local_path).unlink()  # Ignore cleanup errors\n\n    def _process_docling_subprocess_impl(self, local_file_path: str, original_file_path: str) -> Data | None:\n        \"\"\"Implementation of Docling subprocess processing.\n\n        Args:\n            local_file_path: Path to local file to process\n            original_file_path: Original file path to include in metadata\n        Returns:\n            Data object with processed content\n        \"\"\"\n        args: dict[str, Any] = {\n            \"file_path\": local_file_path,\n            \"markdown\": bool(self.markdown),\n            \"image_mode\": str(self.IMAGE_MODE),\n            \"md_image_placeholder\": str(self.md_image_placeholder),\n            \"md_page_break_placeholder\": str(self.md_page_break_placeholder),\n            \"pipeline\": str(self.pipeline),\n            \"ocr_engine\": (\n                self.ocr_engine if self.ocr_engine and self.ocr_engine != \"None\" and self.pipeline != \"vlm\" else None\n            ),\n        }\n\n        # Child script for isolating the docling processing\n        child_script = textwrap.dedent(\n            r\"\"\"\n            import json, sys\n\n            def try_imports():\n                try:\n                    from docling.datamodel.base_models import ConversionStatus, InputFormat  # type: ignore\n                    from docling.document_converter import DocumentConverter  # type: ignore\n                    from docling_core.types.doc import ImageRefMode  # type: ignore\n                    return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"latest\"\n                except Exception as e:\n                    raise e\n\n            def create_converter(strategy, input_format, DocumentConverter, pipeline, ocr_engine):\n                # --- Standard PDF/IMAGE pipeline (your existing behavior), with optional OCR ---\n                if pipeline == \"standard\":\n                    try:\n                        from docling.datamodel.pipeline_options import PdfPipelineOptions  # type: ignore\n                        from docling.document_converter import PdfFormatOption  # type: ignore\n\n                        pipe = PdfPipelineOptions()\n                        pipe.do_ocr = False\n\n                        if ocr_engine:\n                            try:\n                                from docling.models.factories import get_ocr_factory  # type: ignore\n                                pipe.do_ocr = True\n                                fac = get_ocr_factory(allow_external_plugins=False)\n                                pipe.ocr_options = fac.create_options(kind=ocr_engine)\n                            except Exception:\n                                # If OCR setup fails, disable it\n                                pipe.do_ocr = False\n\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(pipeline_options=pipe)\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(pipeline_options=pipe)\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception:\n                        return DocumentConverter()\n\n                # --- Vision-Language Model (VLM) pipeline ---\n                if pipeline == \"vlm\":\n                    try:\n                        from docling.datamodel.pipeline_options import VlmPipelineOptions\n                        from docling.datamodel.vlm_model_specs import GRANITEDOCLING_MLX, GRANITEDOCLING_TRANSFORMERS\n                        from docling.document_converter import PdfFormatOption\n                        from docling.pipeline.vlm_pipeline import VlmPipeline\n\n                        vl_pipe = VlmPipelineOptions(\n                            vlm_options=GRANITEDOCLING_TRANSFORMERS,\n                        )\n\n                        if sys.platform == \"darwin\":\n                            try:\n                                import mlx_vlm\n                                vl_pipe.vlm_options = GRANITEDOCLING_MLX\n                            except ImportError as e:\n                                raise e\n\n                        # VLM paths generally don't need OCR; keep OCR off by default here.\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(\n                            pipeline_cls=VlmPipeline,\n                            pipeline_options=vl_pipe\n                        )\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(\n                            pipeline_cls=VlmPipeline,\n                            pipeline_options=vl_pipe\n                        )\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception as e:\n                        raise e\n\n                # --- Fallback: default converter with no special options ---\n                return DocumentConverter()\n\n            def export_markdown(document, ImageRefMode, image_mode, img_ph, pg_ph):\n                try:\n                    mode = getattr(ImageRefMode, image_mode.upper(), image_mode)\n                    return document.export_to_markdown(\n                        image_mode=mode,\n                        image_placeholder=img_ph,\n                        page_break_placeholder=pg_ph,\n                    )\n                except Exception:\n                    try:\n                        return document.export_to_text()\n                    except Exception:\n                        return str(document)\n\n            def to_rows(doc_dict):\n                rows = []\n                for t in doc_dict.get(\"texts\", []):\n                    prov = t.get(\"prov\") or []\n                    page_no = None\n                    if prov and isinstance(prov, list) and isinstance(prov[0], dict):\n                        page_no = prov[0].get(\"page_no\")\n                    rows.append({\n                        \"page_no\": page_no,\n                        \"label\": t.get(\"label\"),\n                        \"text\": t.get(\"text\"),\n                        \"level\": t.get(\"level\"),\n                    })\n                return rows\n\n            def main():\n                cfg = json.loads(sys.stdin.read())\n                file_path = cfg[\"file_path\"]\n                markdown = cfg[\"markdown\"]\n                image_mode = cfg[\"image_mode\"]\n                img_ph = cfg[\"md_image_placeholder\"]\n                pg_ph = cfg[\"md_page_break_placeholder\"]\n                pipeline = cfg[\"pipeline\"]\n                ocr_engine = cfg.get(\"ocr_engine\")\n                meta = {\"file_path\": file_path}\n\n                try:\n                    ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, strategy = try_imports()\n                    converter = create_converter(strategy, InputFormat, DocumentConverter, pipeline, ocr_engine)\n                    try:\n                        res = converter.convert(file_path)\n                    except Exception as e:\n                        print(json.dumps({\"ok\": False, \"error\": f\"Docling conversion error: {e}\", \"meta\": meta}))\n                        return\n\n                    ok = False\n                    if hasattr(res, \"status\"):\n                        try:\n                            ok = (res.status == ConversionStatus.SUCCESS) or (str(res.status).lower() == \"success\")\n                        except Exception:\n                            ok = (str(res.status).lower() == \"success\")\n                    if not ok and hasattr(res, \"document\"):\n                        ok = getattr(res, \"document\", None) is not None\n                    if not ok:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling conversion failed\", \"meta\": meta}))\n                        return\n\n                    doc = getattr(res, \"document\", None)\n                    if doc is None:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling produced no document\", \"meta\": meta}))\n                        return\n\n                    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\") if proc.stderr else \"no output from child process\"\n            return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": original_file_path})\n\n        try:\n            result = json.loads(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={\n                    \"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\",\n                    \"file_path\": original_file_path,\n                },\n            )\n\n        if not result.get(\"ok\"):\n            error_msg = result.get(\"error\", \"Unknown Docling error\")\n            # Override meta file_path with original_file_path to ensure correct path matching\n            meta = result.get(\"meta\", {})\n            meta[\"file_path\"] = original_file_path\n            return Data(data={\"error\": error_msg, **meta})\n\n        meta = result.get(\"meta\", {})\n        # Override meta file_path with original_file_path to ensure correct path matching\n        # The subprocess returns the temp file path, but we need the original S3/local path for rollup_data\n        meta[\"file_path\"] = original_file_path\n        if result.get(\"mode\") == \"markdown\":\n            exported_content = str(result.get(\"text\", \"\"))\n            return Data(\n                text=exported_content,\n                data={\"exported_content\": exported_content, \"export_format\": self.EXPORT_FORMAT, **meta},\n            )\n\n        rows = list(result.get(\"doc\", []))\n        return Data(data={\"doc\": rows, \"export_format\": self.EXPORT_FORMAT, **meta})\n\n    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        # Validate image files to detect content/extension mismatches\n        # This prevents API errors like \"Image does not match the provided media type\"\n        image_extensions = {\"jpeg\", \"jpg\", \"png\", \"gif\", \"webp\", \"bmp\", \"tiff\"}\n        settings = get_settings_service().settings\n        for file in file_list:\n            extension = file.path.suffix[1:].lower()\n            if extension in image_extensions:\n                # Read bytes based on storage type\n                try:\n                    if settings.storage_type == \"s3\":\n                        # For S3 storage, use storage service to read file bytes\n                        file_path_str = str(file.path)\n                        content = run_until_complete(read_file_bytes(file_path_str))\n                    else:\n                        # For local storage, read bytes directly from filesystem\n                        content = file.path.read_bytes()\n\n                    is_valid, error_msg = validate_image_content_type(\n                        str(file.path),\n                        content=content,\n                    )\n                    if not is_valid:\n                        self.log(error_msg)\n                        if not self.silent_errors:\n                            raise ValueError(error_msg)\n                except (OSError, FileNotFoundError) as e:\n                    self.log(f\"Could not read file for validation: {e}\")\n                    # Continue - let it fail later with better error\n\n        # Validate that files requiring Docling are only processed when advanced mode is enabled\n        if not self.advanced_mode:\n            for file in file_list:\n                extension = file.path.suffix[1:].lower()\n                if extension in self.DOCLING_ONLY_EXTENSIONS:\n                    msg = (\n                        f\"File '{file.path.name}' has extension '.{extension}' which requires \"\n                        f\"Advanced Parser mode. Please enable 'Advanced Parser' to process this file.\"\n                    )\n                    self.log(msg)\n                    raise ValueError(msg)\n\n        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                # Handle None case - Docling processing failed or returned None\n                if advanced_data is None:\n                    error_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"error\": \"Docling processing returned no result. Check logs for details.\",\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [error_data]))\n                    continue\n\n                # --- UNNEST: expand each element in `doc` to its own Data row\n                payload = getattr(advanced_data, \"data\", {}) or {}\n\n                # Check for errors first\n                if \"error\" in payload:\n                    error_msg = payload.get(\"error\", \"Unknown error\")\n                    error_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"error\": error_msg,\n                            **{k: v for k, v in payload.items() if k not in (\"error\", \"file_path\")},\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [error_data]))\n                    continue\n\n                doc_rows = payload.get(\"doc\")\n                if isinstance(doc_rows, list) and doc_rows:\n                    # Non-empty list of structured rows\n                    rows: list[Data | None] = [\n                        Data(\n                            data={\n                                \"file_path\": file_path,\n                                **(item if isinstance(item, dict) else {\"value\": item}),\n                            },\n                        )\n                        for item in doc_rows\n                    ]\n                    final_return.extend(self.rollup_data([file], rows))\n                elif isinstance(doc_rows, list) and not doc_rows:\n                    # Empty list - file was processed but no text content found\n                    # Create a Data object indicating no content was extracted\n                    self.log(f\"No text extracted from '{file_path}', creating placeholder data\")\n                    empty_data = Data(\n                        data={\n                            \"file_path\": file_path,\n                            \"text\": \"(No text content extracted from image)\",\n                            \"info\": \"Image processed successfully but contained no extractable text\",\n                            **{k: v for k, v in payload.items() if k != \"doc\"},\n                        },\n                    )\n                    final_return.extend(self.rollup_data([file], [empty_data]))\n                else:\n                    # If not structured, keep as-is (e.g., markdown export or error dict)\n                    # Ensure file_path is set for proper rollup matching\n                    if not payload.get(\"file_path\"):\n                        payload[\"file_path\"] = file_path\n                        # Create new Data with file_path\n                        advanced_data = Data(\n                            data=payload,\n                            text=getattr(advanced_data, \"text\", None),\n                        )\n                    final_return.extend(self.rollup_data([file], [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\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        # Result is a DataFrame - check if it has any rows\n        if result.empty:\n            msg = \"Could not extract content from the provided file(s).\"\n            raise ValueError(msg)\n\n        # Check for error column with error messages\n        if \"error\" in result.columns:\n            errors = result[\"error\"].dropna().tolist()\n            if errors and not any(col in result.columns for col in [\"text\", \"doc\", \"exported_content\"]):\n                raise ValueError(errors[0])\n\n        return result\n\n    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\n        # Result is a DataFrame - check for text or exported_content columns\n        if \"text\" in result.columns and not result[\"text\"].isna().all():\n            text_values = result[\"text\"].dropna().tolist()\n            if text_values:\n                return Message(text=str(text_values[0]))\n\n        if \"exported_content\" in result.columns and not result[\"exported_content\"].isna().all():\n            content_values = result[\"exported_content\"].dropna().tolist()\n            if content_values:\n                return Message(text=str(content_values[0]))\n\n        # Return empty message with info that no text was found\n        return Message(text=\"(No text content extracted from file)\")\n"
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n\n"
               },
-              "concurrency_multithreading": {
-                "_input_type": "IntInput",
-                "advanced": true,
-                "display_name": "Processing Concurrency",
+              "service_account_key": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "GCP Credentials Secret Key",
                 "dynamic": false,
-                "info": "When multiple files are being processed, the number of files to process concurrently.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "concurrency_multithreading",
+                "info": "Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "service_account_key",
                 "override_skip": false,
+                "password": true,
                 "placeholder": "",
-                "required": false,
-                "show": true,
+                "required": true,
+                "show": false,
                 "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "int",
-                "value": 1
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
               },
-              "delete_server_file_after_processing": {
+              "silent_errors": {
                 "_input_type": "BoolInput",
                 "advanced": true,
-                "display_name": "Delete Server File After Processing",
+                "display_name": "Silent Errors",
                 "dynamic": false,
-                "info": "If true, the Server File Path will be deleted after processing.",
+                "info": "If true, errors will not raise an exception.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "delete_server_file_after_processing",
-                "override_skip": false,
+                "name": "silent_errors",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
                 "type": "bool",
-                "value": true
+                "value": false
               },
-              "doc_key": {
-                "_input_type": "MessageTextInput",
-                "advanced": true,
-                "display_name": "Doc Key",
+              "storage_location": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Storage Location",
                 "dynamic": false,
-                "info": "The key to use for the DoclingDocument column.",
-                "input_types": [
-                  "Message"
+                "info": "Choose where to read the file from.",
+                "limit": 1,
+                "name": "storage_location",
+                "options": [
+                  {
+                    "icon": "hard-drive",
+                    "name": "Local"
+                  },
+                  {
+                    "icon": "Amazon",
+                    "name": "AWS"
+                  },
+                  {
+                    "icon": "google",
+                    "name": "Google Drive"
+                  }
                 ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "doc_key",
                 "override_skip": false,
-                "placeholder": "",
+                "placeholder": "Select Location",
+                "real_time_refresh": true,
                 "required": false,
-                "show": false,
+                "search_category": [],
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
                 "track_in_telemetry": false,
-                "type": "str",
-                "value": "doc"
+                "type": "sortableList",
+                "value": ""
               },
-              "file_id": {
-                "_input_type": "StrInput",
-                "advanced": false,
-                "display_name": "Google Drive File ID",
+              "use_multithreading": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "[Deprecated] Use Multithreading",
                 "dynamic": false,
-                "info": "The Google Drive file ID to read. The file must be shared with the service account email.",
+                "info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "file_id",
-                "override_skip": false,
+                "name": "use_multithreading",
                 "placeholder": "",
-                "required": true,
-                "show": false,
+                "required": false,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": ""
+                "type": "bool",
+                "value": true
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "message",
+          "showNode": true,
+          "type": "File"
+        },
+        "dragging": false,
+        "id": "File-gVVqw",
+        "measured": {
+          "height": 214,
+          "width": 320
+        },
+        "position": {
+          "x": 927.3702382252801,
+          "y": 647.5603858397075
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "LanguageModelComponent-DJzkZ",
+          "node": {
+            "base_classes": [
+              "LanguageModel",
+              "Message"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Runs a language model given a specified provider.",
+            "display_name": "Language Model",
+            "documentation": "https://docs.langflow.org/components-models",
+            "edited": false,
+            "field_order": [
+              "model",
+              "api_key",
+              "base_url_ibm_watsonx",
+              "project_id",
+              "ollama_base_url",
+              "input_value",
+              "system_message",
+              "stream",
+              "temperature"
+            ],
+            "frozen": false,
+            "icon": "brain-circuit",
+            "last_updated": "2025-12-11T21:29:10.202Z",
+            "legacy": false,
+            "lf_version": "1.7.0",
+            "metadata": {
+              "code_hash": "7fe3257f2169",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 1
               },
-              "file_path": {
-                "_input_type": "HandleInput",
-                "advanced": true,
-                "display_name": "Server File Path",
-                "dynamic": false,
-                "info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
-                "input_types": [
-                  "Data",
+              "keywords": [
+                "model",
+                "llm",
+                "language model",
+                "large language model"
+              ],
+              "module": "lfx.components.models_and_agents.language_model.LanguageModelComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Model Response",
+                "group_outputs": false,
+                "loop_types": null,
+                "method": "text_response",
+                "name": "text_output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
                   "Message"
                 ],
-                "list": true,
-                "list_add_label": "Add More",
-                "name": "file_path",
-                "override_skip": false,
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "other",
-                "value": ""
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Language Model",
+                "group_outputs": false,
+                "loop_types": null,
+                "method": "build_model",
+                "name": "model_output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "LanguageModel",
+                "tool_mode": true,
+                "types": [
+                  "LanguageModel"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "priority": 0,
+            "template": {
+              "_frontend_node_flow_id": {
+                "value": "524f71dc-cc58-441a-a009-c71d6755765f"
               },
-              "file_path_str": {
-                "_input_type": "StrInput",
+              "_frontend_node_folder_id": {
+                "value": "afaca9ee-97e3-4211-8569-722a4058ea5e"
+              },
+              "_type": "Component",
+              "api_key": {
+                "_input_type": "SecretStrInput",
                 "advanced": true,
-                "display_name": "File Path",
+                "display_name": "API Key",
                 "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",
+                "info": "Model Provider API key",
+                "input_types": [],
                 "load_from_db": false,
-                "name": "file_path_str",
+                "name": "api_key",
                 "override_skip": false,
+                "password": true,
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
-                "tool_mode": true,
-                "trace_as_metadata": true,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "ignore_unspecified_files": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Ignore Unspecified Files",
+              "base_url_ibm_watsonx": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "watsonx API Endpoint",
                 "dynamic": false,
-                "info": "If true, Data with no 'file_path' property will be ignored.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "ignore_unspecified_files",
+                "external_options": {},
+                "info": "The base URL of the API (IBM watsonx.ai only)",
+                "name": "base_url_ibm_watsonx",
+                "options": [
+                  "https://us-south.ml.cloud.ibm.com",
+                  "https://eu-de.ml.cloud.ibm.com",
+                  "https://eu-gb.ml.cloud.ibm.com",
+                  "https://au-syd.ml.cloud.ibm.com",
+                  "https://jp-tok.ml.cloud.ibm.com",
+                  "https://ca-tor.ml.cloud.ibm.com"
+                ],
+                "options_metadata": [],
                 "override_skip": false,
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "show": true,
+                "show": false,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
+                "type": "str",
+                "value": "https://us-south.ml.cloud.ibm.com"
               },
-              "ignore_unsupported_extensions": {
-                "_input_type": "BoolInput",
+              "code": {
                 "advanced": true,
-                "display_name": "Ignore Unsupported Extensions",
-                "dynamic": false,
-                "info": "If true, files with unsupported extensions will not be processed.",
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
                 "list": false,
-                "list_add_label": "Add More",
-                "name": "ignore_unsupported_extensions",
-                "override_skip": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
                 "placeholder": "",
-                "required": false,
+                "required": true,
                 "show": true,
                 "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": true
+                "type": "code",
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
-              "markdown": {
-                "_input_type": "BoolInput",
+              "input_value": {
+                "_input_type": "MessageInput",
                 "advanced": false,
-                "display_name": "Markdown Export",
+                "display_name": "Input",
                 "dynamic": false,
-                "info": "Export processed documents to Markdown format. Only available when advanced mode is enabled.",
+                "info": "The input text to send to the model",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "markdown",
+                "load_from_db": false,
+                "name": "input_value",
                 "override_skip": false,
                 "placeholder": "",
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
               },
-              "md_image_placeholder": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Image placeholder",
+              "is_refresh": false,
+              "model": {
+                "_input_type": "ModelInput",
+                "advanced": false,
+                "display_name": "Language Model",
                 "dynamic": false,
-                "info": "Specify the image placeholder for markdown exports.",
+                "external_options": {
+                  "fields": {
+                    "data": {
+                      "node": {
+                        "display_name": "Connect other models",
+                        "icon": "CornerDownLeft",
+                        "name": "connect_other_models"
+                      }
+                    }
+                  }
+                },
+                "info": "Select your model provider",
+                "input_types": [
+                  "LanguageModel"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "md_image_placeholder",
+                "model_type": "language",
+                "name": "model",
+                "options": [],
                 "override_skip": false,
-                "placeholder": "",
-                "required": false,
-                "show": false,
+                "placeholder": "Setup Provider",
+                "real_time_refresh": true,
+                "refresh_button": true,
+                "required": true,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
-                "trace_as_metadata": true,
+                "trace_as_input": true,
                 "track_in_telemetry": false,
-                "type": "str",
-                "value": "<!-- image -->"
+                "type": "model",
+                "value": []
               },
-              "md_page_break_placeholder": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Page break placeholder",
+              "ollama_base_url": {
+                "_input_type": "MessageInput",
+                "advanced": false,
+                "display_name": "Ollama API URL",
                 "dynamic": false,
-                "info": "Add this placeholder between pages in the markdown output.",
+                "info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "md_page_break_placeholder",
+                "name": "ollama_base_url",
                 "override_skip": false,
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
                 "show": false,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "ocr_engine": {
-                "_input_type": "DropdownInput",
-                "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "OCR Engine",
-                "dynamic": false,
-                "external_options": {},
-                "info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
-                "name": "ocr_engine",
-                "options": [
-                  "None",
-                  "easyocr"
-                ],
-                "options_metadata": [],
-                "override_skip": false,
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "toggle": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "str",
-                "value": "easyocr"
-              },
-              "path": {
-                "_input_type": "FileInput",
+              "project_id": {
+                "_input_type": "StrInput",
                 "advanced": false,
-                "display_name": "Files",
+                "display_name": "watsonx Project ID",
                 "dynamic": false,
-                "fileTypes": [
-                  "csv",
-                  "json",
-                  "pdf",
-                  "txt",
-                  "md",
-                  "mdx",
-                  "yaml",
-                  "yml",
-                  "xml",
-                  "html",
-                  "htm",
-                  "docx",
-                  "py",
-                  "sh",
-                  "sql",
-                  "js",
-                  "ts",
-                  "tsx",
-                  "adoc",
-                  "asciidoc",
-                  "asc",
-                  "bmp",
-                  "dotx",
-                  "dotm",
-                  "docm",
-                  "jpg",
-                  "jpeg",
-                  "png",
-                  "potx",
-                  "ppsx",
-                  "pptm",
-                  "potm",
-                  "ppsm",
-                  "pptx",
-                  "tiff",
-                  "xls",
-                  "xlsx",
-                  "xhtml",
-                  "webp",
-                  "zip",
-                  "tar",
-                  "tgz",
-                  "bz2",
-                  "gz"
-                ],
-                "file_path": [],
-                "info": "Supported file extensions: csv, json, pdf, txt, md, mdx, yaml, yml, xml, html, htm, docx, py, sh, sql, js, ts, tsx, adoc, asciidoc, asc, bmp, dotx, dotm, docm, jpg, jpeg, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, xls, xlsx, xhtml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
-                "list": true,
+                "info": "The project ID associated with the foundation model (IBM watsonx.ai only)",
+                "list": false,
                 "list_add_label": "Add More",
-                "name": "path",
+                "load_from_db": false,
+                "name": "project_id",
                 "override_skip": false,
                 "placeholder": "",
-                "real_time_refresh": true,
                 "required": false,
-                "show": true,
-                "temp_file": false,
+                "show": false,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "track_in_telemetry": false,
-                "type": "file",
+                "type": "str",
                 "value": ""
               },
-              "pipeline": {
-                "_input_type": "DropdownInput",
+              "stream": {
+                "_input_type": "BoolInput",
                 "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Pipeline",
+                "display_name": "Stream",
                 "dynamic": false,
-                "external_options": {},
-                "info": "Docling pipeline to use",
-                "name": "pipeline",
-                "options": [
-                  "standard",
-                  "vlm"
-                ],
-                "options_metadata": [],
+                "info": "Whether to stream the response",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "stream",
                 "override_skip": false,
                 "placeholder": "",
-                "real_time_refresh": true,
                 "required": false,
                 "show": true,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "track_in_telemetry": true,
-                "type": "str",
-                "value": "standard"
+                "type": "bool",
+                "value": false
               },
-              "s3_file_key": {
-                "_input_type": "StrInput",
+              "system_message": {
+                "_input_type": "MultilineInput",
                 "advanced": false,
-                "display_name": "S3 File Key",
+                "ai_enabled": false,
+                "copy_field": false,
+                "display_name": "System Message",
                 "dynamic": false,
-                "info": "The key (path) of the file in S3 bucket.",
+                "info": "A system message that helps set the behavior of the assistant",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "s3_file_key",
+                "multiline": true,
+                "name": "system_message",
                 "override_skip": false,
                 "placeholder": "",
-                "required": true,
-                "show": false,
+                "required": false,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
                 "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "separator": {
-                "_input_type": "StrInput",
+              "temperature": {
+                "_input_type": "SliderInput",
                 "advanced": true,
-                "display_name": "Separator",
+                "display_name": "Temperature",
                 "dynamic": false,
-                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "info": "Controls randomness in responses",
+                "max_label": "",
+                "max_label_icon": "",
+                "min_label": "",
+                "min_label_icon": "",
+                "name": "temperature",
+                "override_skip": false,
+                "placeholder": "",
+                "range_spec": {
+                  "max": 1,
+                  "min": 0,
+                  "step": 0.01,
+                  "step_type": "float"
+                },
+                "required": false,
+                "show": true,
+                "slider_buttons": false,
+                "slider_buttons_options": [],
+                "slider_input": false,
+                "title_case": false,
+                "tool_mode": false,
+                "track_in_telemetry": false,
+                "type": "slider",
+                "value": 0.1
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "text_output",
+          "showNode": true,
+          "type": "LanguageModelComponent"
+        },
+        "dragging": false,
+        "id": "LanguageModelComponent-DJzkZ",
+        "measured": {
+          "height": 534,
+          "width": 320
+        },
+        "position": {
+          "x": 2174.626510909065,
+          "y": 439.5147119393939
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "note-Sm9Ca",
+          "node": {
+            "description": "### 💡 Add your OpenAI API key here",
+            "display_name": "",
+            "documentation": "",
+            "template": {
+              "backgroundColor": "transparent"
+            }
+          },
+          "type": "note"
+        },
+        "dragging": false,
+        "id": "note-Sm9Ca",
+        "measured": {
+          "height": 324,
+          "width": 324
+        },
+        "position": {
+          "x": 2177.24956539088,
+          "y": 384.73691533198325
+        },
+        "selected": false,
+        "type": "noteNode"
+      },
+      {
+        "data": {
+          "id": "StructuredOutput-wsAT3",
+          "node": {
+            "base_classes": [
+              "Data",
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Uses an LLM to generate structured data. Ideal for extraction and consistency.",
+            "display_name": "Structured Output",
+            "documentation": "https://docs.langflow.org/components-processing#structured-output",
+            "edited": false,
+            "field_order": [
+              "llm",
+              "input_value",
+              "system_prompt",
+              "schema_name",
+              "output_schema"
+            ],
+            "frozen": false,
+            "icon": "braces",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "058ca1f51e9f",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pydantic",
+                    "version": "2.11.10"
+                  },
+                  {
+                    "name": "trustcall",
+                    "version": "0.0.39"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 3
+              },
+              "module": "lfx.components.llm_operations.structured_output.StructuredOutputComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Structured Output",
+                "group_outputs": false,
+                "method": "build_structured_output",
+                "name": "structured_output",
+                "selected": null,
+                "tool_mode": true,
+                "types": [
+                  "Data"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Structured Output",
+                "group_outputs": false,
+                "method": "build_structured_dataframe",
+                "name": "dataframe_output",
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "api_key": {
+                "_input_type": "SecretStrInput",
+                "advanced": true,
+                "display_name": "API Key",
+                "dynamic": false,
+                "info": "Model Provider API key",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "api_key",
+                "override_skip": false,
+                "password": true,
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from pydantic import BaseModel, Field, create_model\nfrom trustcall import create_extractor\n\nfrom lfx.base.models.chat_result import get_chat_result\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.helpers.base_model import build_model_from_schema\nfrom lfx.io import (\n    MessageTextInput,\n    ModelInput,\n    MultilineInput,\n    Output,\n    SecretStrInput,\n    TableInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.table import EditMode\n\n\nclass StructuredOutputComponent(Component):\n    display_name = \"Structured Output\"\n    description = \"Uses an LLM to generate structured data. Ideal for extraction and consistency.\"\n    documentation: str = \"https://docs.langflow.org/structured-output\"\n    name = \"StructuredOutput\"\n    icon = \"braces\"\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        MultilineInput(\n            name=\"input_value\",\n            display_name=\"Input Message\",\n            info=\"The input message to the language model.\",\n            tool_mode=True,\n            required=True,\n        ),\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Format Instructions\",\n            info=\"The instructions to the language model for formatting the output.\",\n            value=(\n                \"You are an AI that extracts structured JSON objects from unstructured text. \"\n                \"Use a predefined schema with expected types (str, int, float, bool, dict). \"\n                \"Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. \"\n                \"Fill missing or ambiguous values with defaults: null for missing values. \"\n                \"Remove exact duplicates but keep variations that have different field values. \"\n                \"Always return valid JSON in the expected format, never throw errors. \"\n                \"If multiple objects can be extracted, return them all in the structured format.\"\n            ),\n            required=True,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"schema_name\",\n            display_name=\"Schema Name\",\n            info=\"Provide a name for the output data schema.\",\n            advanced=True,\n        ),\n        TableInput(\n            name=\"output_schema\",\n            display_name=\"Output Schema\",\n            info=\"Define the structure and data types for the model's output.\",\n            required=True,\n            # TODO: remove deault value\n            table_schema=[\n                {\n                    \"name\": \"name\",\n                    \"display_name\": \"Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Specify the name of the output field.\",\n                    \"default\": \"field\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"description\",\n                    \"display_name\": \"Description\",\n                    \"type\": \"str\",\n                    \"description\": \"Describe the purpose of the output field.\",\n                    \"default\": \"description of field\",\n                    \"edit_mode\": EditMode.POPOVER,\n                },\n                {\n                    \"name\": \"type\",\n                    \"display_name\": \"Type\",\n                    \"type\": \"str\",\n                    \"edit_mode\": EditMode.INLINE,\n                    \"description\": (\"Indicate the data type of the output field (e.g., str, int, float, bool, dict).\"),\n                    \"options\": [\"str\", \"int\", \"float\", \"bool\", \"dict\"],\n                    \"default\": \"str\",\n                },\n                {\n                    \"name\": \"multiple\",\n                    \"display_name\": \"As List\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Set to True if this output field should be a list of the specified type.\",\n                    \"default\": \"False\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"name\": \"field\",\n                    \"description\": \"description of field\",\n                    \"type\": \"str\",\n                    \"multiple\": \"False\",\n                }\n            ],\n        ),\n    ]\n\n    outputs = [\n        Output(\n            name=\"structured_output\",\n            display_name=\"Structured Output\",\n            method=\"build_structured_output\",\n        ),\n        Output(\n            name=\"dataframe_output\",\n            display_name=\"Structured Output\",\n            method=\"build_structured_dataframe\",\n        ),\n    ]\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        return update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n    def build_structured_output_base(self):\n        schema_name = self.schema_name or \"OutputModel\"\n\n        llm = get_llm(model=self.model, user_id=self.user_id, api_key=self.api_key)\n\n        if not hasattr(llm, \"with_structured_output\"):\n            msg = \"Language model does not support structured output.\"\n            raise TypeError(msg)\n        if not self.output_schema:\n            msg = \"Output schema cannot be empty\"\n            raise ValueError(msg)\n\n        output_model_ = build_model_from_schema(self.output_schema)\n        output_model = create_model(\n            schema_name,\n            __doc__=f\"A list of {schema_name}.\",\n            objects=(\n                list[output_model_],\n                Field(\n                    description=f\"A list of {schema_name}.\",  # type: ignore[valid-type]\n                    min_length=1,  # help ensure non-empty output\n                ),\n            ),\n        )\n        # Tracing config\n        config_dict = {\n            \"run_name\": self.display_name,\n            \"project_name\": self.get_project_name(),\n            \"callbacks\": self.get_langchain_callbacks(),\n        }\n        # Generate structured output using Trustcall first, then fallback to Langchain if it fails\n        result = self._extract_output_with_trustcall(llm, output_model, config_dict)\n        if result is None:\n            result = self._extract_output_with_langchain(llm, output_model, config_dict)\n\n        # OPTIMIZATION NOTE: Simplified processing based on trustcall response structure\n        # Handle non-dict responses (shouldn't happen with trustcall, but defensive)\n        if not isinstance(result, dict):\n            return result\n\n        # Extract first response and convert BaseModel to dict\n        responses = result.get(\"responses\", [])\n        if not responses:\n            return result\n\n        # Convert BaseModel to dict (creates the \"objects\" key)\n        first_response = responses[0]\n        structured_data = first_response\n        if isinstance(first_response, BaseModel):\n            structured_data = first_response.model_dump()\n        # Extract the objects array (guaranteed to exist due to our Pydantic model structure)\n        return structured_data.get(\"objects\", structured_data)\n\n    def build_structured_output(self) -> Data:\n        output = self.build_structured_output_base()\n        if not isinstance(output, list) or not output:\n            # handle empty or unexpected type case\n            msg = \"No structured output returned\"\n            raise ValueError(msg)\n        if len(output) == 1:\n            return Data(data=output[0])\n        if len(output) > 1:\n            # Multiple outputs - wrap them in a results container\n            return Data(data={\"results\": output})\n        return Data()\n\n    def build_structured_dataframe(self) -> DataFrame:\n        output = self.build_structured_output_base()\n        if not isinstance(output, list) or not output:\n            # handle empty or unexpected type case\n            msg = \"No structured output returned\"\n            raise ValueError(msg)\n        if len(output) == 1:\n            # For single dictionary, wrap in a list to create DataFrame with one row\n            return DataFrame([output[0]])\n        if len(output) > 1:\n            # Multiple outputs - convert to DataFrame directly\n            return DataFrame(output)\n        return DataFrame()\n\n    def _extract_output_with_trustcall(self, llm, schema: BaseModel, config_dict: dict) -> list[BaseModel] | None:\n        try:\n            llm_with_structured_output = create_extractor(llm, tools=[schema], tool_choice=schema.__name__)\n            result = get_chat_result(\n                runnable=llm_with_structured_output,\n                system_message=self.system_prompt,\n                input_value=self.input_value,\n                config=config_dict,\n            )\n        except Exception as e:  # noqa: BLE001\n            logger.warning(\n                f\"Trustcall extraction failed, falling back to Langchain: {e} \"\n                \"(Note: This may not be an error—some models or configurations do not support tool calling. \"\n                \"Falling back is normal in such cases.)\"\n            )\n            return None\n        return result or None  # langchain fallback is used if error occurs or the result is empty\n\n    def _extract_output_with_langchain(self, llm, schema: BaseModel, config_dict: dict) -> list[BaseModel] | None:\n        try:\n            llm_with_structured_output = llm.with_structured_output(schema)\n            result = get_chat_result(\n                runnable=llm_with_structured_output,\n                system_message=self.system_prompt,\n                input_value=self.input_value,\n                config=config_dict,\n            )\n            if isinstance(result, BaseModel):\n                result = result.model_dump()\n                result = result.get(\"objects\", result)\n        except Exception as fallback_error:\n            msg = (\n                f\"Model does not support tool calling (trustcall failed) \"\n                f\"and fallback with_structured_output also failed: {fallback_error}\"\n            )\n            raise ValueError(msg) from fallback_error\n\n        return result or None\n"
+              },
+              "input_value": {
+                "_input_type": "MultilineInput",
+                "advanced": false,
+                "copy_field": false,
+                "display_name": "Input Message",
+                "dynamic": false,
+                "info": "The input message to the language model.",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "separator",
-                "override_skip": false,
+                "multiline": true,
+                "name": "input_value",
                 "placeholder": "",
-                "required": false,
+                "required": true,
                 "show": true,
                 "title_case": false,
-                "tool_mode": false,
+                "tool_mode": true,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
                 "type": "str",
-                "value": "\n\n"
+                "value": ""
               },
-              "service_account_key": {
-                "_input_type": "SecretStrInput",
+              "model": {
+                "_input_type": "ModelInput",
                 "advanced": false,
-                "display_name": "GCP Credentials Secret Key",
+                "display_name": "Language Model",
                 "dynamic": false,
-                "info": "Your Google Cloud Platform service account JSON key as a secret string (complete JSON content).",
+                "external_options": {
+                  "fields": {
+                    "data": {
+                      "node": {
+                        "display_name": "Connect other models",
+                        "icon": "CornerDownLeft",
+                        "name": "connect_other_models"
+                      }
+                    }
+                  }
+                },
+                "info": "Select your model provider",
                 "input_types": [],
-                "load_from_db": true,
-                "name": "service_account_key",
+                "list": false,
+                "list_add_label": "Add More",
+                "model_type": "language",
+                "name": "model",
                 "override_skip": false,
-                "password": true,
-                "placeholder": "",
+                "placeholder": "Setup Provider",
+                "real_time_refresh": true,
+                "refresh_button": true,
                 "required": true,
-                "show": false,
+                "show": true,
                 "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
                 "track_in_telemetry": false,
-                "type": "str",
+                "type": "model",
                 "value": ""
               },
-              "silent_errors": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Silent Errors",
+              "output_schema": {
+                "_input_type": "TableInput",
+                "advanced": false,
+                "display_name": "Output Schema",
                 "dynamic": false,
-                "info": "If true, errors will not raise an exception.",
-                "list": false,
+                "info": "Define the structure and data types for the model's output.",
+                "is_list": true,
                 "list_add_label": "Add More",
-                "name": "silent_errors",
-                "override_skip": false,
+                "name": "output_schema",
                 "placeholder": "",
-                "required": false,
+                "required": true,
                 "show": true,
+                "table_icon": "Table",
+                "table_schema": [
+                  {
+                    "default": "field",
+                    "description": "Specify the name of the output field.",
+                    "display_name": "Name",
+                    "edit_mode": "inline",
+                    "formatter": "text",
+                    "name": "name",
+                    "type": "str"
+                  },
+                  {
+                    "default": "description of field",
+                    "description": "Describe the purpose of the output field.",
+                    "display_name": "Description",
+                    "edit_mode": "popover",
+                    "formatter": "text",
+                    "name": "description",
+                    "type": "str"
+                  },
+                  {
+                    "default": "str",
+                    "description": "Indicate the data type of the output field (e.g., str, int, float, bool, dict).",
+                    "display_name": "Type",
+                    "edit_mode": "inline",
+                    "formatter": "text",
+                    "name": "type",
+                    "options": [
+                      "str",
+                      "int",
+                      "float",
+                      "bool",
+                      "dict"
+                    ],
+                    "type": "str"
+                  },
+                  {
+                    "default": "False",
+                    "description": "Set to True if this output field should be a list of the specified type.",
+                    "display_name": "As List",
+                    "edit_mode": "inline",
+                    "formatter": "text",
+                    "name": "multiple",
+                    "type": "boolean"
+                  }
+                ],
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
-              },
-              "storage_location": {
-                "_input_type": "SortableListInput",
-                "advanced": false,
-                "display_name": "Storage Location",
-                "dynamic": false,
-                "info": "Choose where to read the file from.",
-                "limit": 1,
-                "name": "storage_location",
-                "options": [
+                "trigger_icon": "Table",
+                "trigger_text": "Open table",
+                "type": "table",
+                "value": [
                   {
-                    "icon": "hard-drive",
-                    "name": "Local"
+                    "description": "Full name of the candidate",
+                    "multiple": "False",
+                    "name": "full_name",
+                    "type": "str"
                   },
                   {
-                    "icon": "Amazon",
-                    "name": "AWS"
+                    "description": "Email ID",
+                    "multiple": "False",
+                    "name": "email",
+                    "type": "str"
                   },
                   {
-                    "icon": "google",
-                    "name": "Google Drive"
+                    "description": "Contact Number",
+                    "multiple": "False",
+                    "name": "phone_number",
+                    "type": "str"
+                  },
+                  {
+                    "description": "LinkedIn URL",
+                    "multiple": "False",
+                    "name": "linkedin",
+                    "type": "str"
+                  },
+                  {
+                    "description": "GitHub profile URL (if applicable)",
+                    "multiple": "False",
+                    "name": "github",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Personal website or portfolio URL",
+                    "multiple": "False",
+                    "name": "portfolio",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Visa/work authorization details (if applicable)",
+                    "multiple": "False",
+                    "name": "visa_status",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Short professional summary or objective statement",
+                    "multiple": "False",
+                    "name": "summary",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Dictionaries of experience details with following keys:\\n    \\\"job_title\\\": Job position/title,\\n\\t\\\"company_name\\\": Employer or organization\\n\\t\\\"location\\\": Job location (remote/in-office)\\n\\t\\\"start_date\\\": Start date (YYYY-MM)\\n\\t\\\"end_date\\\": End date or \\\"Present\\\"\\n\\t\\\"responsibilities\\\": List of responsibilities and tasks\\n\\t\\\"achievements\\\": List of key achievements and contributions",
+                    "multiple": "True",
+                    "name": "experience",
+                    "type": "dict"
+                  },
+                  {
+                    "description": "Dictionaries of Education details with following keys:\\n\\\"degree\\\": Degree obtained (e.g., B.Sc., M.Sc., Ph.D.),\\n\\\"field_of_study\\\": Major or specialization,\\n\\\"institution\\\": University/college name,\\n\\\"location\\\": Location of institution,\\n\\\"start_date\\\": Start date (YYYY-MM),\\n\\\"end_date\\\": Graduation/completion date (YYYY-MM),\\n\\\"gpa\\\": GPA/grade (if available),\\n\\\"relevant_courses\\\": List of relevant coursework (if applicable)",
+                    "multiple": "True",
+                    "name": "education",
+                    "type": "dict"
+                  },
+                  {
+                    "description": "Skills mentioned in the resume. Comma separated.",
+                    "multiple": "True",
+                    "name": "skills",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Title and description and details of the project. Including the skills and technologies used.",
+                    "multiple": "False",
+                    "name": "projects",
+                    "type": "str"
                   }
+                ]
+              },
+              "schema_name": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Schema Name",
+                "dynamic": false,
+                "info": "Provide a name for the output data schema.",
+                "input_types": [
+                  "Message"
                 ],
-                "override_skip": false,
-                "placeholder": "Select Location",
-                "real_time_refresh": true,
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "schema_name",
+                "placeholder": "",
                 "required": false,
-                "search_category": [],
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "sortableList",
+                "type": "str",
                 "value": ""
               },
-              "use_multithreading": {
-                "_input_type": "BoolInput",
+              "system_prompt": {
+                "_input_type": "MultilineInput",
                 "advanced": true,
-                "display_name": "[Deprecated] Use Multithreading",
+                "copy_field": false,
+                "display_name": "Format Instructions",
                 "dynamic": false,
-                "info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
+                "info": "The instructions to the language model for formatting the output.",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "use_multithreading",
-                "override_skip": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "system_prompt",
                 "placeholder": "",
-                "required": false,
+                "required": true,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": true
+                "type": "str",
+                "value": "You are an AI that extracts structured JSON objects from unstructured text. Use a predefined schema with expected types (str, int, float, bool, dict). Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. Fill missing or ambiguous values with defaults: null for missing values. Remove exact duplicates but keep variations that have different field values. Always return valid JSON in the expected format, never throw errors. If multiple objects can be extracted, return them all in the structured format."
               }
             },
             "tool_mode": false
           },
+          "selected_output": "dataframe_output",
           "showNode": true,
-          "type": "File"
+          "type": "StructuredOutput"
         },
         "dragging": false,
-        "id": "File-Ln2gO",
+        "id": "StructuredOutput-wsAT3",
         "measured": {
-          "height": 341,
+          "height": 349,
           "width": 320
         },
         "position": {
-          "x": 939.716428493645,
-          "y": 648.3992877545212
+          "x": 1308.5338025647359,
+          "y": 651.6998573907567
         },
-        "selected": true,
+        "selected": false,
         "type": "genericNode"
       }
     ],
     "viewport": {
-      "x": -109.59928978699065,
-      "y": 92.33264934787798,
-      "zoom": 0.42585711094575973
+      "x": -89.9205649953526,
+      "y": 43.735261805036544,
+      "zoom": 0.5746419520979581
     }
   },
   "description": "This template transforms PDF or TXT resume documents into structured JSON, generating a portfolio website HTML code from the structured data.",
   "endpoint_name": null,
-  "id": "89c8132e-a746-460b-b091-24b7b9279147",
+  "id": "34740f33-b354-440e-a984-fc51079578e7",
   "is_component": false,
-  "last_tested_version": "1.7.0",
+  "last_tested_version": "1.6.0",
   "name": "Portfolio Website Code Generator",
   "tags": [
     "chatbots",