langflow-base-nightly 1.7.1.dev0__py3-none-any.whl → 1.7.1.dev1__py3-none-any.whl

langflow/initial_setup/starter_projects/Vector Store RAG.json

@@ -7,7 +7,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "ChatInput",
-            "id": "ChatInput-bK5uZ",
+            "id": "ChatInput-8l9oz",
             "name": "message",
             "output_types": [
               "Message"
@@ -15,7 +15,7 @@
           },
           "targetHandle": {
             "fieldName": "question",
-            "id": "Prompt-zBlCK",
+            "id": "Prompt-ML5XQ",
             "inputTypes": [
               "Message",
               "Text"
@@ -23,12 +23,12 @@
             "type": "str"
           }
         },
-        "id": "reactflow__edge-ChatInput-bK5uZ{œdataTypeœ:œChatInputœ,œidœ:œChatInput-bK5uZœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-Prompt-zBlCK{œfieldNameœ:œquestionœ,œidœ:œPrompt-zBlCKœ,œinputTypesœ:[œMessageœ,œTextœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-ChatInput-8l9oz{œdataTypeœ:œChatInputœ,œidœ:œChatInput-8l9ozœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-Prompt-ML5XQ{œfieldNameœ:œquestionœ,œidœ:œPrompt-ML5XQœ,œinputTypesœ:[œMessageœ,œTextœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "ChatInput-bK5uZ",
-        "sourceHandle": "{œdataTypeœ: œChatInputœ, œidœ: œChatInput-bK5uZœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "Prompt-zBlCK",
-        "targetHandle": "{œfieldNameœ: œquestionœ, œidœ: œPrompt-zBlCKœ, œinputTypesœ: [œMessageœ, œTextœ], œtypeœ: œstrœ}"
+        "source": "ChatInput-8l9oz",
+        "sourceHandle": "{œdataTypeœ: œChatInputœ, œidœ: œChatInput-8l9ozœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "Prompt-ML5XQ",
+        "targetHandle": "{œfieldNameœ: œquestionœ, œidœ: œPrompt-ML5XQœ, œinputTypesœ: [œMessageœ, œTextœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
@@ -36,7 +36,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "parser",
-            "id": "parser-brnh5",
+            "id": "parser-oHf4E",
             "name": "parsed_text",
             "output_types": [
               "Message"
@@ -44,7 +44,7 @@
           },
           "targetHandle": {
             "fieldName": "context",
-            "id": "Prompt-zBlCK",
+            "id": "Prompt-ML5XQ",
             "inputTypes": [
               "Message",
               "Text"
@@ -52,12 +52,42 @@
             "type": "str"
           }
         },
-        "id": "reactflow__edge-parser-brnh5{œdataTypeœ:œparserœ,œidœ:œparser-brnh5œ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}-Prompt-zBlCK{œfieldNameœ:œcontextœ,œidœ:œPrompt-zBlCKœ,œinputTypesœ:[œMessageœ,œTextœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-parser-oHf4E{œdataTypeœ:œparserœ,œidœ:œparser-oHf4Eœ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}-Prompt-ML5XQ{œfieldNameœ:œcontextœ,œidœ:œPrompt-ML5XQœ,œinputTypesœ:[œMessageœ,œTextœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "parser-brnh5",
-        "sourceHandle": "{œdataTypeœ: œparserœ, œidœ: œparser-brnh5œ, œnameœ: œparsed_textœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "Prompt-zBlCK",
-        "targetHandle": "{œfieldNameœ: œcontextœ, œidœ: œPrompt-zBlCKœ, œinputTypesœ: [œMessageœ, œTextœ], œtypeœ: œstrœ}"
+        "source": "parser-oHf4E",
+        "sourceHandle": "{œdataTypeœ: œparserœ, œidœ: œparser-oHf4Eœ, œnameœ: œparsed_textœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "Prompt-ML5XQ",
+        "targetHandle": "{œfieldNameœ: œcontextœ, œidœ: œPrompt-ML5XQœ, œinputTypesœ: [œMessageœ, œTextœ], œtypeœ: œstrœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "File",
+            "id": "File-7D3hP",
+            "name": "message",
+            "output_types": [
+              "Message"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "data_inputs",
+            "id": "SplitText-4s7Dt",
+            "inputTypes": [
+              "Data",
+              "DataFrame",
+              "Message"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "reactflow__edge-File-7D3hP{œdataTypeœ:œFileœ,œidœ:œFile-7D3hPœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-SplitText-4s7Dt{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-4s7Dtœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "File-7D3hP",
+        "sourceHandle": "{œdataTypeœ: œFileœ, œidœ: œFile-7D3hPœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "SplitText-4s7Dt",
+        "targetHandle": "{œfieldNameœ: œdata_inputsœ, œidœ: œSplitText-4s7Dtœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}"
       },
       {
         "animated": false,
@@ -65,7 +95,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "Prompt",
-            "id": "Prompt-zBlCK",
+            "id": "Prompt-ML5XQ",
             "name": "prompt",
             "output_types": [
               "Message"
@@ -73,19 +103,19 @@
           },
           "targetHandle": {
             "fieldName": "input_value",
-            "id": "LanguageModelComponent-rL7g3",
+            "id": "LanguageModelComponent-Wqbva",
             "inputTypes": [
               "Message"
             ],
             "type": "str"
           }
         },
-        "id": "reactflow__edge-Prompt-zBlCK{œdataTypeœ:œPromptœ,œidœ:œPrompt-zBlCKœ,œnameœ:œpromptœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-rL7g3{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-rL7g3œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-Prompt-ML5XQ{œdataTypeœ:œPromptœ,œidœ:œPrompt-ML5XQœ,œnameœ:œpromptœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-Wqbva{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-Wqbvaœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "Prompt-zBlCK",
-        "sourceHandle": "{œdataTypeœ: œPromptœ, œidœ: œPrompt-zBlCKœ, œnameœ: œpromptœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "LanguageModelComponent-rL7g3",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œLanguageModelComponent-rL7g3œ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
+        "source": "Prompt-ML5XQ",
+        "sourceHandle": "{œdataTypeœ: œPromptœ, œidœ: œPrompt-ML5XQœ, œnameœ: œpromptœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "LanguageModelComponent-Wqbva",
+        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œLanguageModelComponent-Wqbvaœ, œinputTypesœ: [œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
@@ -93,7 +123,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "LanguageModelComponent",
-            "id": "LanguageModelComponent-rL7g3",
+            "id": "LanguageModelComponent-Wqbva",
             "name": "text_output",
             "output_types": [
               "Message"
@@ -101,7 +131,7 @@
           },
           "targetHandle": {
             "fieldName": "input_value",
-            "id": "ChatOutput-G4VgE",
+            "id": "ChatOutput-g0Phk",
             "inputTypes": [
               "Data",
               "DataFrame",
@@ -110,12 +140,12 @@
             "type": "str"
           }
         },
-        "id": "reactflow__edge-LanguageModelComponent-rL7g3{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-rL7g3œ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-G4VgE{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-G4VgEœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œstrœ}",
+        "id": "reactflow__edge-LanguageModelComponent-Wqbva{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-Wqbvaœ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-g0Phk{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-g0Phkœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œstrœ}",
         "selected": false,
-        "source": "LanguageModelComponent-rL7g3",
-        "sourceHandle": "{œdataTypeœ: œLanguageModelComponentœ, œidœ: œLanguageModelComponent-rL7g3œ, œnameœ: œtext_outputœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "ChatOutput-G4VgE",
-        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-G4VgEœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œstrœ}"
+        "source": "LanguageModelComponent-Wqbva",
+        "sourceHandle": "{œdataTypeœ: œLanguageModelComponentœ, œidœ: œLanguageModelComponent-Wqbvaœ, œnameœ: œtext_outputœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "ChatOutput-g0Phk",
+        "targetHandle": "{œfieldNameœ: œinput_valueœ, œidœ: œChatOutput-g0Phkœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œstrœ}"
       },
       {
         "animated": false,
@@ -123,7 +153,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "SplitText",
-            "id": "SplitText-1fBfh",
+            "id": "SplitText-4s7Dt",
             "name": "dataframe",
             "output_types": [
               "DataFrame"
@@ -131,7 +161,7 @@
           },
           "targetHandle": {
             "fieldName": "ingest_data",
-            "id": "AstraDB-ECtXX",
+            "id": "AstraDB-TCSqR",
             "inputTypes": [
               "Data",
               "DataFrame"
@@ -139,12 +169,12 @@
             "type": "other"
           }
         },
-        "id": "reactflow__edge-SplitText-1fBfh{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-1fBfhœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-AstraDB-ECtXX{œfieldNameœ:œingest_dataœ,œidœ:œAstraDB-ECtXXœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
+        "id": "reactflow__edge-SplitText-4s7Dt{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-4s7Dtœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-AstraDB-TCSqR{œfieldNameœ:œingest_dataœ,œidœ:œAstraDB-TCSqRœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
         "selected": false,
-        "source": "SplitText-1fBfh",
-        "sourceHandle": "{œdataTypeœ: œSplitTextœ, œidœ: œSplitText-1fBfhœ, œnameœ: œdataframeœ, œoutput_typesœ: [œDataFrameœ]}",
-        "target": "AstraDB-ECtXX",
-        "targetHandle": "{œfieldNameœ: œingest_dataœ, œidœ: œAstraDB-ECtXXœ, œinputTypesœ: [œDataœ, œDataFrameœ], œtypeœ: œotherœ}"
+        "source": "SplitText-4s7Dt",
+        "sourceHandle": "{œdataTypeœ: œSplitTextœ, œidœ: œSplitText-4s7Dtœ, œnameœ: œdataframeœ, œoutput_typesœ: [œDataFrameœ]}",
+        "target": "AstraDB-TCSqR",
+        "targetHandle": "{œfieldNameœ: œingest_dataœ, œidœ: œAstraDB-TCSqRœ, œinputTypesœ: [œDataœ, œDataFrameœ], œtypeœ: œotherœ}"
       },
       {
         "animated": false,
@@ -152,7 +182,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "ChatInput",
-            "id": "ChatInput-bK5uZ",
+            "id": "ChatInput-8l9oz",
             "name": "message",
             "output_types": [
               "Message"
@@ -160,19 +190,19 @@
           },
           "targetHandle": {
             "fieldName": "search_query",
-            "id": "AstraDB-RaUqw",
+            "id": "AstraDB-BteL9",
             "inputTypes": [
               "Message"
             ],
             "type": "query"
           }
         },
-        "id": "reactflow__edge-ChatInput-bK5uZ{œdataTypeœ:œChatInputœ,œidœ:œChatInput-bK5uZœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-AstraDB-RaUqw{œfieldNameœ:œsearch_queryœ,œidœ:œAstraDB-RaUqwœ,œinputTypesœ:[œMessageœ],œtypeœ:œqueryœ}",
+        "id": "reactflow__edge-ChatInput-8l9oz{œdataTypeœ:œChatInputœ,œidœ:œChatInput-8l9ozœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-AstraDB-BteL9{œfieldNameœ:œsearch_queryœ,œidœ:œAstraDB-BteL9œ,œinputTypesœ:[œMessageœ],œtypeœ:œqueryœ}",
         "selected": false,
-        "source": "ChatInput-bK5uZ",
-        "sourceHandle": "{œdataTypeœ: œChatInputœ, œidœ: œChatInput-bK5uZœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "AstraDB-RaUqw",
-        "targetHandle": "{œfieldNameœ: œsearch_queryœ, œidœ: œAstraDB-RaUqwœ, œinputTypesœ: [œMessageœ], œtypeœ: œqueryœ}"
+        "source": "ChatInput-8l9oz",
+        "sourceHandle": "{œdataTypeœ: œChatInputœ, œidœ: œChatInput-8l9ozœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
+        "target": "AstraDB-BteL9",
+        "targetHandle": "{œfieldNameœ: œsearch_queryœ, œidœ: œAstraDB-BteL9œ, œinputTypesœ: [œMessageœ], œtypeœ: œqueryœ}"
       },
       {
         "animated": false,
@@ -180,7 +210,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "AstraDB",
-            "id": "AstraDB-RaUqw",
+            "id": "AstraDB-BteL9",
             "name": "dataframe",
             "output_types": [
               "DataFrame"
@@ -188,7 +218,7 @@
           },
           "targetHandle": {
             "fieldName": "input_data",
-            "id": "parser-brnh5",
+            "id": "parser-oHf4E",
             "inputTypes": [
               "DataFrame",
               "Data"
@@ -196,12 +226,12 @@
             "type": "other"
           }
         },
-        "id": "reactflow__edge-AstraDB-RaUqw{œdataTypeœ:œAstraDBœ,œidœ:œAstraDB-RaUqwœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-parser-brnh5{œfieldNameœ:œinput_dataœ,œidœ:œparser-brnh5œ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}",
+        "id": "reactflow__edge-AstraDB-BteL9{œdataTypeœ:œAstraDBœ,œidœ:œAstraDB-BteL9œ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-parser-oHf4E{œfieldNameœ:œinput_dataœ,œidœ:œparser-oHf4Eœ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}",
         "selected": false,
-        "source": "AstraDB-RaUqw",
-        "sourceHandle": "{œdataTypeœ: œAstraDBœ, œidœ: œAstraDB-RaUqwœ, œnameœ: œdataframeœ, œoutput_typesœ: [œDataFrameœ]}",
-        "target": "parser-brnh5",
-        "targetHandle": "{œfieldNameœ: œinput_dataœ, œidœ: œparser-brnh5œ, œinputTypesœ: [œDataFrameœ, œDataœ], œtypeœ: œotherœ}"
+        "source": "AstraDB-BteL9",
+        "sourceHandle": "{œdataTypeœ: œAstraDBœ, œidœ: œAstraDB-BteL9œ, œnameœ: œdataframeœ, œoutput_typesœ: [œDataFrameœ]}",
+        "target": "parser-oHf4E",
+        "targetHandle": "{œfieldNameœ: œinput_dataœ, œidœ: œparser-oHf4Eœ, œinputTypesœ: [œDataFrameœ, œDataœ], œtypeœ: œotherœ}"
       },
       {
         "animated": false,
@@ -209,7 +239,7 @@
         "data": {
           "sourceHandle": {
             "dataType": "OpenAIEmbeddings",
-            "id": "OpenAIEmbeddings-CYjxN",
+            "id": "OpenAIEmbeddings-U8tZg",
             "name": "embeddings",
             "output_types": [
               "Embeddings"
@@ -217,27 +247,26 @@
           },
           "targetHandle": {
             "fieldName": "embedding_model",
-            "id": "AstraDB-ECtXX",
+            "id": "AstraDB-TCSqR",
             "inputTypes": [
               "Embeddings"
             ],
             "type": "other"
           }
         },
-        "id": "reactflow__edge-OpenAIEmbeddings-CYjxN{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-CYjxNœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-AstraDB-ECtXX{œfieldNameœ:œembedding_modelœ,œidœ:œAstraDB-ECtXXœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
+        "id": "xy-edge__OpenAIEmbeddings-U8tZg{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-U8tZgœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-AstraDB-TCSqR{œfieldNameœ:œembedding_modelœ,œidœ:œAstraDB-TCSqRœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
         "selected": false,
-        "source": "OpenAIEmbeddings-CYjxN",
-        "sourceHandle": "{œdataTypeœ: œOpenAIEmbeddingsœ, œidœ: œOpenAIEmbeddings-CYjxNœ, œnameœ: œembeddingsœ, œoutput_typesœ: [œEmbeddingsœ]}",
-        "target": "AstraDB-ECtXX",
-        "targetHandle": "{œfieldNameœ: œembedding_modelœ, œidœ: œAstraDB-ECtXXœ, œinputTypesœ: [œEmbeddingsœ], œtypeœ: œotherœ}"
+        "source": "OpenAIEmbeddings-U8tZg",
+        "sourceHandle": "{œdataTypeœ: œOpenAIEmbeddingsœ, œidœ: œOpenAIEmbeddings-U8tZgœ, œnameœ: œembeddingsœ, œoutput_typesœ: [œEmbeddingsœ]}",
+        "target": "AstraDB-TCSqR",
+        "targetHandle": "{œfieldNameœ: œembedding_modelœ, œidœ: œAstraDB-TCSqRœ, œinputTypesœ: [œEmbeddingsœ], œtypeœ: œotherœ}"
       },
       {
-        "animated": false,
         "className": "",
         "data": {
           "sourceHandle": {
             "dataType": "OpenAIEmbeddings",
-            "id": "OpenAIEmbeddings-m4ukj",
+            "id": "OpenAIEmbeddings-jsaKm",
             "name": "embeddings",
             "output_types": [
               "Embeddings"
@@ -245,49 +274,18 @@
           },
           "targetHandle": {
             "fieldName": "embedding_model",
-            "id": "AstraDB-RaUqw",
+            "id": "AstraDB-BteL9",
             "inputTypes": [
               "Embeddings"
             ],
             "type": "other"
           }
         },
-        "id": "reactflow__edge-OpenAIEmbeddings-m4ukj{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-m4ukjœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-AstraDB-RaUqw{œfieldNameœ:œembedding_modelœ,œidœ:œAstraDB-RaUqwœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
-        "selected": false,
-        "source": "OpenAIEmbeddings-m4ukj",
-        "sourceHandle": "{œdataTypeœ: œOpenAIEmbeddingsœ, œidœ: œOpenAIEmbeddings-m4ukjœ, œnameœ: œembeddingsœ, œoutput_typesœ: [œEmbeddingsœ]}",
-        "target": "AstraDB-RaUqw",
-        "targetHandle": "{œfieldNameœ: œembedding_modelœ, œidœ: œAstraDB-RaUqwœ, œinputTypesœ: [œEmbeddingsœ], œtypeœ: œotherœ}"
-      },
-      {
-        "animated": false,
-        "className": "",
-        "data": {
-          "sourceHandle": {
-            "dataType": "File",
-            "id": "File-CxEQk",
-            "name": "message",
-            "output_types": [
-              "Message"
-            ]
-          },
-          "targetHandle": {
-            "fieldName": "data_inputs",
-            "id": "SplitText-1fBfh",
-            "inputTypes": [
-              "Data",
-              "DataFrame",
-              "Message"
-            ],
-            "type": "other"
-          }
-        },
-        "id": "reactflow__edge-File-CxEQk{œdataTypeœ:œFileœ,œidœ:œFile-CxEQkœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-SplitText-1fBfh{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-1fBfhœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
-        "selected": false,
-        "source": "File-CxEQk",
-        "sourceHandle": "{œdataTypeœ: œFileœ, œidœ: œFile-CxEQkœ, œnameœ: œmessageœ, œoutput_typesœ: [œMessageœ]}",
-        "target": "SplitText-1fBfh",
-        "targetHandle": "{œfieldNameœ: œdata_inputsœ, œidœ: œSplitText-1fBfhœ, œinputTypesœ: [œDataœ, œDataFrameœ, œMessageœ], œtypeœ: œotherœ}"
+        "id": "xy-edge__OpenAIEmbeddings-jsaKm{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-jsaKmœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-AstraDB-BteL9{œfieldNameœ:œembedding_modelœ,œidœ:œAstraDB-BteL9œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
+        "source": "OpenAIEmbeddings-jsaKm",
+        "sourceHandle": "{œdataTypeœ: œOpenAIEmbeddingsœ, œidœ: œOpenAIEmbeddings-jsaKmœ, œnameœ: œembeddingsœ, œoutput_typesœ: [œEmbeddingsœ]}",
+        "target": "AstraDB-BteL9",
+        "targetHandle": "{œfieldNameœ: œembedding_modelœ, œidœ: œAstraDB-BteL9œ, œinputTypesœ: [œEmbeddingsœ], œtypeœ: œotherœ}"
       }
     ],
     "nodes": [
@@ -295,7 +293,7 @@
         "data": {
           "description": "Get chat inputs from the Playground.",
           "display_name": "Chat Input",
-          "id": "ChatInput-bK5uZ",
+          "id": "ChatInput-8l9oz",
           "node": {
             "base_classes": [
               "Message"
@@ -533,9 +531,9 @@
           "type": "ChatInput"
         },
         "dragging": false,
-        "id": "ChatInput-bK5uZ",
+        "id": "ChatInput-8l9oz",
         "measured": {
-          "height": 204,
+          "height": 234,
           "width": 320
         },
         "position": {
@@ -553,7 +551,7 @@
         "data": {
           "description": "Create a prompt template with dynamic variables.",
           "display_name": "Prompt",
-          "id": "Prompt-zBlCK",
+          "id": "Prompt-ML5XQ",
           "node": {
             "base_classes": [
               "Message"
@@ -716,9 +714,9 @@
           "type": "Prompt"
         },
         "dragging": false,
-        "id": "Prompt-zBlCK",
+        "id": "Prompt-ML5XQ",
         "measured": {
-          "height": 449,
+          "height": 433,
           "width": 320
         },
         "position": {
@@ -736,7 +734,7 @@
         "data": {
           "description": "Split text into chunks based on specified criteria.",
           "display_name": "Split Text",
-          "id": "SplitText-1fBfh",
+          "id": "SplitText-4s7Dt",
           "node": {
             "base_classes": [
               "Data"
@@ -937,9 +935,9 @@
           "type": "SplitText"
         },
         "dragging": false,
-        "id": "SplitText-1fBfh",
+        "id": "SplitText-4s7Dt",
         "measured": {
-          "height": 413,
+          "height": 475,
           "width": 320
         },
         "position": {
@@ -955,7 +953,7 @@
       },
       {
         "data": {
-          "id": "note-TwiPL",
+          "id": "note-PMpi6",
           "node": {
             "description": "## 🐕 2. Retriever Flow\n\nThis flow answers your questions with contextual data retrieved from your vector database.\n\nOpen the **Playground** and ask, \n\n```\nWhat is this document about?\n```\n",
             "display_name": "",
@@ -968,7 +966,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-TwiPL",
+        "id": "note-PMpi6",
         "measured": {
           "height": 324,
           "width": 324
@@ -992,7 +990,7 @@
       },
       {
         "data": {
-          "id": "note-67DoI",
+          "id": "note-WvtH0",
           "node": {
             "description": "Retrieval Augmented Generation (RAG) is a way of providing additional context to a Large Language Model (LLM) by preloading a vector database with embeddings for relevant content. When a user chats with the LLM, a _similarity search_ retrieves relevant content by comparing an embedding for the user's query against the embeddings in the vector database.\nFor example, a RAG chatbot could be pre-loaded with product data, and then it can help customers find specific products based on their queries.\nThis template has two sub-flows. One flow loads data into your vector store, and the other is the user-driven chat flow that compares a new query against the existing content in your vector database.\n\n## Quickstart\n1. Add your OpenAI API key to the **Language Model** component and the two **Embeddings** components.\n2. Add an Astra application token to the **Astra DB** vector store components, or replace these components with other vector store components available in the **Components** menu.\n**💡 Store your credentials as Langflow global variables 🌐 to simplify token management and reuse in your flows.**\n\n## Run the flows\n1. Load your data into a vector database with the 📚 **Load Data** flow. Select a file to upload in the **File** component, and then click **Play** ▶️ on the **Astra DB** component to run the **Load Data** flow.\n2. Open the **Playground** to start a chat with the 🐕 **Retriever** flow.\n\nOnly the run the **Load Data** flow when you need to populate your vector database with baseline content, such as product data.\nThe **Retriever** flow is the user-facing chat flow. This flow generates an embedding from chat input, runs a similarity search against the vector database to retrieve relevant content, and then passes the original query and the retrieved content to the LLM, which produces the chat response sent to the user.\n\n## Next steps\nExperiment by changing the prompt and the loaded data to see how the LLM's responses change.",
             "display_name": "Read Me",
@@ -1005,7 +1003,7 @@
         },
         "dragging": false,
         "height": 556,
-        "id": "note-67DoI",
+        "id": "note-WvtH0",
         "measured": {
           "height": 556,
           "width": 389
@@ -1031,7 +1029,7 @@
         "data": {
           "description": "Display a chat message in the Playground.",
           "display_name": "Chat Output",
-          "id": "ChatOutput-G4VgE",
+          "id": "ChatOutput-g0Phk",
           "node": {
             "base_classes": [
               "Message"
@@ -1290,9 +1288,9 @@
           "type": "ChatOutput"
         },
         "dragging": false,
-        "id": "ChatOutput-G4VgE",
+        "id": "ChatOutput-g0Phk",
         "measured": {
-          "height": 204,
+          "height": 234,
           "width": 320
         },
         "position": {
@@ -1308,7 +1306,7 @@
       },
       {
         "data": {
-          "id": "OpenAIEmbeddings-m4ukj",
+          "id": "OpenAIEmbeddings-jsaKm",
           "node": {
             "base_classes": [
               "Embeddings"
@@ -1609,7 +1607,7 @@
                 "dynamic": false,
                 "info": "",
                 "input_types": [],
-                "load_from_db": false,
+                "load_from_db": true,
                 "name": "openai_api_key",
                 "password": true,
                 "placeholder": "",
@@ -1617,7 +1615,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "str",
-                "value": ""
+                "value": "OPENAI_API_KEY"
               },
               "openai_api_type": {
                 "_input_type": "MessageTextInput",
@@ -1800,9 +1798,9 @@
           "type": "OpenAIEmbeddings"
         },
         "dragging": false,
-        "id": "OpenAIEmbeddings-m4ukj",
+        "id": "OpenAIEmbeddings-jsaKm",
         "measured": {
-          "height": 286,
+          "height": 320,
           "width": 320
         },
         "position": {
@@ -1818,7 +1816,7 @@
       },
       {
         "data": {
-          "id": "note-RfY95",
+          "id": "note-WLlNM",
           "node": {
             "description": "## 📚 1. Load Data Flow\n\nRun this first! Load data from a local file and embed it into the vector database.\n\nSelect a Database and a Collection, or create new ones. \n\nClick  **Run component** on the **Astra DB** component to load your data.\n\n\n### Next steps:\n Experiment by changing the prompt and the contextual data to see how the retrieval flow's responses change.",
             "display_name": "",
@@ -1831,7 +1829,7 @@
         },
         "dragging": false,
         "height": 460,
-        "id": "note-RfY95",
+        "id": "note-WLlNM",
         "measured": {
           "height": 460,
           "width": 340
@@ -1855,7 +1853,7 @@
       },
       {
         "data": {
-          "id": "OpenAIEmbeddings-CYjxN",
+          "id": "OpenAIEmbeddings-U8tZg",
           "node": {
             "base_classes": [
               "Embeddings"
@@ -2156,7 +2154,7 @@
                 "dynamic": false,
                 "info": "",
                 "input_types": [],
-                "load_from_db": false,
+                "load_from_db": true,
                 "name": "openai_api_key",
                 "password": true,
                 "placeholder": "",
@@ -2164,7 +2162,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "str",
-                "value": ""
+                "value": "OPENAI_API_KEY"
               },
               "openai_api_type": {
                 "_input_type": "MessageTextInput",
@@ -2347,9 +2345,9 @@
           "type": "OpenAIEmbeddings"
         },
         "dragging": false,
-        "id": "OpenAIEmbeddings-CYjxN",
+        "id": "OpenAIEmbeddings-U8tZg",
         "measured": {
-          "height": 286,
+          "height": 320,
           "width": 320
         },
         "position": {
@@ -2365,7 +2363,7 @@
       },
       {
         "data": {
-          "id": "note-7vsn8",
+          "id": "note-5qEgh",
           "node": {
             "description": "### 💡 Add your OpenAI API key here 👇",
             "display_name": "",
@@ -2378,7 +2376,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-7vsn8",
+        "id": "note-5qEgh",
         "measured": {
           "height": 324,
           "width": 324
@@ -2397,7 +2395,7 @@
       },
       {
         "data": {
-          "id": "note-eZXHW",
+          "id": "note-siZGp",
           "node": {
             "description": "### 💡 Add your OpenAI API key here 👇",
             "display_name": "",
@@ -2410,7 +2408,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-eZXHW",
+        "id": "note-siZGp",
         "measured": {
           "height": 324,
           "width": 324
@@ -2429,7 +2427,7 @@
       },
       {
         "data": {
-          "id": "note-JkBeF",
+          "id": "note-qKdBl",
           "node": {
             "description": "### 💡 Add your OpenAI API key here 👇",
             "display_name": "",
@@ -2442,7 +2440,7 @@
         },
         "dragging": false,
         "height": 324,
-        "id": "note-JkBeF",
+        "id": "note-qKdBl",
         "measured": {
           "height": 324,
           "width": 324
@@ -2461,7 +2459,7 @@
       },
       {
         "data": {
-          "id": "parser-brnh5",
+          "id": "parser-oHf4E",
           "node": {
             "base_classes": [
               "Message"
@@ -2623,7 +2621,7 @@
           "type": "parser"
         },
         "dragging": false,
-        "id": "parser-brnh5",
+        "id": "parser-oHf4E",
         "measured": {
           "height": 361,
           "width": 320
@@ -2637,53 +2635,57 @@
       },
       {
         "data": {
-          "id": "LanguageModelComponent-rL7g3",
+          "id": "File-7D3hP",
           "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": "2025-12-20T16:56:30.808Z",
+            "icon": "file-text",
+            "last_updated": "2025-10-10T17:51:29.596Z",
             "legacy": false,
-            "lf_version": "1.7.0",
             "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": [],
@@ -2691,101 +2693,119 @@
               {
                 "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": "be165273-a6ce-4053-9548-e5b5c8a657bf"
-              },
-              "_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": true,
+                "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,
@@ -2803,810 +2823,370 @@
                 "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-rL7g3",
-        "measured": {
-          "height": 369,
-          "width": 320
-        },
-        "position": {
-          "x": 2354.7612483129965,
-          "y": 633.8261067248878
-        },
-        "selected": false,
-        "type": "genericNode"
-      },
-      {
-        "data": {
-          "id": "AstraDB-ECtXX",
-          "node": {
-            "base_classes": [
-              "Data",
-              "DataFrame",
-              "VectorStore"
-            ],
-            "beta": false,
-            "conditional_paths": [],
-            "custom_fields": {},
-            "description": "Ingest and search documents in Astra DB",
-            "display_name": "Astra DB",
-            "documentation": "https://docs.datastax.com/en/langflow/astra-components.html",
-            "edited": false,
-            "field_order": [
-              "token",
-              "environment",
-              "database_name",
-              "api_endpoint",
-              "keyspace",
-              "collection_name",
-              "embedding_model",
-              "ingest_data",
-              "search_query",
-              "should_cache_vector_store",
-              "search_method",
-              "reranker",
-              "lexical_terms",
-              "number_of_results",
-              "search_type",
-              "search_score_threshold",
-              "advanced_search_filter",
-              "autodetect_collection",
-              "content_field",
-              "deletion_field",
-              "ignore_invalid_documents",
-              "astradb_vectorstore_kwargs"
-            ],
-            "frozen": false,
-            "icon": "AstraDB",
-            "last_updated": "2025-12-20T17:35:17.510Z",
-            "legacy": false,
-            "metadata": {
-              "code_hash": "d52094e54e96",
-              "dependencies": {
-                "dependencies": [
-                  {
-                    "name": "astrapy",
-                    "version": "2.1.0"
-                  },
-                  {
-                    "name": "langchain_core",
-                    "version": "0.3.80"
-                  },
-                  {
-                    "name": "lfx",
-                    "version": null
-                  },
-                  {
-                    "name": "langchain_astradb",
-                    "version": "0.6.1"
-                  }
-                ],
-                "total_dependencies": 4
-              },
-              "module": "lfx.components.datastax.astradb_vectorstore.AstraDBVectorStoreComponent"
-            },
-            "minimized": false,
-            "output_types": [],
-            "outputs": [
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Search Results",
-                "group_outputs": false,
-                "method": "search_documents",
-                "name": "search_results",
-                "selected": "Data",
-                "tool_mode": true,
-                "types": [
-                  "Data"
-                ],
-                "value": "__UNDEFINED__"
-              },
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "DataFrame",
-                "group_outputs": false,
-                "method": "as_dataframe",
-                "name": "dataframe",
-                "selected": "DataFrame",
-                "tool_mode": true,
-                "types": [
-                  "DataFrame"
-                ],
-                "value": "__UNDEFINED__"
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "easyocr"
               },
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Vector Store Connection",
-                "group_outputs": false,
-                "hidden": false,
-                "method": "as_vector_store",
-                "name": "vectorstoreconnection",
-                "selected": "VectorStore",
-                "tool_mode": true,
-                "types": [
-                  "VectorStore"
-                ],
-                "value": "__UNDEFINED__"
-              }
-            ],
-            "pinned": false,
-            "template": {
-              "_type": "Component",
-              "advanced_search_filter": {
-                "_input_type": "NestedDictInput",
-                "advanced": true,
-                "display_name": "Search Metadata Filter",
+              "path": {
+                "_input_type": "FileInput",
+                "advanced": false,
+                "display_name": "Files",
                 "dynamic": false,
-                "info": "Optional dictionary of filters to apply to the search query.",
-                "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_search_filter",
+                "name": "path",
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
                 "show": true,
+                "temp_file": false,
                 "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "type": "NestedDict",
-                "value": {}
+                "type": "file",
+                "value": ""
               },
-              "api_endpoint": {
+              "pipeline": {
                 "_input_type": "DropdownInput",
                 "advanced": true,
                 "combobox": false,
                 "dialog_inputs": {},
-                "display_name": "Astra DB API Endpoint",
+                "display_name": "Pipeline",
                 "dynamic": false,
                 "external_options": {},
-                "info": "The API Endpoint for the Astra DB instance. Supercedes database selection.",
-                "name": "api_endpoint",
-                "options": [],
+                "info": "Docling pipeline to use",
+                "name": "pipeline",
+                "options": [
+                  "standard",
+                  "vlm"
+                ],
                 "options_metadata": [],
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "show": true,
+                "show": false,
                 "title_case": false,
                 "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "type": "str",
-                "value": ""
-              },
-              "astradb_vectorstore_kwargs": {
-                "_input_type": "NestedDictInput",
-                "advanced": true,
-                "display_name": "AstraDBVectorStore Parameters",
-                "dynamic": false,
-                "info": "Optional dictionary of additional parameters for the AstraDBVectorStore.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "astradb_vectorstore_kwargs",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
-                "trace_as_metadata": true,
-                "type": "NestedDict",
-                "value": {}
+                "value": "standard"
               },
-              "autodetect_collection": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Autodetect Collection",
+              "s3_file_key": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "S3 File Key",
                 "dynamic": false,
-                "info": "Boolean flag to determine whether to autodetect the collection.",
+                "info": "The key (path) of the file in S3 bucket.",
                 "list": false,
-                "list_add_label": "Add More",
-                "name": "autodetect_collection",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": true
-              },
-              "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 astrapy import DataAPIClient\nfrom langchain_core.documents import Document\n\nfrom lfx.base.datastax.astradb_base import AstraDBBaseComponent\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom lfx.helpers.data import docs_to_data\nfrom lfx.io import BoolInput, DropdownInput, FloatInput, HandleInput, IntInput, NestedDictInput, QueryInput, StrInput\nfrom lfx.schema.data import Data\nfrom lfx.serialization import serialize\nfrom lfx.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(AstraDBBaseComponent, LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.langflow.org/bundles-datastax\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    inputs = [\n        *AstraDBBaseComponent.inputs,\n        *LCVectorStoreComponent.inputs,\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n    ]\n\n    async def update_build_config(\n        self,\n        build_config: dict,\n        field_value: str | dict,\n        field_name: str | None = None,\n    ) -> dict:\n        \"\"\"Update build configuration with proper handling of embedding and search options.\"\"\"\n        # Handle base astra db build config updates\n        build_config = await super().update_build_config(\n            build_config,\n            field_value=field_value,\n            field_name=field_name,\n        )\n\n        # Set embedding model display based on provider selection\n        if isinstance(field_value, dict) and \"02_embedding_generation_provider\" in field_value:\n            embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n            is_custom_provider = embedding_provider and embedding_provider != \"Bring your own\"\n            provider = embedding_provider.lower() if is_custom_provider and embedding_provider is not None else None\n\n            build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n            build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Early return if no API endpoint is configured\n        if not self.get_api_endpoint():\n            return build_config\n\n        # Configure search method and related options\n        return self._configure_search_options(build_config)\n\n    def _configure_search_options(self, build_config: dict) -> dict:\n        \"\"\"Configure hybrid search, reranker, and vector search options.\"\"\"\n        # Detect available hybrid search capabilities\n        hybrid_capabilities = self._detect_hybrid_capabilities()\n\n        # Return if we haven't selected a collection\n        if not build_config[\"collection_name\"][\"options\"] or not build_config[\"collection_name\"][\"value\"]:\n            return build_config\n\n        # Get collection options\n        collection_options = self._get_collection_options(build_config)\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(build_config[\"collection_name\"][\"value\"])\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Determine search configuration\n        is_vector_search = build_config[\"search_method\"][\"value\"] == \"Vector Search\"\n        is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n        # Apply hybrid search configuration\n        if hybrid_capabilities[\"available\"]:\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = build_config[\"search_method\"].get(\"value\", \"Hybrid Search\")\n\n            build_config[\"reranker\"][\"options\"] = hybrid_capabilities[\"reranker_models\"]\n            build_config[\"reranker\"][\"options_metadata\"] = hybrid_capabilities[\"reranker_metadata\"]\n            if hybrid_capabilities[\"reranker_models\"]:\n                build_config[\"reranker\"][\"value\"] = hybrid_capabilities[\"reranker_models\"][0]\n        else:\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n        # Configure reranker visibility and state\n        hybrid_enabled = (\n            collection_options[\"rerank_enabled\"] and build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        )\n\n        build_config[\"reranker\"][\"show\"] = hybrid_enabled\n        build_config[\"reranker\"][\"toggle_value\"] = hybrid_enabled\n        build_config[\"reranker\"][\"toggle_disable\"] = is_vector_search\n\n        # Configure lexical terms\n        lexical_visible = collection_options[\"lexical_enabled\"] and not is_vector_search\n        build_config[\"lexical_terms\"][\"show\"] = lexical_visible\n        build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n        # Configure search type and score threshold\n        build_config[\"search_type\"][\"show\"] = is_vector_search\n        build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n        # Force similarity search for hybrid mode or autodetect\n        if hybrid_enabled or is_autodetect:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    def _detect_hybrid_capabilities(self) -> dict:\n        \"\"\"Detect available hybrid search and reranking capabilities.\"\"\"\n        environment = self.get_environment(self.environment)\n        client = DataAPIClient(environment=environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        try:\n            providers = db_admin.find_reranking_providers()\n            reranker_models = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            reranker_metadata = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Hybrid search not available: {e}\")\n            return {\n                \"available\": False,\n                \"reranker_models\": [],\n                \"reranker_metadata\": [],\n            }\n        else:\n            return {\n                \"available\": True,\n                \"reranker_models\": reranker_models,\n                \"reranker_metadata\": reranker_metadata,\n            }\n\n    def _get_collection_options(self, build_config: dict) -> dict:\n        \"\"\"Retrieve collection-level search options.\"\"\"\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=build_config[\"collection_name\"][\"value\"],\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        col_options = collection.options()\n\n        return {\n            \"rerank_enabled\": bool(col_options.rerank and col_options.rerank.enabled),\n            \"lexical_enabled\": bool(col_options.lexical and col_options.lexical.enabled),\n        }\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n            from langchain_astradb.utils.astradb import HybridSearchMode\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except ValueError as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except ValueError as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except ValueError as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except ValueError as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except ValueError as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
-              },
-              "collection_name": {
-                "_input_type": "DropdownInput",
-                "advanced": false,
-                "combobox": true,
-                "dialog_inputs": {
-                  "fields": {
-                    "data": {
-                      "node": {
-                        "description": "Please allow several seconds for creation to complete.",
-                        "display_name": "Create new collection",
-                        "field_order": [
-                          "01_new_collection_name",
-                          "02_embedding_generation_provider",
-                          "03_embedding_generation_model",
-                          "04_dimension"
-                        ],
-                        "name": "create_collection",
-                        "template": {
-                          "01_new_collection_name": {
-                            "_input_type": "StrInput",
-                            "advanced": false,
-                            "display_name": "Name",
-                            "dynamic": false,
-                            "info": "Name of the new collection to create in Astra DB.",
-                            "list": false,
-                            "list_add_label": "Add More",
-                            "load_from_db": false,
-                            "name": "new_collection_name",
-                            "placeholder": "",
-                            "required": true,
-                            "show": true,
-                            "title_case": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          },
-                          "02_embedding_generation_provider": {
-                            "_input_type": "DropdownInput",
-                            "advanced": false,
-                            "combobox": false,
-                            "dialog_inputs": {},
-                            "display_name": "Embedding generation method",
-                            "dynamic": false,
-                            "external_options": {},
-                            "helper_text": "To create collections with more embedding provider options, go to <a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" rel=\"noopener noreferrer\">your database in Astra DB</a>",
-                            "info": "Provider to use for generating embeddings.",
-                            "name": "embedding_generation_provider",
-                            "options": [],
-                            "options_metadata": [],
-                            "placeholder": "",
-                            "real_time_refresh": true,
-                            "required": true,
-                            "show": true,
-                            "title_case": false,
-                            "toggle": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          },
-                          "03_embedding_generation_model": {
-                            "_input_type": "DropdownInput",
-                            "advanced": false,
-                            "combobox": false,
-                            "dialog_inputs": {},
-                            "display_name": "Embedding model",
-                            "dynamic": false,
-                            "external_options": {},
-                            "info": "Model to use for generating embeddings.",
-                            "name": "embedding_generation_model",
-                            "options": [],
-                            "options_metadata": [],
-                            "placeholder": "",
-                            "real_time_refresh": true,
-                            "required": false,
-                            "show": true,
-                            "title_case": false,
-                            "toggle": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          },
-                          "04_dimension": {
-                            "_input_type": "IntInput",
-                            "advanced": false,
-                            "display_name": "Dimensions",
-                            "dynamic": false,
-                            "info": "Dimensions of the embeddings to generate.",
-                            "list": false,
-                            "list_add_label": "Add More",
-                            "name": "dimension",
-                            "placeholder": "",
-                            "required": false,
-                            "show": true,
-                            "title_case": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "int"
-                          }
-                        }
-                      }
-                    }
-                  },
-                  "functionality": "create"
-                },
-                "display_name": "Collection",
-                "dynamic": false,
-                "external_options": {},
-                "info": "The name of the collection within Astra DB where the vectors will be stored.",
-                "name": "collection_name",
-                "options": [],
-                "options_metadata": [],
-                "placeholder": "",
-                "real_time_refresh": true,
-                "refresh_button": true,
-                "required": true,
-                "show": false,
-                "title_case": false,
-                "toggle": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "content_field": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Content Field",
-                "dynamic": false,
-                "info": "Field to use as the text content field for the vector store.",
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "content_field",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "database_name": {
-                "_input_type": "DropdownInput",
-                "advanced": false,
-                "combobox": true,
-                "dialog_inputs": {
-                  "fields": {
-                    "data": {
-                      "node": {
-                        "description": "Please allow several minutes for creation to complete.",
-                        "display_name": "Create new database",
-                        "field_order": [
-                          "01_new_database_name",
-                          "02_cloud_provider",
-                          "03_region"
-                        ],
-                        "name": "create_database",
-                        "template": {
-                          "01_new_database_name": {
-                            "_input_type": "StrInput",
-                            "advanced": false,
-                            "display_name": "Name",
-                            "dynamic": false,
-                            "info": "Name of the new database to create in Astra DB.",
-                            "list": false,
-                            "list_add_label": "Add More",
-                            "load_from_db": false,
-                            "name": "new_database_name",
-                            "placeholder": "",
-                            "required": true,
-                            "show": true,
-                            "title_case": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          },
-                          "02_cloud_provider": {
-                            "_input_type": "DropdownInput",
-                            "advanced": false,
-                            "combobox": false,
-                            "dialog_inputs": {},
-                            "display_name": "Cloud provider",
-                            "dynamic": false,
-                            "external_options": {},
-                            "info": "Cloud provider for the new database.",
-                            "name": "cloud_provider",
-                            "options": [
-                              "Google Cloud Platform",
-                              "Amazon Web Services"
-                            ],
-                            "options_metadata": [],
-                            "placeholder": "",
-                            "real_time_refresh": true,
-                            "required": true,
-                            "show": true,
-                            "title_case": false,
-                            "toggle": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          },
-                          "03_region": {
-                            "_input_type": "DropdownInput",
-                            "advanced": false,
-                            "combobox": false,
-                            "dialog_inputs": {},
-                            "display_name": "Region",
-                            "dynamic": false,
-                            "external_options": {},
-                            "info": "Region for the new database.",
-                            "name": "region",
-                            "options": [],
-                            "options_metadata": [],
-                            "placeholder": "",
-                            "required": true,
-                            "show": true,
-                            "title_case": false,
-                            "toggle": false,
-                            "tool_mode": false,
-                            "trace_as_metadata": true,
-                            "type": "str",
-                            "value": ""
-                          }
-                        }
-                      }
-                    }
-                  },
-                  "functionality": "create"
-                },
-                "display_name": "Database",
-                "dynamic": false,
-                "external_options": {},
-                "info": "The Database name for the Astra DB instance.",
-                "name": "database_name",
-                "options": [],
-                "options_metadata": [],
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "s3_file_key",
+                "override_skip": false,
                 "placeholder": "",
-                "real_time_refresh": true,
-                "refresh_button": true,
                 "required": true,
                 "show": false,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
+                "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "deletion_field": {
+              "separator": {
                 "_input_type": "StrInput",
                 "advanced": true,
-                "display_name": "Deletion Based On Field",
+                "display_name": "Separator",
                 "dynamic": false,
-                "info": "When this parameter is provided, documents in the target collection with metadata field values matching the input metadata field value will be deleted before new data is loaded.",
+                "info": "Specify the separator to use between multiple outputs in Message format.",
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "deletion_field",
+                "name": "separator",
                 "placeholder": "",
                 "required": false,
                 "show": true,
@@ -3614,64 +3194,89 @@
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "type": "str",
-                "value": ""
+                "value": "\n\n"
               },
-              "embedding_model": {
-                "_input_type": "HandleInput",
+              "service_account_key": {
+                "_input_type": "SecretStrInput",
                 "advanced": false,
-                "display_name": "Embedding Model",
+                "display_name": "GCP Credentials Secret Key",
                 "dynamic": false,
-                "info": "Specify the Embedding Model. Not required for Astra Vectorize collections.",
-                "input_types": [
-                  "Embeddings"
-                ],
+                "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": true,
+                "show": false,
+                "title_case": false,
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
+              },
+              "silent_errors": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Silent Errors",
+                "dynamic": false,
+                "info": "If true, errors will not raise an exception.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "embedding_model",
+                "name": "silent_errors",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
+                "tool_mode": false,
                 "trace_as_metadata": true,
-                "type": "other",
-                "value": ""
+                "type": "bool",
+                "value": false
               },
-              "environment": {
-                "_input_type": "DropdownInput",
-                "advanced": true,
-                "combobox": true,
-                "dialog_inputs": {},
-                "display_name": "Environment",
+              "storage_location": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Storage Location",
                 "dynamic": false,
-                "external_options": {},
-                "info": "The environment for the Astra DB API Endpoint.",
-                "name": "environment",
+                "info": "Choose where to read the file from.",
+                "limit": 1,
+                "name": "storage_location",
                 "options": [
-                  "prod",
-                  "test",
-                  "dev"
+                  {
+                    "icon": "hard-drive",
+                    "name": "Local"
+                  },
+                  {
+                    "icon": "Amazon",
+                    "name": "AWS"
+                  },
+                  {
+                    "icon": "google",
+                    "name": "Google Drive"
+                  }
                 ],
-                "options_metadata": [],
-                "placeholder": "",
+                "override_skip": false,
+                "placeholder": "Select Location",
                 "real_time_refresh": true,
                 "required": false,
+                "search_category": [],
                 "show": true,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "type": "str",
-                "value": "prod"
+                "track_in_telemetry": false,
+                "type": "sortableList",
+                "value": ""
               },
-              "ignore_invalid_documents": {
+              "use_multithreading": {
                 "_input_type": "BoolInput",
                 "advanced": true,
-                "display_name": "Ignore Invalid Documents",
+                "display_name": "[Deprecated] Use Multithreading",
                 "dynamic": false,
-                "info": "Boolean flag to determine whether to ignore invalid documents at runtime.",
+                "info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "ignore_invalid_documents",
+                "name": "use_multithreading",
                 "placeholder": "",
                 "required": false,
                 "show": true,
@@ -3679,275 +3284,407 @@
                 "tool_mode": false,
                 "trace_as_metadata": true,
                 "type": "bool",
-                "value": false
+                "value": true
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "File"
+        },
+        "dragging": false,
+        "id": "File-7D3hP",
+        "measured": {
+          "height": 256,
+          "width": 320
+        },
+        "position": {
+          "x": 1330.7650978046952,
+          "y": 1431.5905495627503
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "LanguageModelComponent-Wqbva",
+          "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
               },
-              "ingest_data": {
-                "_input_type": "HandleInput",
-                "advanced": false,
-                "display_name": "Ingest Data",
-                "dynamic": false,
-                "info": "",
-                "input_types": [
-                  "Data",
-                  "DataFrame"
+              "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": "ingest_data",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "trace_as_metadata": true,
-                "type": "other",
-                "value": ""
+                "value": "__UNDEFINED__"
               },
-              "keyspace": {
-                "_input_type": "DropdownInput",
+              {
+                "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"
+              },
+              "_frontend_node_folder_id": {
+                "value": "afaca9ee-97e3-4211-8569-722a4058ea5e"
+              },
+              "_type": "Component",
+              "api_key": {
+                "_input_type": "SecretStrInput",
                 "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Keyspace",
+                "display_name": "API Key",
                 "dynamic": false,
-                "external_options": {},
-                "info": "Optional keyspace within Astra DB to use for the collection.",
-                "name": "keyspace",
-                "options": [],
-                "options_metadata": [],
+                "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,
-                "toggle": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
+                "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "lexical_terms": {
-                "_input_type": "QueryInput",
+              "base_url_ibm_watsonx": {
+                "_input_type": "DropdownInput",
                 "advanced": false,
-                "display_name": "Lexical Terms",
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "watsonx API Endpoint",
                 "dynamic": false,
-                "info": "Add additional terms/keywords to augment search precision.",
-                "input_types": [
-                  "Message"
+                "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"
                 ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "lexical_terms",
-                "placeholder": "Enter terms to search...",
+                "options_metadata": [],
+                "override_skip": false,
+                "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "separator": " ",
                 "show": false,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
-                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "type": "query",
-                "value": ""
+                "track_in_telemetry": true,
+                "type": "str",
+                "value": "https://us-south.ml.cloud.ibm.com"
               },
-              "number_of_results": {
-                "_input_type": "IntInput",
+              "code": {
                 "advanced": true,
-                "display_name": "Number of Search Results",
-                "dynamic": false,
-                "info": "Number of search results to return.",
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
                 "list": false,
-                "list_add_label": "Add More",
-                "name": "number_of_results",
+                "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,
-                "type": "int",
-                "value": 4
+                "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"
               },
-              "reranker": {
-                "_input_type": "DropdownInput",
+              "input_value": {
+                "_input_type": "MessageInput",
                 "advanced": false,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Reranker",
+                "display_name": "Input",
                 "dynamic": false,
-                "external_options": {},
-                "info": "Post-retrieval model that re-scores results for optimal relevance ranking.",
-                "name": "reranker",
-                "options": [],
-                "options_metadata": [],
+                "info": "The input text to send to the model",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "input_value",
+                "override_skip": false,
                 "placeholder": "",
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
-                "toggle": true,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
+                "track_in_telemetry": false,
                 "type": "str",
                 "value": ""
               },
-              "search_method": {
-                "_input_type": "DropdownInput",
-                "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Search Method",
+              "is_refresh": false,
+              "model": {
+                "_input_type": "ModelInput",
+                "advanced": false,
+                "display_name": "Language Model",
                 "dynamic": false,
-                "external_options": {},
-                "info": "Determine how your content is matched: Vector finds semantic similarity, and Hybrid Search (suggested) combines both approaches with a reranker.",
-                "name": "search_method",
-                "options": [
-                  "Hybrid Search",
-                  "Vector Search"
-                ],
-                "options_metadata": [
-                  {
-                    "icon": "SearchHybrid"
-                  },
-                  {
-                    "icon": "SearchVector"
+                "external_options": {
+                  "fields": {
+                    "data": {
+                      "node": {
+                        "display_name": "Connect other models",
+                        "icon": "CornerDownLeft",
+                        "name": "connect_other_models"
+                      }
+                    }
                   }
+                },
+                "info": "Select your model provider",
+                "input_types": [
+                  "LanguageModel"
                 ],
-                "placeholder": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "model_type": "language",
+                "name": "model",
+                "options": [],
+                "override_skip": false,
+                "placeholder": "Setup Provider",
                 "real_time_refresh": true,
-                "required": false,
+                "refresh_button": true,
+                "required": true,
                 "show": true,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": "Vector Search"
+                "trace_as_input": true,
+                "track_in_telemetry": false,
+                "type": "model",
+                "value": []
               },
-              "search_query": {
-                "_input_type": "QueryInput",
+              "ollama_base_url": {
+                "_input_type": "MessageInput",
                 "advanced": false,
-                "display_name": "Search Query",
+                "display_name": "Ollama API URL",
                 "dynamic": false,
-                "info": "Enter a query to run a similarity search.",
+                "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": "search_query",
-                "placeholder": "Enter a query...",
+                "name": "ollama_base_url",
+                "override_skip": false,
+                "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "show": true,
+                "show": false,
                 "title_case": false,
-                "tool_mode": true,
+                "tool_mode": false,
                 "trace_as_input": true,
                 "trace_as_metadata": true,
-                "type": "query",
+                "track_in_telemetry": false,
+                "type": "str",
                 "value": ""
               },
-              "search_score_threshold": {
-                "_input_type": "FloatInput",
-                "advanced": true,
-                "display_name": "Search Score Threshold",
+              "project_id": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "watsonx Project ID",
                 "dynamic": false,
-                "info": "Minimum similarity score threshold for search results. (when using 'Similarity with score threshold')",
+                "info": "The project ID associated with the foundation model (IBM watsonx.ai only)",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "search_score_threshold",
+                "load_from_db": false,
+                "name": "project_id",
+                "override_skip": false,
                 "placeholder": "",
                 "required": false,
-                "show": true,
+                "show": false,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "type": "float",
-                "value": 0
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
               },
-              "search_type": {
-                "_input_type": "DropdownInput",
+              "stream": {
+                "_input_type": "BoolInput",
                 "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Search Type",
+                "display_name": "Stream",
                 "dynamic": false,
-                "external_options": {},
-                "info": "Search type to use",
-                "name": "search_type",
-                "options": [
-                  "Similarity",
-                  "Similarity with score threshold",
-                  "MMR (Max Marginal Relevance)"
-                ],
-                "options_metadata": [],
+                "info": "Whether to stream the response",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "stream",
+                "override_skip": false,
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
-                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "type": "str",
-                "value": "Similarity"
+                "track_in_telemetry": true,
+                "type": "bool",
+                "value": false
               },
-              "should_cache_vector_store": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Cache Vector Store",
+              "system_message": {
+                "_input_type": "MultilineInput",
+                "advanced": false,
+                "ai_enabled": false,
+                "copy_field": false,
+                "display_name": "System Message",
                 "dynamic": false,
-                "info": "If True, the vector store will be cached for the current build of the component. This is useful for components that have multiple output methods and want to share the same vector store.",
+                "info": "A system message that helps set the behavior of the assistant",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "should_cache_vector_store",
+                "load_from_db": false,
+                "multiline": true,
+                "name": "system_message",
+                "override_skip": false,
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "type": "bool",
-                "value": true
+                "track_in_telemetry": false,
+                "type": "str",
+                "value": ""
               },
-              "token": {
-                "_input_type": "SecretStrInput",
-                "advanced": false,
-                "display_name": "Astra DB Application Token",
+              "temperature": {
+                "_input_type": "SliderInput",
+                "advanced": true,
+                "display_name": "Temperature",
                 "dynamic": false,
-                "info": "Authentication token for accessing Astra DB.",
-                "input_types": [],
-                "load_from_db": false,
-                "name": "token",
-                "password": true,
+                "info": "Controls randomness in responses",
+                "max_label": "",
+                "max_label_icon": "",
+                "min_label": "",
+                "min_label_icon": "",
+                "name": "temperature",
+                "override_skip": false,
                 "placeholder": "",
-                "real_time_refresh": true,
-                "required": true,
+                "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,
-                "type": "str",
-                "value": ""
+                "tool_mode": false,
+                "track_in_telemetry": false,
+                "type": "slider",
+                "value": 0.1
               }
             },
             "tool_mode": false
           },
-          "selected_output": "search_results",
+          "selected_output": "text_output",
           "showNode": true,
-          "type": "AstraDB"
+          "type": "LanguageModelComponent"
         },
         "dragging": false,
-        "id": "AstraDB-ECtXX",
+        "id": "LanguageModelComponent-Wqbva",
         "measured": {
-          "height": 375,
+          "height": 451,
           "width": 320
         },
         "position": {
-          "x": 2095.3200255891484,
-          "y": 1501.719729125222
+          "x": 2354.7612483129965,
+          "y": 633.8261067248878
         },
         "selected": false,
         "type": "genericNode"
       },
       {
         "data": {
-          "id": "AstraDB-RaUqw",
+          "id": "AstraDB-TCSqR",
           "node": {
             "base_classes": [
               "Data",
@@ -3987,7 +3724,6 @@
             ],
             "frozen": false,
             "icon": "AstraDB",
-            "last_updated": "2025-12-20T17:35:17.511Z",
             "legacy": false,
             "metadata": {
               "code_hash": "d52094e54e96",
@@ -4351,10 +4087,7 @@
                             "external_options": {},
                             "info": "Cloud provider for the new database.",
                             "name": "cloud_provider",
-                            "options": [
-                              "Google Cloud Platform",
-                              "Amazon Web Services"
-                            ],
+                            "options": [],
                             "options_metadata": [],
                             "placeholder": "",
                             "real_time_refresh": true,
@@ -4406,7 +4139,7 @@
                 "real_time_refresh": true,
                 "refresh_button": true,
                 "required": true,
-                "show": false,
+                "show": true,
                 "title_case": false,
                 "toggle": false,
                 "tool_mode": false,
@@ -4731,7 +4464,7 @@
                 "dynamic": false,
                 "info": "Authentication token for accessing Astra DB.",
                 "input_types": [],
-                "load_from_db": false,
+                "load_from_db": true,
                 "name": "token",
                 "password": true,
                 "placeholder": "",
@@ -4740,97 +4473,95 @@
                 "show": true,
                 "title_case": false,
                 "type": "str",
-                "value": ""
+                "value": "ASTRA_DB_APPLICATION_TOKEN"
               }
             },
             "tool_mode": false
           },
-          "selected_output": "dataframe",
+          "selected_output": "search_results",
           "showNode": true,
           "type": "AstraDB"
         },
         "dragging": false,
-        "id": "AstraDB-RaUqw",
+        "id": "AstraDB-TCSqR",
         "measured": {
-          "height": 375,
+          "height": 458,
           "width": 320
         },
         "position": {
-          "x": 1210.9603958451855,
-          "y": 519.26557834351
+          "x": 2095.3200255891484,
+          "y": 1501.719729125222
         },
         "selected": false,
         "type": "genericNode"
       },
       {
         "data": {
-          "id": "File-CxEQk",
+          "id": "AstraDB-BteL9",
           "node": {
             "base_classes": [
-              "Message"
+              "Data",
+              "DataFrame",
+              "VectorStore"
             ],
             "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",
+            "description": "Ingest and search documents in Astra DB",
+            "display_name": "Astra DB",
+            "documentation": "https://docs.datastax.com/en/langflow/astra-components.html",
             "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"
+              "token",
+              "environment",
+              "database_name",
+              "api_endpoint",
+              "keyspace",
+              "collection_name",
+              "embedding_model",
+              "ingest_data",
+              "search_query",
+              "should_cache_vector_store",
+              "search_method",
+              "reranker",
+              "lexical_terms",
+              "number_of_results",
+              "search_type",
+              "search_score_threshold",
+              "advanced_search_filter",
+              "autodetect_collection",
+              "content_field",
+              "deletion_field",
+              "ignore_invalid_documents",
+              "astradb_vectorstore_kwargs"
             ],
             "frozen": false,
-            "icon": "file-text",
-            "last_updated": "2025-12-20T17:35:27.280Z",
+            "icon": "AstraDB",
             "legacy": false,
             "metadata": {
-              "code_hash": "9d57e0bfda44",
+              "code_hash": "d52094e54e96",
               "dependencies": {
                 "dependencies": [
                   {
-                    "name": "lfx",
-                    "version": null
+                    "name": "astrapy",
+                    "version": "2.1.0"
                   },
                   {
                     "name": "langchain_core",
                     "version": "0.3.80"
                   },
                   {
-                    "name": "pydantic",
-                    "version": "2.11.10"
+                    "name": "lfx",
+                    "version": null
                   },
                   {
-                    "name": "googleapiclient",
-                    "version": "2.154.0"
+                    "name": "langchain_astradb",
+                    "version": "0.6.1"
                   }
                 ],
                 "total_dependencies": 4
               },
-              "module": "lfx.components.files_and_knowledge.file.FileComponent"
+              "module": "lfx.components.datastax.astradb_vectorstore.AstraDBVectorStoreComponent"
             },
             "minimized": false,
             "output_types": [],
@@ -4838,14 +4569,43 @@
               {
                 "allows_loop": false,
                 "cache": true,
-                "display_name": "Raw Content",
+                "display_name": "Search Results",
                 "group_outputs": false,
-                "method": "load_files_message",
-                "name": "message",
-                "selected": "Message",
+                "method": "search_documents",
+                "name": "search_results",
+                "selected": "Data",
                 "tool_mode": true,
                 "types": [
-                  "Message"
+                  "Data"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "as_dataframe",
+                "name": "dataframe",
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Vector Store Connection",
+                "group_outputs": false,
+                "hidden": false,
+                "method": "as_vector_store",
+                "name": "vectorstoreconnection",
+                "selected": "VectorStore",
+                "tool_mode": true,
+                "types": [
+                  "VectorStore"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -4853,469 +4613,470 @@
             "pinned": false,
             "template": {
               "_type": "Component",
-              "advanced_mode": {
-                "_input_type": "BoolInput",
-                "advanced": false,
-                "display_name": "Advanced Parser",
-                "dynamic": false,
-                "info": "Enable advanced document processing and export with Docling for PDFs, images, and office documents. Note that advanced document processing can consume significant resources.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "advanced_mode",
-                "override_skip": false,
-                "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": true,
-                "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",
-                "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,
-                "dynamic": true,
-                "fileTypes": [],
-                "file_path": "",
-                "info": "",
-                "list": false,
-                "load_from_db": false,
-                "multiline": true,
-                "name": "code",
-                "password": false,
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "type": "code",
-                "value": "\"\"\"Enhanced file component with Docling support and process isolation.\n\nNotes:\n-----\n- ALL Docling parsing/export runs in a separate OS process to prevent memory\n  growth and native library state from impacting the main Langflow process.\n- Standard text/structured parsing continues to use existing BaseFileComponent\n  utilities (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"
-              },
-              "concurrency_multithreading": {
-                "_input_type": "IntInput",
+              "advanced_search_filter": {
+                "_input_type": "NestedDictInput",
                 "advanced": true,
-                "display_name": "Processing Concurrency",
+                "display_name": "Search Metadata Filter",
                 "dynamic": false,
-                "info": "When multiple files are being processed, the number of files to process concurrently.",
+                "info": "Optional dictionary of filters to apply to the search query.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "concurrency_multithreading",
-                "override_skip": false,
+                "name": "advanced_search_filter",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "int",
-                "value": 1
+                "type": "NestedDict",
+                "value": {}
               },
-              "delete_server_file_after_processing": {
-                "_input_type": "BoolInput",
+              "api_endpoint": {
+                "_input_type": "DropdownInput",
                 "advanced": true,
-                "display_name": "Delete Server File After Processing",
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Astra DB API Endpoint",
                 "dynamic": false,
-                "info": "If true, the Server File Path will be deleted after processing.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "delete_server_file_after_processing",
-                "override_skip": false,
+                "external_options": {},
+                "info": "The API Endpoint for the Astra DB instance. Supercedes database selection.",
+                "name": "api_endpoint",
+                "options": [],
+                "options_metadata": [],
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": true
+                "type": "str",
+                "value": ""
               },
-              "doc_key": {
-                "_input_type": "MessageTextInput",
+              "astradb_vectorstore_kwargs": {
+                "_input_type": "NestedDictInput",
                 "advanced": true,
-                "display_name": "Doc Key",
+                "display_name": "AstraDBVectorStore Parameters",
                 "dynamic": false,
-                "info": "The key to use for the DoclingDocument column.",
-                "input_types": [
-                  "Message"
-                ],
+                "info": "Optional dictionary of additional parameters for the AstraDBVectorStore.",
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "doc_key",
-                "override_skip": false,
+                "name": "astradb_vectorstore_kwargs",
                 "placeholder": "",
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "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": ""
+                "type": "NestedDict",
+                "value": {}
               },
-              "file_path": {
-                "_input_type": "HandleInput",
+              "autodetect_collection": {
+                "_input_type": "BoolInput",
                 "advanced": true,
-                "display_name": "Server File Path",
+                "display_name": "Autodetect Collection",
                 "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,
+                "info": "Boolean flag to determine whether to autodetect the collection.",
+                "list": false,
                 "list_add_label": "Add More",
-                "name": "file_path",
-                "override_skip": false,
+                "name": "autodetect_collection",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
+                "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "other",
-                "value": ""
+                "type": "bool",
+                "value": true
               },
-              "file_path_str": {
-                "_input_type": "StrInput",
+              "code": {
                 "advanced": true,
-                "display_name": "File Path",
-                "dynamic": false,
-                "info": "Path to the file to read. Used when component is called as a tool. If not provided, will use the uploaded file from 'path' input.",
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
                 "list": false,
-                "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "file_path_str",
-                "override_skip": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
                 "placeholder": "",
-                "required": false,
-                "show": false,
+                "required": true,
+                "show": true,
                 "title_case": false,
-                "tool_mode": true,
-                "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": ""
+                "type": "code",
+                "value": "from astrapy import DataAPIClient\nfrom langchain_core.documents import Document\n\nfrom lfx.base.datastax.astradb_base import AstraDBBaseComponent\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom lfx.helpers.data import docs_to_data\nfrom lfx.io import BoolInput, DropdownInput, FloatInput, HandleInput, IntInput, NestedDictInput, QueryInput, StrInput\nfrom lfx.schema.data import Data\nfrom lfx.serialization import serialize\nfrom lfx.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(AstraDBBaseComponent, LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.langflow.org/bundles-datastax\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    inputs = [\n        *AstraDBBaseComponent.inputs,\n        *LCVectorStoreComponent.inputs,\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n    ]\n\n    async def update_build_config(\n        self,\n        build_config: dict,\n        field_value: str | dict,\n        field_name: str | None = None,\n    ) -> dict:\n        \"\"\"Update build configuration with proper handling of embedding and search options.\"\"\"\n        # Handle base astra db build config updates\n        build_config = await super().update_build_config(\n            build_config,\n            field_value=field_value,\n            field_name=field_name,\n        )\n\n        # Set embedding model display based on provider selection\n        if isinstance(field_value, dict) and \"02_embedding_generation_provider\" in field_value:\n            embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n            is_custom_provider = embedding_provider and embedding_provider != \"Bring your own\"\n            provider = embedding_provider.lower() if is_custom_provider and embedding_provider is not None else None\n\n            build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n            build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Early return if no API endpoint is configured\n        if not self.get_api_endpoint():\n            return build_config\n\n        # Configure search method and related options\n        return self._configure_search_options(build_config)\n\n    def _configure_search_options(self, build_config: dict) -> dict:\n        \"\"\"Configure hybrid search, reranker, and vector search options.\"\"\"\n        # Detect available hybrid search capabilities\n        hybrid_capabilities = self._detect_hybrid_capabilities()\n\n        # Return if we haven't selected a collection\n        if not build_config[\"collection_name\"][\"options\"] or not build_config[\"collection_name\"][\"value\"]:\n            return build_config\n\n        # Get collection options\n        collection_options = self._get_collection_options(build_config)\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(build_config[\"collection_name\"][\"value\"])\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Determine search configuration\n        is_vector_search = build_config[\"search_method\"][\"value\"] == \"Vector Search\"\n        is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n        # Apply hybrid search configuration\n        if hybrid_capabilities[\"available\"]:\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = build_config[\"search_method\"].get(\"value\", \"Hybrid Search\")\n\n            build_config[\"reranker\"][\"options\"] = hybrid_capabilities[\"reranker_models\"]\n            build_config[\"reranker\"][\"options_metadata\"] = hybrid_capabilities[\"reranker_metadata\"]\n            if hybrid_capabilities[\"reranker_models\"]:\n                build_config[\"reranker\"][\"value\"] = hybrid_capabilities[\"reranker_models\"][0]\n        else:\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n        # Configure reranker visibility and state\n        hybrid_enabled = (\n            collection_options[\"rerank_enabled\"] and build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        )\n\n        build_config[\"reranker\"][\"show\"] = hybrid_enabled\n        build_config[\"reranker\"][\"toggle_value\"] = hybrid_enabled\n        build_config[\"reranker\"][\"toggle_disable\"] = is_vector_search\n\n        # Configure lexical terms\n        lexical_visible = collection_options[\"lexical_enabled\"] and not is_vector_search\n        build_config[\"lexical_terms\"][\"show\"] = lexical_visible\n        build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n        # Configure search type and score threshold\n        build_config[\"search_type\"][\"show\"] = is_vector_search\n        build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n        # Force similarity search for hybrid mode or autodetect\n        if hybrid_enabled or is_autodetect:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    def _detect_hybrid_capabilities(self) -> dict:\n        \"\"\"Detect available hybrid search and reranking capabilities.\"\"\"\n        environment = self.get_environment(self.environment)\n        client = DataAPIClient(environment=environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        try:\n            providers = db_admin.find_reranking_providers()\n            reranker_models = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            reranker_metadata = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Hybrid search not available: {e}\")\n            return {\n                \"available\": False,\n                \"reranker_models\": [],\n                \"reranker_metadata\": [],\n            }\n        else:\n            return {\n                \"available\": True,\n                \"reranker_models\": reranker_models,\n                \"reranker_metadata\": reranker_metadata,\n            }\n\n    def _get_collection_options(self, build_config: dict) -> dict:\n        \"\"\"Retrieve collection-level search options.\"\"\"\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=build_config[\"collection_name\"][\"value\"],\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        col_options = collection.options()\n\n        return {\n            \"rerank_enabled\": bool(col_options.rerank and col_options.rerank.enabled),\n            \"lexical_enabled\": bool(col_options.lexical and col_options.lexical.enabled),\n        }\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n            from langchain_astradb.utils.astradb import HybridSearchMode\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except ValueError as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except ValueError as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except ValueError as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except ValueError as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except ValueError as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
               },
-              "ignore_unspecified_files": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Ignore Unspecified Files",
+              "collection_name": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": true,
+                "dialog_inputs": {
+                  "fields": {
+                    "data": {
+                      "node": {
+                        "description": "Please allow several seconds for creation to complete.",
+                        "display_name": "Create new collection",
+                        "field_order": [
+                          "01_new_collection_name",
+                          "02_embedding_generation_provider",
+                          "03_embedding_generation_model",
+                          "04_dimension"
+                        ],
+                        "name": "create_collection",
+                        "template": {
+                          "01_new_collection_name": {
+                            "_input_type": "StrInput",
+                            "advanced": false,
+                            "display_name": "Name",
+                            "dynamic": false,
+                            "info": "Name of the new collection to create in Astra DB.",
+                            "list": false,
+                            "list_add_label": "Add More",
+                            "load_from_db": false,
+                            "name": "new_collection_name",
+                            "placeholder": "",
+                            "required": true,
+                            "show": true,
+                            "title_case": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          },
+                          "02_embedding_generation_provider": {
+                            "_input_type": "DropdownInput",
+                            "advanced": false,
+                            "combobox": false,
+                            "dialog_inputs": {},
+                            "display_name": "Embedding generation method",
+                            "dynamic": false,
+                            "external_options": {},
+                            "helper_text": "To create collections with more embedding provider options, go to <a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" rel=\"noopener noreferrer\">your database in Astra DB</a>",
+                            "info": "Provider to use for generating embeddings.",
+                            "name": "embedding_generation_provider",
+                            "options": [],
+                            "options_metadata": [],
+                            "placeholder": "",
+                            "real_time_refresh": true,
+                            "required": true,
+                            "show": true,
+                            "title_case": false,
+                            "toggle": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          },
+                          "03_embedding_generation_model": {
+                            "_input_type": "DropdownInput",
+                            "advanced": false,
+                            "combobox": false,
+                            "dialog_inputs": {},
+                            "display_name": "Embedding model",
+                            "dynamic": false,
+                            "external_options": {},
+                            "info": "Model to use for generating embeddings.",
+                            "name": "embedding_generation_model",
+                            "options": [],
+                            "options_metadata": [],
+                            "placeholder": "",
+                            "real_time_refresh": true,
+                            "required": false,
+                            "show": true,
+                            "title_case": false,
+                            "toggle": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          },
+                          "04_dimension": {
+                            "_input_type": "IntInput",
+                            "advanced": false,
+                            "display_name": "Dimensions",
+                            "dynamic": false,
+                            "info": "Dimensions of the embeddings to generate.",
+                            "list": false,
+                            "list_add_label": "Add More",
+                            "name": "dimension",
+                            "placeholder": "",
+                            "required": false,
+                            "show": true,
+                            "title_case": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "int"
+                          }
+                        }
+                      }
+                    }
+                  },
+                  "functionality": "create"
+                },
+                "display_name": "Collection",
                 "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",
-                "override_skip": false,
+                "external_options": {},
+                "info": "The name of the collection within Astra DB where the vectors will be stored.",
+                "name": "collection_name",
+                "options": [],
+                "options_metadata": [],
                 "placeholder": "",
-                "required": false,
-                "show": true,
+                "real_time_refresh": true,
+                "refresh_button": true,
+                "required": 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": ""
               },
-              "ignore_unsupported_extensions": {
-                "_input_type": "BoolInput",
+              "content_field": {
+                "_input_type": "StrInput",
                 "advanced": true,
-                "display_name": "Ignore Unsupported Extensions",
+                "display_name": "Content Field",
                 "dynamic": false,
-                "info": "If true, files with unsupported extensions will not be processed.",
+                "info": "Field to use as the text content field for the vector store.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "ignore_unsupported_extensions",
-                "override_skip": false,
+                "load_from_db": false,
+                "name": "content_field",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": true
+                "type": "str",
+                "value": ""
               },
-              "markdown": {
-                "_input_type": "BoolInput",
+              "database_name": {
+                "_input_type": "DropdownInput",
                 "advanced": false,
-                "display_name": "Markdown Export",
+                "combobox": true,
+                "dialog_inputs": {
+                  "fields": {
+                    "data": {
+                      "node": {
+                        "description": "Please allow several minutes for creation to complete.",
+                        "display_name": "Create new database",
+                        "field_order": [
+                          "01_new_database_name",
+                          "02_cloud_provider",
+                          "03_region"
+                        ],
+                        "name": "create_database",
+                        "template": {
+                          "01_new_database_name": {
+                            "_input_type": "StrInput",
+                            "advanced": false,
+                            "display_name": "Name",
+                            "dynamic": false,
+                            "info": "Name of the new database to create in Astra DB.",
+                            "list": false,
+                            "list_add_label": "Add More",
+                            "load_from_db": false,
+                            "name": "new_database_name",
+                            "placeholder": "",
+                            "required": true,
+                            "show": true,
+                            "title_case": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          },
+                          "02_cloud_provider": {
+                            "_input_type": "DropdownInput",
+                            "advanced": false,
+                            "combobox": false,
+                            "dialog_inputs": {},
+                            "display_name": "Cloud provider",
+                            "dynamic": false,
+                            "external_options": {},
+                            "info": "Cloud provider for the new database.",
+                            "name": "cloud_provider",
+                            "options": [],
+                            "options_metadata": [],
+                            "placeholder": "",
+                            "real_time_refresh": true,
+                            "required": true,
+                            "show": true,
+                            "title_case": false,
+                            "toggle": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          },
+                          "03_region": {
+                            "_input_type": "DropdownInput",
+                            "advanced": false,
+                            "combobox": false,
+                            "dialog_inputs": {},
+                            "display_name": "Region",
+                            "dynamic": false,
+                            "external_options": {},
+                            "info": "Region for the new database.",
+                            "name": "region",
+                            "options": [],
+                            "options_metadata": [],
+                            "placeholder": "",
+                            "required": true,
+                            "show": true,
+                            "title_case": false,
+                            "toggle": false,
+                            "tool_mode": false,
+                            "trace_as_metadata": true,
+                            "type": "str",
+                            "value": ""
+                          }
+                        }
+                      }
+                    }
+                  },
+                  "functionality": "create"
+                },
+                "display_name": "Database",
                 "dynamic": false,
-                "info": "Export processed documents to Markdown format. Only available when advanced mode is enabled.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "markdown",
-                "override_skip": false,
+                "external_options": {},
+                "info": "The Database name for the Astra DB instance.",
+                "name": "database_name",
+                "options": [],
+                "options_metadata": [],
                 "placeholder": "",
-                "required": false,
-                "show": false,
+                "real_time_refresh": true,
+                "refresh_button": true,
+                "required": true,
+                "show": true,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
+                "type": "str",
+                "value": ""
               },
-              "md_image_placeholder": {
+              "deletion_field": {
                 "_input_type": "StrInput",
                 "advanced": true,
-                "display_name": "Image placeholder",
+                "display_name": "Deletion Based On Field",
                 "dynamic": false,
-                "info": "Specify the image placeholder for markdown exports.",
+                "info": "When this parameter is provided, documents in the target collection with metadata field values matching the input metadata field value will be deleted before new data is loaded.",
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "md_image_placeholder",
-                "override_skip": false,
+                "name": "deletion_field",
                 "placeholder": "",
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
                 "type": "str",
-                "value": "<!-- image -->"
+                "value": ""
               },
-              "md_page_break_placeholder": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Page break placeholder",
+              "embedding_model": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Embedding Model",
                 "dynamic": false,
-                "info": "Add this placeholder between pages in the markdown output.",
+                "info": "Specify the Embedding Model. Not required for Astra Vectorize collections.",
+                "input_types": [
+                  "Embeddings"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "md_page_break_placeholder",
-                "override_skip": false,
+                "name": "embedding_model",
                 "placeholder": "",
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
-                "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
+                "type": "other",
                 "value": ""
               },
-              "ocr_engine": {
+              "environment": {
                 "_input_type": "DropdownInput",
                 "advanced": true,
-                "combobox": false,
+                "combobox": true,
                 "dialog_inputs": {},
-                "display_name": "OCR Engine",
+                "display_name": "Environment",
                 "dynamic": false,
                 "external_options": {},
-                "info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
-                "name": "ocr_engine",
+                "info": "The environment for the Astra DB API Endpoint.",
+                "name": "environment",
                 "options": [
-                  "None",
-                  "easyocr"
+                  "prod",
+                  "test",
+                  "dev"
                 ],
                 "options_metadata": [],
-                "override_skip": false,
                 "placeholder": "",
+                "real_time_refresh": true,
                 "required": false,
-                "show": false,
+                "show": true,
                 "title_case": false,
                 "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
                 "type": "str",
-                "value": "easyocr"
+                "value": "prod"
               },
-              "path": {
-                "_input_type": "FileInput",
-                "advanced": false,
-                "display_name": "Files",
+              "ignore_invalid_documents": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Ignore Invalid Documents",
                 "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"
+                "info": "Boolean flag to determine whether to ignore invalid documents at runtime.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ignore_invalid_documents",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              },
+              "ingest_data": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Ingest Data",
+                "dynamic": false,
+                "info": "",
+                "input_types": [
+                  "Data",
+                  "DataFrame"
                 ],
-                "file_path": [],
-                "info": "Supported file extensions: csv, json, pdf, txt, md, mdx, yaml, yml, xml, html, htm, docx, py, sh, sql, js, ts, tsx, adoc, asciidoc, asc, bmp, dotx, dotm, docm, jpg, jpeg, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, xls, xlsx, xhtml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
                 "list": true,
                 "list_add_label": "Add More",
-                "name": "path",
-                "override_skip": false,
+                "name": "ingest_data",
                 "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": false,
-                "type": "file",
+                "type": "other",
                 "value": ""
               },
-              "pipeline": {
+              "keyspace": {
                 "_input_type": "DropdownInput",
                 "advanced": true,
                 "combobox": false,
                 "dialog_inputs": {},
-                "display_name": "Pipeline",
+                "display_name": "Keyspace",
                 "dynamic": false,
                 "external_options": {},
-                "info": "Docling pipeline to use",
-                "name": "pipeline",
-                "options": [
-                  "standard",
-                  "vlm"
-                ],
+                "info": "Optional keyspace within Astra DB to use for the collection.",
+                "name": "keyspace",
+                "options": [],
                 "options_metadata": [],
-                "override_skip": false,
                 "placeholder": "",
                 "real_time_refresh": true,
                 "required": false,
@@ -5324,177 +5085,241 @@
                 "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
                 "type": "str",
-                "value": "standard"
+                "value": ""
               },
-              "s3_file_key": {
-                "_input_type": "StrInput",
+              "lexical_terms": {
+                "_input_type": "QueryInput",
                 "advanced": false,
-                "display_name": "S3 File Key",
+                "display_name": "Lexical Terms",
                 "dynamic": false,
-                "info": "The key (path) of the file in S3 bucket.",
+                "info": "Add additional terms/keywords to augment search precision.",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
                 "load_from_db": false,
-                "name": "s3_file_key",
-                "override_skip": false,
-                "placeholder": "",
-                "required": true,
+                "name": "lexical_terms",
+                "placeholder": "Enter terms to search...",
+                "required": false,
+                "separator": " ",
                 "show": false,
                 "title_case": false,
                 "tool_mode": false,
+                "trace_as_input": true,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
+                "type": "query",
                 "value": ""
               },
-              "separator": {
-                "_input_type": "StrInput",
+              "number_of_results": {
+                "_input_type": "IntInput",
                 "advanced": true,
-                "display_name": "Separator",
+                "display_name": "Number of Search Results",
                 "dynamic": false,
-                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "info": "Number of search results to return.",
                 "list": false,
                 "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "separator",
-                "override_skip": false,
+                "name": "number_of_results",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "str",
-                "value": "\n\n"
+                "type": "int",
+                "value": 4
               },
-              "service_account_key": {
-                "_input_type": "SecretStrInput",
+              "reranker": {
+                "_input_type": "DropdownInput",
                 "advanced": false,
-                "display_name": "GCP Credentials Secret Key",
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Reranker",
                 "dynamic": false,
-                "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,
+                "external_options": {},
+                "info": "Post-retrieval model that re-scores results for optimal relevance ranking.",
+                "name": "reranker",
+                "options": [],
+                "options_metadata": [],
                 "placeholder": "",
-                "required": true,
+                "required": false,
                 "show": false,
                 "title_case": false,
-                "track_in_telemetry": false,
+                "toggle": true,
+                "tool_mode": false,
+                "trace_as_metadata": true,
                 "type": "str",
                 "value": ""
               },
-              "silent_errors": {
-                "_input_type": "BoolInput",
+              "search_method": {
+                "_input_type": "DropdownInput",
                 "advanced": true,
-                "display_name": "Silent Errors",
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Search Method",
                 "dynamic": false,
-                "info": "If true, errors will not raise an exception.",
+                "external_options": {},
+                "info": "Determine how your content is matched: Vector finds semantic similarity, and Hybrid Search (suggested) combines both approaches with a reranker.",
+                "name": "search_method",
+                "options": [
+                  "Hybrid Search",
+                  "Vector Search"
+                ],
+                "options_metadata": [
+                  {
+                    "icon": "SearchHybrid"
+                  },
+                  {
+                    "icon": "SearchVector"
+                  }
+                ],
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "Vector Search"
+              },
+              "search_query": {
+                "_input_type": "QueryInput",
+                "advanced": false,
+                "display_name": "Search Query",
+                "dynamic": false,
+                "info": "Enter a query to run a similarity search.",
+                "input_types": [
+                  "Message"
+                ],
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "silent_errors",
-                "override_skip": false,
+                "load_from_db": false,
+                "name": "search_query",
+                "placeholder": "Enter a query...",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": true,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "query",
+                "value": ""
+              },
+              "search_score_threshold": {
+                "_input_type": "FloatInput",
+                "advanced": true,
+                "display_name": "Search Score Threshold",
+                "dynamic": false,
+                "info": "Minimum similarity score threshold for search results. (when using 'Similarity with score threshold')",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "search_score_threshold",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
-                "type": "bool",
-                "value": false
+                "type": "float",
+                "value": 0
               },
-              "storage_location": {
-                "_input_type": "SortableListInput",
-                "advanced": false,
-                "display_name": "Storage Location",
+              "search_type": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Search Type",
                 "dynamic": false,
-                "info": "Choose where to read the file from.",
-                "limit": 1,
-                "name": "storage_location",
+                "external_options": {},
+                "info": "Search type to use",
+                "name": "search_type",
                 "options": [
-                  {
-                    "icon": "hard-drive",
-                    "name": "Local"
-                  },
-                  {
-                    "icon": "Amazon",
-                    "name": "AWS"
-                  },
-                  {
-                    "icon": "google",
-                    "name": "Google Drive"
-                  }
+                  "Similarity",
+                  "Similarity with score threshold",
+                  "MMR (Max Marginal Relevance)"
                 ],
-                "override_skip": false,
-                "placeholder": "Select Location",
-                "real_time_refresh": true,
+                "options_metadata": [],
+                "placeholder": "",
                 "required": false,
-                "search_category": [],
                 "show": true,
                 "title_case": false,
+                "toggle": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": false,
-                "type": "sortableList",
-                "value": ""
+                "type": "str",
+                "value": "Similarity"
               },
-              "use_multithreading": {
+              "should_cache_vector_store": {
                 "_input_type": "BoolInput",
                 "advanced": true,
-                "display_name": "[Deprecated] Use Multithreading",
+                "display_name": "Cache Vector Store",
                 "dynamic": false,
-                "info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
+                "info": "If True, the vector store will be cached for the current build of the component. This is useful for components that have multiple output methods and want to share the same vector store.",
                 "list": false,
                 "list_add_label": "Add More",
-                "name": "use_multithreading",
-                "override_skip": false,
+                "name": "should_cache_vector_store",
                 "placeholder": "",
                 "required": false,
                 "show": true,
                 "title_case": false,
                 "tool_mode": false,
                 "trace_as_metadata": true,
-                "track_in_telemetry": true,
                 "type": "bool",
                 "value": true
+              },
+              "token": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "Astra DB Application Token",
+                "dynamic": false,
+                "info": "Authentication token for accessing Astra DB.",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "token",
+                "password": true,
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "str",
+                "value": "ASTRA_DB_APPLICATION_TOKEN"
               }
             },
             "tool_mode": false
           },
+          "selected_output": "dataframe",
           "showNode": true,
-          "type": "File"
+          "type": "AstraDB"
         },
         "dragging": false,
-        "id": "File-CxEQk",
+        "id": "AstraDB-BteL9",
         "measured": {
-          "height": 341,
+          "height": 458,
           "width": 320
         },
         "position": {
-          "x": 1302.7984173779507,
-          "y": 1488.2184097961633
+          "x": 1210.9603958451855,
+          "y": 519.26557834351
         },
-        "selected": true,
+        "selected": false,
         "type": "genericNode"
       }
     ],
     "viewport": {
-      "x": -4.162462882999193,
-      "y": -126.94022637175613,
-      "zoom": 0.37674635518371946
+      "x": -242.44739610333954,
+      "y": -59.21391294314947,
+      "zoom": 0.4677494046491174
     }
   },
   "description": "Load your data for chat context with Retrieval Augmented Generation.",
   "endpoint_name": null,
-  "id": "be165273-a6ce-4053-9548-e5b5c8a657bf",
+  "id": "64f82d31-c711-441d-8082-fdb46cda7cdd",
   "is_component": false,
-  "last_tested_version": "1.7.0",
+  "last_tested_version": "1.6.4",
   "name": "Vector Store RAG",
   "tags": [
     "openai",