diff --git a/flows/ingestion_flow.json b/flows/ingestion_flow.json index 911c3e38..092e2cec 100644 --- a/flows/ingestion_flow.json +++ b/flows/ingestion_flow.json @@ -23,12 +23,12 @@ "type": "other" } }, - "id": "xy-edge__SplitText-QIKhg{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}", + "id": "xy-edge__SplitText-QIKhg{\u0153dataType\u0153:\u0153SplitText\u0153,\u0153id\u0153:\u0153SplitText-QIKhg\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-OpenSearchHybrid-Ve6bS{\u0153fieldName\u0153:\u0153ingest_data\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "SplitText-QIKhg", - "sourceHandle": "{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153SplitText\u0153,\u0153id\u0153:\u0153SplitText-QIKhg\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "OpenSearchHybrid-Ve6bS", - "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153ingest_data\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -51,12 +51,12 @@ "type": "other" } }, - "id": "xy-edge__EmbeddingModel-eZ6bT{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-eZ6bTœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}", + "id": "xy-edge__EmbeddingModel-eZ6bT{\u0153dataType\u0153:\u0153EmbeddingModel\u0153,\u0153id\u0153:\u0153EmbeddingModel-eZ6bT\u0153,\u0153name\u0153:\u0153embeddings\u0153,\u0153output_types\u0153:[\u0153Embeddings\u0153]}-OpenSearchHybrid-Ve6bS{\u0153fieldName\u0153:\u0153embedding\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Embeddings\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "EmbeddingModel-eZ6bT", - "sourceHandle": "{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-eZ6bTœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153EmbeddingModel\u0153,\u0153id\u0153:\u0153EmbeddingModel-eZ6bT\u0153,\u0153name\u0153:\u0153embeddings\u0153,\u0153output_types\u0153:[\u0153Embeddings\u0153]}", "target": "OpenSearchHybrid-Ve6bS", - "targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153embedding\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Embeddings\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -80,12 +80,12 @@ "type": "str" } }, - "id": "xy-edge__SecretInput-F34VJ{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-F34VJœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-81Exw{œfieldNameœ:œdynamic_connector_typeœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}", + "id": "xy-edge__SecretInput-F34VJ{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-F34VJ\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-AdvancedDynamicFormBuilder-81Exw{\u0153fieldName\u0153:\u0153dynamic_connector_type\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}", "selected": false, "source": "SecretInput-F34VJ", - "sourceHandle": "{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-F34VJœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-F34VJ\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}", "target": "AdvancedDynamicFormBuilder-81Exw", - "targetHandle": "{œfieldNameœ:œdynamic_connector_typeœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153dynamic_connector_type\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}" }, { "animated": false, @@ -109,12 +109,12 @@ "type": "str" } }, - "id": "xy-edge__SecretInput-b2cab{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-b2cabœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-81Exw{œfieldNameœ:œdynamic_ownerœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}", + "id": "xy-edge__SecretInput-b2cab{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-b2cab\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-AdvancedDynamicFormBuilder-81Exw{\u0153fieldName\u0153:\u0153dynamic_owner\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}", "selected": false, "source": "SecretInput-b2cab", - "sourceHandle": "{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-b2cabœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-b2cab\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}", "target": "AdvancedDynamicFormBuilder-81Exw", - "targetHandle": "{œfieldNameœ:œdynamic_ownerœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153dynamic_owner\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}" }, { "animated": false, @@ -138,12 +138,12 @@ "type": "str" } }, - "id": "xy-edge__SecretInput-ZVfuS{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-ZVfuSœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-81Exw{œfieldNameœ:œdynamic_owner_emailœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}", + "id": "xy-edge__SecretInput-ZVfuS{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-ZVfuS\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-AdvancedDynamicFormBuilder-81Exw{\u0153fieldName\u0153:\u0153dynamic_owner_email\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}", "selected": false, "source": "SecretInput-ZVfuS", - "sourceHandle": "{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-ZVfuSœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-ZVfuS\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}", "target": "AdvancedDynamicFormBuilder-81Exw", - "targetHandle": "{œfieldNameœ:œdynamic_owner_emailœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153dynamic_owner_email\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}" }, { "animated": false, @@ -167,12 +167,12 @@ "type": "str" } }, - "id": "xy-edge__SecretInput-Iqtxd{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-Iqtxdœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-AdvancedDynamicFormBuilder-81Exw{œfieldNameœ:œdynamic_owner_nameœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}", + "id": "xy-edge__SecretInput-Iqtxd{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-Iqtxd\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}-AdvancedDynamicFormBuilder-81Exw{\u0153fieldName\u0153:\u0153dynamic_owner_name\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}", "selected": false, "source": "SecretInput-Iqtxd", - "sourceHandle": "{œdataTypeœ:œSecretInputœ,œidœ:œSecretInput-Iqtxdœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153SecretInput\u0153,\u0153id\u0153:\u0153SecretInput-Iqtxd\u0153,\u0153name\u0153:\u0153text\u0153,\u0153output_types\u0153:[\u0153Message\u0153]}", "target": "AdvancedDynamicFormBuilder-81Exw", - "targetHandle": "{œfieldNameœ:œdynamic_owner_nameœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œinputTypesœ:[œTextœ,œMessageœ],œtypeœ:œstrœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153dynamic_owner_name\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153inputTypes\u0153:[\u0153Text\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153str\u0153}" }, { "animated": false, @@ -195,12 +195,12 @@ "type": "table" } }, - "id": "xy-edge__AdvancedDynamicFormBuilder-81Exw{œdataTypeœ:œAdvancedDynamicFormBuilderœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œnameœ:œform_dataœ,œoutput_typesœ:[œDataœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œdocs_metadataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ],œtypeœ:œtableœ}", + "id": "xy-edge__AdvancedDynamicFormBuilder-81Exw{\u0153dataType\u0153:\u0153AdvancedDynamicFormBuilder\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153name\u0153:\u0153form_data\u0153,\u0153output_types\u0153:[\u0153Data\u0153]}-OpenSearchHybrid-Ve6bS{\u0153fieldName\u0153:\u0153docs_metadata\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153],\u0153type\u0153:\u0153table\u0153}", "selected": false, "source": "AdvancedDynamicFormBuilder-81Exw", - "sourceHandle": "{œdataTypeœ:œAdvancedDynamicFormBuilderœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œnameœ:œform_dataœ,œoutput_typesœ:[œDataœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153AdvancedDynamicFormBuilder\u0153,\u0153id\u0153:\u0153AdvancedDynamicFormBuilder-81Exw\u0153,\u0153name\u0153:\u0153form_data\u0153,\u0153output_types\u0153:[\u0153Data\u0153]}", "target": "OpenSearchHybrid-Ve6bS", - "targetHandle": "{œfieldNameœ:œdocs_metadataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ],œtypeœ:œtableœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153docs_metadata\u0153,\u0153id\u0153:\u0153OpenSearchHybrid-Ve6bS\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153],\u0153type\u0153:\u0153table\u0153}" }, { "animated": false, @@ -224,12 +224,12 @@ "type": "other" } }, - "id": "xy-edge__DoclingRemote-Dp3PX{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-ExportDoclingDocument-zZdRg{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}", + "id": "xy-edge__DoclingRemote-Dp3PX{\u0153dataType\u0153:\u0153DoclingRemote\u0153,\u0153id\u0153:\u0153DoclingRemote-Dp3PX\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-ExportDoclingDocument-zZdRg{\u0153fieldName\u0153:\u0153data_inputs\u0153,\u0153id\u0153:\u0153ExportDoclingDocument-zZdRg\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "DoclingRemote-Dp3PX", - "sourceHandle": "{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153DoclingRemote\u0153,\u0153id\u0153:\u0153DoclingRemote-Dp3PX\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "ExportDoclingDocument-zZdRg", - "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153data_inputs\u0153,\u0153id\u0153:\u0153ExportDoclingDocument-zZdRg\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -252,12 +252,12 @@ "type": "other" } }, - "id": "xy-edge__ExportDoclingDocument-zZdRg{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-1BWXB{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-1BWXBœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}", + "id": "xy-edge__ExportDoclingDocument-zZdRg{\u0153dataType\u0153:\u0153ExportDoclingDocument\u0153,\u0153id\u0153:\u0153ExportDoclingDocument-zZdRg\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-DataFrameOperations-1BWXB{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-1BWXB\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "ExportDoclingDocument-zZdRg", - "sourceHandle": "{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153ExportDoclingDocument\u0153,\u0153id\u0153:\u0153ExportDoclingDocument-zZdRg\u0153,\u0153name\u0153:\u0153dataframe\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "DataFrameOperations-1BWXB", - "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-1BWXBœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-1BWXB\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -282,12 +282,12 @@ "type": "other" } }, - "id": "xy-edge__DataFrameOperations-N80fC{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-N80fCœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-SplitText-QIKhg{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}", + "id": "xy-edge__DataFrameOperations-N80fC{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-N80fC\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-SplitText-QIKhg{\u0153fieldName\u0153:\u0153data_inputs\u0153,\u0153id\u0153:\u0153SplitText-QIKhg\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "DataFrameOperations-N80fC", - "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-N80fCœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-N80fC\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "SplitText-QIKhg", - "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153data_inputs\u0153,\u0153id\u0153:\u0153SplitText-QIKhg\u0153,\u0153inputTypes\u0153:[\u0153Data\u0153,\u0153DataFrame\u0153,\u0153Message\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -310,12 +310,12 @@ "type": "other" } }, - "id": "xy-edge__DataFrameOperations-1BWXB{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-1BWXBœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-9vMrp{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-9vMrpœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}", + "id": "xy-edge__DataFrameOperations-1BWXB{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-1BWXB\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-DataFrameOperations-9vMrp{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-9vMrp\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "DataFrameOperations-1BWXB", - "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-1BWXBœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-1BWXB\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "DataFrameOperations-9vMrp", - "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-9vMrpœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-9vMrp\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}" }, { "animated": false, @@ -338,12 +338,12 @@ "type": "other" } }, - "id": "xy-edge__DataFrameOperations-9vMrp{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-9vMrpœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-N80fC{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-N80fCœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}", + "id": "xy-edge__DataFrameOperations-9vMrp{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-9vMrp\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}-DataFrameOperations-N80fC{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-N80fC\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}", "selected": false, "source": "DataFrameOperations-9vMrp", - "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-9vMrpœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}", + "sourceHandle": "{\u0153dataType\u0153:\u0153DataFrameOperations\u0153,\u0153id\u0153:\u0153DataFrameOperations-9vMrp\u0153,\u0153name\u0153:\u0153output\u0153,\u0153output_types\u0153:[\u0153DataFrame\u0153]}", "target": "DataFrameOperations-N80fC", - "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-N80fCœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}" + "targetHandle": "{\u0153fieldName\u0153:\u0153df\u0153,\u0153id\u0153:\u0153DataFrameOperations-N80fC\u0153,\u0153inputTypes\u0153:[\u0153DataFrame\u0153],\u0153type\u0153:\u0153other\u0153}" } ], "nodes": [ @@ -602,8 +602,8 @@ "beta": false, "conditional_paths": [], "custom_fields": {}, - "description": "Store and search documents using OpenSearch with hybrid semantic and keyword search capabilities.", - "display_name": "OpenSearch", + "description": "Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search.", + "display_name": "OpenSearch (Multi-Model)", "documentation": "", "edited": true, "field_order": [ @@ -618,6 +618,7 @@ "search_query", "should_cache_vector_store", "embedding", + "embedding_model_name", "vector_field", "number_of_results", "filter_expression", @@ -632,10 +633,10 @@ ], "frozen": false, "icon": "OpenSearch", + "last_updated": "2025-10-10T14:37:10.405Z", "legacy": false, - "lf_version": "1.6.3.dev0", "metadata": { - "code_hash": "c81b23acb81a", + "code_hash": "62d330aec569", "dependencies": { "dependencies": [ { @@ -644,12 +645,12 @@ }, { "name": "lfx", - "version": null + "version": "0.1.12.dev32" } ], "total_dependencies": 2 }, - "module": "custom_components.opensearch" + "module": "custom_components.opensearch_multimodel" }, "minimized": false, "output_types": [], @@ -747,7 +748,7 @@ "name": "bearer_prefix", "placeholder": "", "required": false, - "show": false, + "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, @@ -770,7 +771,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from __future__ import annotations\n\nimport json\nimport uuid\nfrom typing import Any\n\nfrom opensearchpy import OpenSearch, helpers\n\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.io import BoolInput, DropdownInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput, TableInput\nfrom lfx.log import logger\nfrom lfx.schema.data import Data\n\n\n@vector_store_connection\nclass OpenSearchVectorStoreComponent(LCVectorStoreComponent):\n \"\"\"OpenSearch Vector Store Component with Hybrid Search Capabilities.\n\n This component provides vector storage and retrieval using OpenSearch, combining semantic\n similarity search (KNN) with keyword-based search for optimal results. It supports document\n ingestion, vector embeddings, and advanced filtering with authentication options.\n\n Features:\n - Vector storage with configurable engines (jvector, nmslib, faiss, lucene)\n - Hybrid search combining KNN vector similarity and keyword matching\n - Flexible authentication (Basic auth, JWT tokens)\n - Advanced filtering and aggregations\n - Metadata injection during document ingestion\n \"\"\"\n\n display_name: str = \"OpenSearch\"\n icon: str = \"OpenSearch\"\n description: str = (\n \"Store and search documents using OpenSearch with hybrid semantic and keyword search capabilities.\"\n )\n\n # Keys we consider baseline\n default_keys: list[str] = [\n \"opensearch_url\",\n \"index_name\",\n *[i.name for i in LCVectorStoreComponent.inputs], # search_query, add_documents, etc.\n \"embedding\",\n \"vector_field\",\n \"number_of_results\",\n \"auth_mode\",\n \"username\",\n \"password\",\n \"jwt_token\",\n \"jwt_header\",\n \"bearer_prefix\",\n \"use_ssl\",\n \"verify_certs\",\n \"filter_expression\",\n \"engine\",\n \"space_type\",\n \"ef_construction\",\n \"m\",\n \"docs_metadata\",\n ]\n\n inputs = [\n TableInput(\n name=\"docs_metadata\",\n display_name=\"Document Metadata\",\n info=(\n \"Additional metadata key-value pairs to be added to all ingested documents. \"\n \"Useful for tagging documents with source information, categories, or other custom attributes.\"\n ),\n table_schema=[\n {\n \"name\": \"key\",\n \"display_name\": \"Key\",\n \"type\": \"str\",\n \"description\": \"Key name\",\n },\n {\n \"name\": \"value\",\n \"display_name\": \"Value\",\n \"type\": \"str\",\n \"description\": \"Value of the metadata\",\n },\n ],\n value=[],\n # advanced=True,\n input_types=[\"Data\"]\n ),\n StrInput(\n name=\"opensearch_url\",\n display_name=\"OpenSearch URL\",\n value=\"http://localhost:9200\",\n info=(\n \"The connection URL for your OpenSearch cluster \"\n \"(e.g., http://localhost:9200 for local development or your cloud endpoint).\"\n ),\n ),\n StrInput(\n name=\"index_name\",\n display_name=\"Index Name\",\n value=\"langflow\",\n info=(\n \"The OpenSearch index name where documents will be stored and searched. \"\n \"Will be created automatically if it doesn't exist.\"\n ),\n ),\n DropdownInput(\n name=\"engine\",\n display_name=\"Vector Engine\",\n options=[\"jvector\", \"nmslib\", \"faiss\", \"lucene\"],\n value=\"jvector\",\n info=(\n \"Vector search engine for similarity calculations. 'jvector' is recommended for most use cases. \"\n \"Note: Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.\"\n ),\n advanced=True,\n ),\n DropdownInput(\n name=\"space_type\",\n display_name=\"Distance Metric\",\n options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n value=\"l2\",\n info=(\n \"Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, \"\n \"'cosinesimil' for cosine similarity, 'innerproduct' for dot product.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"ef_construction\",\n display_name=\"EF Construction\",\n value=512,\n info=(\n \"Size of the dynamic candidate list during index construction. \"\n \"Higher values improve recall but increase indexing time and memory usage.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"m\",\n display_name=\"M Parameter\",\n value=16,\n info=(\n \"Number of bidirectional connections for each vector in the HNSW graph. \"\n \"Higher values improve search quality but increase memory usage and indexing time.\"\n ),\n advanced=True,\n ),\n *LCVectorStoreComponent.inputs, # includes search_query, add_documents, etc.\n HandleInput(name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"]),\n StrInput(\n name=\"vector_field\",\n display_name=\"Vector Field Name\",\n value=\"chunk_embedding\",\n advanced=True,\n info=\"Name of the field in OpenSearch documents that stores the vector embeddings for similarity search.\",\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Default Result Limit\",\n value=10,\n advanced=True,\n info=(\n \"Default maximum number of search results to return when no limit is \"\n \"specified in the filter expression.\"\n ),\n ),\n MultilineInput(\n name=\"filter_expression\",\n display_name=\"Search Filters (JSON)\",\n value=\"\",\n info=(\n \"Optional JSON configuration for search filtering, result limits, and score thresholds.\\n\\n\"\n \"Format 1 - Explicit filters:\\n\"\n '{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, '\n '{\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\\n\\n'\n \"Format 2 - Context-style mapping:\\n\"\n '{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\\n\\n'\n \"Use __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.\"\n ),\n ),\n # ----- Auth controls (dynamic) -----\n DropdownInput(\n name=\"auth_mode\",\n display_name=\"Authentication Mode\",\n value=\"basic\",\n options=[\"basic\", \"jwt\"],\n info=(\n \"Authentication method: 'basic' for username/password authentication, \"\n \"or 'jwt' for JSON Web Token (Bearer) authentication.\"\n ),\n real_time_refresh=True,\n advanced=False,\n ),\n StrInput(\n name=\"username\",\n display_name=\"Username\",\n value=\"admin\",\n show=False,\n ),\n SecretStrInput(\n name=\"password\",\n display_name=\"OpenSearch Password\",\n value=\"admin\",\n show=False,\n ),\n SecretStrInput(\n name=\"jwt_token\",\n display_name=\"JWT Token\",\n value=\"JWT\",\n load_from_db=False,\n show=True,\n info=(\n \"Valid JSON Web Token for authentication. \"\n \"Will be sent in the Authorization header (with optional 'Bearer ' prefix).\"\n ),\n ),\n StrInput(\n name=\"jwt_header\",\n display_name=\"JWT Header Name\",\n value=\"Authorization\",\n show=False,\n advanced=True,\n ),\n BoolInput(\n name=\"bearer_prefix\",\n display_name=\"Prefix 'Bearer '\",\n value=True,\n show=False,\n advanced=True,\n ),\n # ----- TLS -----\n BoolInput(\n name=\"use_ssl\",\n display_name=\"Use SSL/TLS\",\n value=True,\n advanced=True,\n info=\"Enable SSL/TLS encryption for secure connections to OpenSearch.\",\n ),\n BoolInput(\n name=\"verify_certs\",\n display_name=\"Verify SSL Certificates\",\n value=False,\n advanced=True,\n info=(\n \"Verify SSL certificates when connecting. \"\n \"Disable for self-signed certificates in development environments.\"\n ),\n ),\n ]\n\n # ---------- helper functions for index management ----------\n def _default_text_mapping(\n self,\n dim: int,\n engine: str = \"jvector\",\n space_type: str = \"l2\",\n ef_search: int = 512,\n ef_construction: int = 100,\n m: int = 16,\n vector_field: str = \"vector_field\",\n ) -> dict[str, Any]:\n \"\"\"Create the default OpenSearch index mapping for vector search.\n\n This method generates the index configuration with k-NN settings optimized\n for approximate nearest neighbor search using the specified vector engine.\n\n Args:\n dim: Dimensionality of the vector embeddings\n engine: Vector search engine (jvector, nmslib, faiss, lucene)\n space_type: Distance metric for similarity calculation\n ef_search: Size of dynamic list used during search\n ef_construction: Size of dynamic list used during index construction\n m: Number of bidirectional links for each vector\n vector_field: Name of the field storing vector embeddings\n\n Returns:\n Dictionary containing OpenSearch index mapping configuration\n \"\"\"\n return {\n \"settings\": {\"index\": {\"knn\": True, \"knn.algo_param.ef_search\": ef_search}},\n \"mappings\": {\n \"properties\": {\n vector_field: {\n \"type\": \"knn_vector\",\n \"dimension\": dim,\n \"method\": {\n \"name\": \"disk_ann\",\n \"space_type\": space_type,\n \"engine\": engine,\n \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n },\n }\n }\n },\n }\n\n def _validate_aoss_with_engines(self, *, is_aoss: bool, engine: str) -> None:\n \"\"\"Validate engine compatibility with Amazon OpenSearch Serverless (AOSS).\n\n Amazon OpenSearch Serverless has restrictions on which vector engines\n can be used. This method ensures the selected engine is compatible.\n\n Args:\n is_aoss: Whether the connection is to Amazon OpenSearch Serverless\n engine: The selected vector search engine\n\n Raises:\n ValueError: If AOSS is used with an incompatible engine\n \"\"\"\n if is_aoss and engine not in {\"nmslib\", \"faiss\"}:\n msg = \"Amazon OpenSearch Service Serverless only supports `nmslib` or `faiss` engines\"\n raise ValueError(msg)\n\n def _is_aoss_enabled(self, http_auth: Any) -> bool:\n \"\"\"Determine if Amazon OpenSearch Serverless (AOSS) is being used.\n\n Args:\n http_auth: The HTTP authentication object\n\n Returns:\n True if AOSS is enabled, False otherwise\n \"\"\"\n return http_auth is not None and hasattr(http_auth, \"service\") and http_auth.service == \"aoss\"\n\n def _bulk_ingest_embeddings(\n self,\n client: OpenSearch,\n index_name: str,\n embeddings: list[list[float]],\n texts: list[str],\n metadatas: list[dict] | None = None,\n ids: list[str] | None = None,\n vector_field: str = \"vector_field\",\n text_field: str = \"text\",\n mapping: dict | None = None,\n max_chunk_bytes: int | None = 1 * 1024 * 1024,\n *,\n is_aoss: bool = False,\n ) -> list[str]:\n \"\"\"Efficiently ingest multiple documents with embeddings into OpenSearch.\n\n This method uses bulk operations to insert documents with their vector\n embeddings and metadata into the specified OpenSearch index.\n\n Args:\n client: OpenSearch client instance\n index_name: Target index for document storage\n embeddings: List of vector embeddings for each document\n texts: List of document texts\n metadatas: Optional metadata dictionaries for each document\n ids: Optional document IDs (UUIDs generated if not provided)\n vector_field: Field name for storing vector embeddings\n text_field: Field name for storing document text\n mapping: Optional index mapping configuration\n max_chunk_bytes: Maximum size per bulk request chunk\n is_aoss: Whether using Amazon OpenSearch Serverless\n\n Returns:\n List of document IDs that were successfully ingested\n \"\"\"\n if not mapping:\n mapping = {}\n\n requests = []\n return_ids = []\n\n for i, text in enumerate(texts):\n metadata = metadatas[i] if metadatas else {}\n _id = ids[i] if ids else str(uuid.uuid4())\n request = {\n \"_op_type\": \"index\",\n \"_index\": index_name,\n vector_field: embeddings[i],\n text_field: text,\n **metadata,\n }\n if is_aoss:\n request[\"id\"] = _id\n else:\n request[\"_id\"] = _id\n requests.append(request)\n return_ids.append(_id)\n if metadatas:\n self.log(f\"Sample metadata: {metadatas[0] if metadatas else {}}\")\n helpers.bulk(client, requests, max_chunk_bytes=max_chunk_bytes)\n return return_ids\n\n # ---------- auth / client ----------\n def _build_auth_kwargs(self) -> dict[str, Any]:\n \"\"\"Build authentication configuration for OpenSearch client.\n\n Constructs the appropriate authentication parameters based on the\n selected auth mode (basic username/password or JWT token).\n\n Returns:\n Dictionary containing authentication configuration\n\n Raises:\n ValueError: If required authentication parameters are missing\n \"\"\"\n mode = (self.auth_mode or \"basic\").strip().lower()\n if mode == \"jwt\":\n token = (self.jwt_token or \"\").strip()\n if not token:\n msg = \"Auth Mode is 'jwt' but no jwt_token was provided.\"\n raise ValueError(msg)\n header_name = (self.jwt_header or \"Authorization\").strip()\n header_value = f\"Bearer {token}\" if self.bearer_prefix else token\n return {\"headers\": {header_name: header_value}}\n user = (self.username or \"\").strip()\n pwd = (self.password or \"\").strip()\n if not user or not pwd:\n msg = \"Auth Mode is 'basic' but username/password are missing.\"\n raise ValueError(msg)\n return {\"http_auth\": (user, pwd)}\n\n def build_client(self) -> OpenSearch:\n \"\"\"Create and configure an OpenSearch client instance.\n\n Returns:\n Configured OpenSearch client ready for operations\n \"\"\"\n auth_kwargs = self._build_auth_kwargs()\n return OpenSearch(\n hosts=[self.opensearch_url],\n use_ssl=self.use_ssl,\n verify_certs=self.verify_certs,\n ssl_assert_hostname=False,\n ssl_show_warn=False,\n **auth_kwargs,\n )\n\n @check_cached_vector_store\n def build_vector_store(self) -> OpenSearch:\n # Return raw OpenSearch client as our “vector store.”\n self.log(self.ingest_data)\n client = self.build_client()\n self._add_documents_to_vector_store(client=client)\n return client\n\n # ---------- ingest ----------\n def _add_documents_to_vector_store(self, client: OpenSearch) -> None:\n \"\"\"Process and ingest documents into the OpenSearch vector store.\n\n This method handles the complete document ingestion pipeline:\n - Prepares document data and metadata\n - Generates vector embeddings\n - Creates appropriate index mappings\n - Bulk inserts documents with vectors\n\n Args:\n client: OpenSearch client for performing operations\n \"\"\"\n # Convert DataFrame to Data if needed using parent's method\n self.ingest_data = self._prepare_ingest_data()\n\n docs = self.ingest_data or []\n if not docs:\n self.log(\"No documents to ingest.\")\n return\n\n # Extract texts and metadata from documents\n texts = []\n metadatas = []\n # Process docs_metadata table input into a dict\n additional_metadata = {}\n if hasattr(self, \"docs_metadata\") and self.docs_metadata:\n logger.info(f\"[LF] Docs metadata {self.docs_metadata}\")\n if isinstance(self.docs_metadata[-1], Data):\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n self.docs_metadata = self.docs_metadata[-1].data\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n additional_metadata.update(self.docs_metadata)\n else:\n for item in self.docs_metadata:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n additional_metadata[item[\"key\"]] = item[\"value\"]\n # Replace string \"None\" values with actual None\n for key, value in additional_metadata.items():\n if value == \"None\":\n additional_metadata[key] = None\n logger.info(f\"[LF] Additional metadata {additional_metadata}\")\n for doc_obj in docs:\n data_copy = json.loads(doc_obj.model_dump_json())\n text = data_copy.pop(doc_obj.text_key, doc_obj.default_value)\n texts.append(text)\n\n # Merge additional metadata from table input\n data_copy.update(additional_metadata)\n\n metadatas.append(data_copy)\n self.log(metadatas)\n if not self.embedding:\n msg = \"Embedding handle is required to embed documents.\"\n raise ValueError(msg)\n\n # Generate embeddings\n vectors = self.embedding.embed_documents(texts)\n\n if not vectors:\n self.log(\"No vectors generated from documents.\")\n return\n\n # Get vector dimension for mapping\n dim = len(vectors[0]) if vectors else 768 # default fallback\n\n # Check for AOSS\n auth_kwargs = self._build_auth_kwargs()\n is_aoss = self._is_aoss_enabled(auth_kwargs.get(\"http_auth\"))\n\n # Validate engine with AOSS\n engine = getattr(self, \"engine\", \"jvector\")\n self._validate_aoss_with_engines(is_aoss=is_aoss, engine=engine)\n\n # Create mapping with proper KNN settings\n space_type = getattr(self, \"space_type\", \"l2\")\n ef_construction = getattr(self, \"ef_construction\", 512)\n m = getattr(self, \"m\", 16)\n\n mapping = self._default_text_mapping(\n dim=dim,\n engine=engine,\n space_type=space_type,\n ef_construction=ef_construction,\n m=m,\n vector_field=self.vector_field,\n )\n\n self.log(f\"Indexing {len(texts)} documents into '{self.index_name}' with proper KNN mapping...\")\n\n # Use the LangChain-style bulk ingestion\n return_ids = self._bulk_ingest_embeddings(\n client=client,\n index_name=self.index_name,\n embeddings=vectors,\n texts=texts,\n metadatas=metadatas,\n vector_field=self.vector_field,\n text_field=\"text\",\n mapping=mapping,\n is_aoss=is_aoss,\n )\n self.log(metadatas)\n\n self.log(f\"Successfully indexed {len(return_ids)} documents.\")\n\n # ---------- helpers for filters ----------\n def _is_placeholder_term(self, term_obj: dict) -> bool:\n # term_obj like {\"filename\": \"__IMPOSSIBLE_VALUE__\"}\n return any(v == \"__IMPOSSIBLE_VALUE__\" for v in term_obj.values())\n\n def _coerce_filter_clauses(self, filter_obj: dict | None) -> list[dict]:\n \"\"\"Convert filter expressions into OpenSearch-compatible filter clauses.\n\n This method accepts two filter formats and converts them to standardized\n OpenSearch query clauses:\n\n Format A - Explicit filters:\n {\"filter\": [{\"term\": {\"field\": \"value\"}}, {\"terms\": {\"field\": [\"val1\", \"val2\"]}}],\n \"limit\": 10, \"score_threshold\": 1.5}\n\n Format B - Context-style mapping:\n {\"data_sources\": [\"file1.pdf\"], \"document_types\": [\"pdf\"], \"owners\": [\"user1\"]}\n\n Args:\n filter_obj: Filter configuration dictionary or None\n\n Returns:\n List of OpenSearch filter clauses (term/terms objects)\n Placeholder values with \"__IMPOSSIBLE_VALUE__\" are ignored\n \"\"\"\n if not filter_obj:\n return []\n\n # If it is a string, try to parse it once\n if isinstance(filter_obj, str):\n try:\n filter_obj = json.loads(filter_obj)\n except json.JSONDecodeError:\n # Not valid JSON - treat as no filters\n return []\n\n # Case A: already an explicit list/dict under \"filter\"\n if \"filter\" in filter_obj:\n raw = filter_obj[\"filter\"]\n if isinstance(raw, dict):\n raw = [raw]\n explicit_clauses: list[dict] = []\n for f in raw or []:\n if \"term\" in f and isinstance(f[\"term\"], dict) and not self._is_placeholder_term(f[\"term\"]):\n explicit_clauses.append(f)\n elif \"terms\" in f and isinstance(f[\"terms\"], dict):\n field, vals = next(iter(f[\"terms\"].items()))\n if isinstance(vals, list) and len(vals) > 0:\n explicit_clauses.append(f)\n return explicit_clauses\n\n # Case B: convert context-style maps into clauses\n field_mapping = {\n \"data_sources\": \"filename\",\n \"document_types\": \"mimetype\",\n \"owners\": \"owner\",\n }\n context_clauses: list[dict] = []\n for k, values in filter_obj.items():\n if not isinstance(values, list):\n continue\n field = field_mapping.get(k, k)\n if len(values) == 0:\n # Match-nothing placeholder (kept to mirror your tool semantics)\n context_clauses.append({\"term\": {field: \"__IMPOSSIBLE_VALUE__\"}})\n elif len(values) == 1:\n if values[0] != \"__IMPOSSIBLE_VALUE__\":\n context_clauses.append({\"term\": {field: values[0]}})\n else:\n context_clauses.append({\"terms\": {field: values}})\n return context_clauses\n\n # ---------- search (single hybrid path matching your tool) ----------\n def search(self, query: str | None = None) -> list[dict[str, Any]]:\n \"\"\"Perform hybrid search combining vector similarity and keyword matching.\n\n This method executes a sophisticated search that combines:\n - K-nearest neighbor (KNN) vector similarity search (70% weight)\n - Multi-field keyword search with fuzzy matching (30% weight)\n - Optional filtering and score thresholds\n - Aggregations for faceted search results\n\n Args:\n query: Search query string (used for both vector embedding and keyword search)\n\n Returns:\n List of search results with page_content, metadata, and relevance scores\n\n Raises:\n ValueError: If embedding component is not provided or filter JSON is invalid\n \"\"\"\n logger.info(self.ingest_data)\n client = self.build_client()\n q = (query or \"\").strip()\n\n # Parse optional filter expression (can be either A or B shape; see _coerce_filter_clauses)\n filter_obj = None\n if getattr(self, \"filter_expression\", \"\") and self.filter_expression.strip():\n try:\n filter_obj = json.loads(self.filter_expression)\n except json.JSONDecodeError as e:\n msg = f\"Invalid filter_expression JSON: {e}\"\n raise ValueError(msg) from e\n\n if not self.embedding:\n msg = \"Embedding is required to run hybrid search (KNN + keyword).\"\n raise ValueError(msg)\n\n # Embed the query\n vec = self.embedding.embed_query(q)\n\n # Build filter clauses (accept both shapes)\n filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n # Respect the tool's limit/threshold defaults\n limit = (filter_obj or {}).get(\"limit\", self.number_of_results)\n score_threshold = (filter_obj or {}).get(\"score_threshold\", 0)\n\n # Build the same hybrid body as your SearchService\n body = {\n \"query\": {\n \"bool\": {\n \"should\": [\n {\n \"knn\": {\n self.vector_field: {\n \"vector\": vec,\n \"k\": 10, # fixed to match the tool\n \"boost\": 0.7,\n }\n }\n },\n {\n \"multi_match\": {\n \"query\": q,\n \"fields\": [\"text^2\", \"filename^1.5\"],\n \"type\": \"best_fields\",\n \"fuzziness\": \"AUTO\",\n \"boost\": 0.3,\n }\n },\n ],\n \"minimum_should_match\": 1,\n }\n },\n \"aggs\": {\n \"data_sources\": {\"terms\": {\"field\": \"filename\", \"size\": 20}},\n \"document_types\": {\"terms\": {\"field\": \"mimetype\", \"size\": 10}},\n \"owners\": {\"terms\": {\"field\": \"owner\", \"size\": 10}},\n },\n \"_source\": [\n \"filename\",\n \"mimetype\",\n \"page\",\n \"text\",\n \"source_url\",\n \"owner\",\n \"allowed_users\",\n \"allowed_groups\",\n ],\n \"size\": limit,\n }\n if filter_clauses:\n body[\"query\"][\"bool\"][\"filter\"] = filter_clauses\n\n if isinstance(score_threshold, (int, float)) and score_threshold > 0:\n # top-level min_score (matches your tool)\n body[\"min_score\"] = score_threshold\n\n resp = client.search(index=self.index_name, body=body)\n hits = resp.get(\"hits\", {}).get(\"hits\", [])\n return [\n {\n \"page_content\": hit[\"_source\"].get(\"text\", \"\"),\n \"metadata\": {k: v for k, v in hit[\"_source\"].items() if k != \"text\"},\n \"score\": hit.get(\"_score\"),\n }\n for hit in hits\n ]\n\n def search_documents(self) -> list[Data]:\n \"\"\"Search documents and return results as Data objects.\n\n This is the main interface method that performs the search using the\n configured search_query and returns results in Langflow's Data format.\n\n Returns:\n List of Data objects containing search results with text and metadata\n\n Raises:\n Exception: If search operation fails\n \"\"\"\n try:\n raw = self.search(self.search_query or \"\")\n return [Data(text=hit[\"page_content\"], **hit[\"metadata\"]) for hit in raw]\n self.log(self.ingest_data)\n except Exception as e:\n self.log(f\"search_documents error: {e}\")\n raise\n\n # -------- dynamic UI handling (auth switch) --------\n async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n \"\"\"Dynamically update component configuration based on field changes.\n\n This method handles real-time UI updates, particularly for authentication\n mode changes that show/hide relevant input fields.\n\n Args:\n build_config: Current component configuration\n field_value: New value for the changed field\n field_name: Name of the field that changed\n\n Returns:\n Updated build configuration with appropriate field visibility\n \"\"\"\n try:\n if field_name == \"auth_mode\":\n mode = (field_value or \"basic\").strip().lower()\n is_basic = mode == \"basic\"\n is_jwt = mode == \"jwt\"\n\n build_config[\"username\"][\"show\"] = is_basic\n build_config[\"password\"][\"show\"] = is_basic\n\n build_config[\"jwt_token\"][\"show\"] = is_jwt\n build_config[\"jwt_header\"][\"show\"] = is_jwt\n build_config[\"bearer_prefix\"][\"show\"] = is_jwt\n\n build_config[\"username\"][\"required\"] = is_basic\n build_config[\"password\"][\"required\"] = is_basic\n\n build_config[\"jwt_token\"][\"required\"] = is_jwt\n build_config[\"jwt_header\"][\"required\"] = is_jwt\n build_config[\"bearer_prefix\"][\"required\"] = False\n\n if is_basic:\n build_config[\"jwt_token\"][\"value\"] = \"\"\n\n return build_config\n\n except (KeyError, ValueError) as e:\n self.log(f\"update_build_config error: {e}\")\n\n return build_config\n" + "value": "from __future__ import annotations\n\nimport asyncio\nimport copy\nimport json\nimport uuid\nfrom typing import Any\n\nfrom opensearchpy import OpenSearch, helpers\nfrom opensearchpy.exceptions import RequestError\n\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.io import BoolInput, DropdownInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput, TableInput\nfrom lfx.log import logger\nfrom lfx.schema.data import Data\n\n\ndef normalize_model_name(model_name: str) -> str:\n \"\"\"Normalize embedding model name for use as field suffix.\n\n Converts model names to valid OpenSearch field names by replacing\n special characters and ensuring alphanumeric format.\n\n Args:\n model_name: Original embedding model name (e.g., \"text-embedding-3-small\")\n\n Returns:\n Normalized field suffix (e.g., \"text_embedding_3_small\")\n \"\"\"\n normalized = model_name.lower()\n # Replace common separators with underscores\n normalized = normalized.replace(\"-\", \"_\").replace(\":\", \"_\").replace(\"/\", \"_\").replace(\".\", \"_\")\n # Remove any non-alphanumeric characters except underscores\n normalized = \"\".join(c if c.isalnum() or c == \"_\" else \"_\" for c in normalized)\n # Remove duplicate underscores\n while \"__\" in normalized:\n normalized = normalized.replace(\"__\", \"_\")\n return normalized.strip(\"_\")\n\n\ndef get_embedding_field_name(model_name: str) -> str:\n \"\"\"Get the dynamic embedding field name for a model.\n\n Args:\n model_name: Embedding model name\n\n Returns:\n Field name in format: chunk_embedding_{normalized_model_name}\n \"\"\"\n return f\"chunk_embedding_{normalize_model_name(model_name)}\"\n\n\n@vector_store_connection\nclass OpenSearchVectorStoreComponent(LCVectorStoreComponent):\n \"\"\"OpenSearch Vector Store Component with Multi-Model Hybrid Search Capabilities.\n\n This component provides vector storage and retrieval using OpenSearch, combining semantic\n similarity search (KNN) with keyword-based search for optimal results. It supports:\n - Multiple embedding models per index with dynamic field names\n - Automatic detection and querying of all available embedding models\n - Parallel embedding generation for multi-model search\n - Document ingestion with model tracking\n - Advanced filtering and aggregations\n - Flexible authentication options\n\n Features:\n - Multi-model vector storage with dynamic fields (chunk_embedding_{model_name})\n - Hybrid search combining multiple KNN queries (dis_max) + keyword matching\n - Auto-detection of available models in the index\n - Parallel query embedding generation for all detected models\n - Vector storage with configurable engines (jvector, nmslib, faiss, lucene)\n - Flexible authentication (Basic auth, JWT tokens)\n \"\"\"\n\n display_name: str = \"OpenSearch (Multi-Model)\"\n icon: str = \"OpenSearch\"\n description: str = (\n \"Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search.\"\n )\n\n # Keys we consider baseline\n default_keys: list[str] = [\n \"opensearch_url\",\n \"index_name\",\n *[i.name for i in LCVectorStoreComponent.inputs], # search_query, add_documents, etc.\n \"embedding\",\n \"embedding_model_name\",\n \"vector_field\",\n \"number_of_results\",\n \"auth_mode\",\n \"username\",\n \"password\",\n \"jwt_token\",\n \"jwt_header\",\n \"bearer_prefix\",\n \"use_ssl\",\n \"verify_certs\",\n \"filter_expression\",\n \"engine\",\n \"space_type\",\n \"ef_construction\",\n \"m\",\n \"num_candidates\",\n \"docs_metadata\",\n ]\n\n inputs = [\n TableInput(\n name=\"docs_metadata\",\n display_name=\"Document Metadata\",\n info=(\n \"Additional metadata key-value pairs to be added to all ingested documents. \"\n \"Useful for tagging documents with source information, categories, or other custom attributes.\"\n ),\n table_schema=[\n {\n \"name\": \"key\",\n \"display_name\": \"Key\",\n \"type\": \"str\",\n \"description\": \"Key name\",\n },\n {\n \"name\": \"value\",\n \"display_name\": \"Value\",\n \"type\": \"str\",\n \"description\": \"Value of the metadata\",\n },\n ],\n value=[],\n input_types=[\"Data\"]\n ),\n StrInput(\n name=\"opensearch_url\",\n display_name=\"OpenSearch URL\",\n value=\"http://localhost:9200\",\n info=(\n \"The connection URL for your OpenSearch cluster \"\n \"(e.g., http://localhost:9200 for local development or your cloud endpoint).\"\n ),\n ),\n StrInput(\n name=\"index_name\",\n display_name=\"Index Name\",\n value=\"langflow\",\n info=(\n \"The OpenSearch index name where documents will be stored and searched. \"\n \"Will be created automatically if it doesn't exist.\"\n ),\n ),\n DropdownInput(\n name=\"engine\",\n display_name=\"Vector Engine\",\n options=[\"jvector\", \"nmslib\", \"faiss\", \"lucene\"],\n value=\"jvector\",\n info=(\n \"Vector search engine for similarity calculations. 'jvector' is recommended for most use cases. \"\n \"Note: Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.\"\n ),\n advanced=True,\n ),\n DropdownInput(\n name=\"space_type\",\n display_name=\"Distance Metric\",\n options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n value=\"l2\",\n info=(\n \"Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, \"\n \"'cosinesimil' for cosine similarity, 'innerproduct' for dot product.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"ef_construction\",\n display_name=\"EF Construction\",\n value=512,\n info=(\n \"Size of the dynamic candidate list during index construction. \"\n \"Higher values improve recall but increase indexing time and memory usage.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"m\",\n display_name=\"M Parameter\",\n value=16,\n info=(\n \"Number of bidirectional connections for each vector in the HNSW graph. \"\n \"Higher values improve search quality but increase memory usage and indexing time.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"num_candidates\",\n display_name=\"Candidate Pool Size\",\n value=1000,\n info=(\n \"Number of approximate neighbors to consider for each KNN query. \"\n \"Some OpenSearch deployments do not support this parameter; set to 0 to disable.\"\n ),\n advanced=True,\n ),\n *LCVectorStoreComponent.inputs, # includes search_query, add_documents, etc.\n HandleInput(name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"]),\n StrInput(\n name=\"embedding_model_name\",\n display_name=\"Embedding Model Name\",\n value=\"\",\n info=(\n \"Name of the embedding model being used (e.g., 'text-embedding-3-small'). \"\n \"Used to create dynamic vector field names and track which model embedded each document. \"\n \"Auto-detected from embedding component if not specified.\"\n ),\n ),\n StrInput(\n name=\"vector_field\",\n display_name=\"Legacy Vector Field Name\",\n value=\"chunk_embedding\",\n advanced=True,\n info=(\n \"Legacy field name for backward compatibility. New documents use dynamic fields \"\n \"(chunk_embedding_{model_name}) based on the embedding_model_name.\"\n ),\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Default Result Limit\",\n value=10,\n advanced=True,\n info=(\n \"Default maximum number of search results to return when no limit is \"\n \"specified in the filter expression.\"\n ),\n ),\n MultilineInput(\n name=\"filter_expression\",\n display_name=\"Search Filters (JSON)\",\n value=\"\",\n info=(\n \"Optional JSON configuration for search filtering, result limits, and score thresholds.\\n\\n\"\n \"Format 1 - Explicit filters:\\n\"\n '{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, '\n '{\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\\n\\n'\n \"Format 2 - Context-style mapping:\\n\"\n '{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\\n\\n'\n \"Use __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.\"\n ),\n ),\n # ----- Auth controls (dynamic) -----\n DropdownInput(\n name=\"auth_mode\",\n display_name=\"Authentication Mode\",\n value=\"basic\",\n options=[\"basic\", \"jwt\"],\n info=(\n \"Authentication method: 'basic' for username/password authentication, \"\n \"or 'jwt' for JSON Web Token (Bearer) authentication.\"\n ),\n real_time_refresh=True,\n advanced=False,\n ),\n StrInput(\n name=\"username\",\n display_name=\"Username\",\n value=\"admin\",\n show=False,\n ),\n SecretStrInput(\n name=\"password\",\n display_name=\"OpenSearch Password\",\n value=\"admin\",\n show=False,\n ),\n SecretStrInput(\n name=\"jwt_token\",\n display_name=\"JWT Token\",\n value=\"JWT\",\n load_from_db=False,\n show=True,\n info=(\n \"Valid JSON Web Token for authentication. \"\n \"Will be sent in the Authorization header (with optional 'Bearer ' prefix).\"\n ),\n ),\n StrInput(\n name=\"jwt_header\",\n display_name=\"JWT Header Name\",\n value=\"Authorization\",\n show=False,\n advanced=True,\n ),\n BoolInput(\n name=\"bearer_prefix\",\n display_name=\"Prefix 'Bearer '\",\n value=True,\n show=False,\n advanced=True,\n ),\n # ----- TLS -----\n BoolInput(\n name=\"use_ssl\",\n display_name=\"Use SSL/TLS\",\n value=True,\n advanced=True,\n info=\"Enable SSL/TLS encryption for secure connections to OpenSearch.\",\n ),\n BoolInput(\n name=\"verify_certs\",\n display_name=\"Verify SSL Certificates\",\n value=False,\n advanced=True,\n info=(\n \"Verify SSL certificates when connecting. \"\n \"Disable for self-signed certificates in development environments.\"\n ),\n ),\n ]\n\n def _get_embedding_model_name(self) -> str:\n \"\"\"Get the embedding model name from component config or embedding object.\n\n Returns:\n Embedding model name\n\n Raises:\n ValueError: If embedding model name cannot be determined\n \"\"\"\n # First try explicit embedding_model_name input\n if hasattr(self, \"embedding_model_name\") and self.embedding_model_name:\n return self.embedding_model_name.strip()\n\n # Try to get from embedding component\n if hasattr(self, \"embedding\") and self.embedding:\n if hasattr(self.embedding, \"model\"):\n return str(self.embedding.model)\n if hasattr(self.embedding, \"model_name\"):\n return str(self.embedding.model_name)\n\n msg = (\n \"Could not determine embedding model name. \"\n \"Please set the 'embedding_model_name' field or ensure the embedding component \"\n \"has a 'model' or 'model_name' attribute.\"\n )\n raise ValueError(msg)\n\n # ---------- helper functions for index management ----------\n def _default_text_mapping(\n self,\n dim: int,\n engine: str = \"jvector\",\n space_type: str = \"l2\",\n ef_search: int = 512,\n ef_construction: int = 100,\n m: int = 16,\n vector_field: str = \"vector_field\",\n ) -> dict[str, Any]:\n \"\"\"Create the default OpenSearch index mapping for vector search.\n\n This method generates the index configuration with k-NN settings optimized\n for approximate nearest neighbor search using the specified vector engine.\n Includes the embedding_model keyword field for tracking which model was used.\n\n Args:\n dim: Dimensionality of the vector embeddings\n engine: Vector search engine (jvector, nmslib, faiss, lucene)\n space_type: Distance metric for similarity calculation\n ef_search: Size of dynamic list used during search\n ef_construction: Size of dynamic list used during index construction\n m: Number of bidirectional links for each vector\n vector_field: Name of the field storing vector embeddings\n\n Returns:\n Dictionary containing OpenSearch index mapping configuration\n \"\"\"\n return {\n \"settings\": {\"index\": {\"knn\": True, \"knn.algo_param.ef_search\": ef_search}},\n \"mappings\": {\n \"properties\": {\n vector_field: {\n \"type\": \"knn_vector\",\n \"dimension\": dim,\n \"method\": {\n \"name\": \"disk_ann\",\n \"space_type\": space_type,\n \"engine\": engine,\n \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n },\n },\n \"embedding_model\": {\"type\": \"keyword\"}, # Track which model was used\n \"embedding_dimensions\": {\"type\": \"integer\"},\n }\n },\n }\n\n def _ensure_embedding_field_mapping(\n self,\n client: OpenSearch,\n index_name: str,\n field_name: str,\n dim: int,\n engine: str,\n space_type: str,\n ef_construction: int,\n m: int,\n ) -> None:\n \"\"\"Lazily add a dynamic embedding field to the index if it doesn't exist.\n\n This allows adding new embedding models without recreating the entire index.\n Also ensures the embedding_model tracking field exists.\n\n Args:\n client: OpenSearch client instance\n index_name: Target index name\n field_name: Dynamic field name for this embedding model\n dim: Vector dimensionality\n engine: Vector search engine\n space_type: Distance metric\n ef_construction: Construction parameter\n m: HNSW parameter\n \"\"\"\n try:\n mapping = {\n \"properties\": {\n field_name: {\n \"type\": \"knn_vector\",\n \"dimension\": dim,\n \"method\": {\n \"name\": \"disk_ann\",\n \"space_type\": space_type,\n \"engine\": engine,\n \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n },\n },\n # Also ensure the embedding_model tracking field exists as keyword\n \"embedding_model\": {\n \"type\": \"keyword\"\n },\n \"embedding_dimensions\": {\n \"type\": \"integer\"\n }\n }\n }\n client.indices.put_mapping(index=index_name, body=mapping)\n logger.info(f\"Added/updated embedding field mapping: {field_name}\")\n except Exception as e:\n logger.warning(f\"Could not add embedding field mapping for {field_name}: {e}\")\n\n def _validate_aoss_with_engines(self, *, is_aoss: bool, engine: str) -> None:\n \"\"\"Validate engine compatibility with Amazon OpenSearch Serverless (AOSS).\n\n Amazon OpenSearch Serverless has restrictions on which vector engines\n can be used. This method ensures the selected engine is compatible.\n\n Args:\n is_aoss: Whether the connection is to Amazon OpenSearch Serverless\n engine: The selected vector search engine\n\n Raises:\n ValueError: If AOSS is used with an incompatible engine\n \"\"\"\n if is_aoss and engine not in {\"nmslib\", \"faiss\"}:\n msg = \"Amazon OpenSearch Service Serverless only supports `nmslib` or `faiss` engines\"\n raise ValueError(msg)\n\n def _is_aoss_enabled(self, http_auth: Any) -> bool:\n \"\"\"Determine if Amazon OpenSearch Serverless (AOSS) is being used.\n\n Args:\n http_auth: The HTTP authentication object\n\n Returns:\n True if AOSS is enabled, False otherwise\n \"\"\"\n return http_auth is not None and hasattr(http_auth, \"service\") and http_auth.service == \"aoss\"\n\n def _bulk_ingest_embeddings(\n self,\n client: OpenSearch,\n index_name: str,\n embeddings: list[list[float]],\n texts: list[str],\n metadatas: list[dict] | None = None,\n ids: list[str] | None = None,\n vector_field: str = \"vector_field\",\n text_field: str = \"text\",\n embedding_model: str = \"unknown\",\n mapping: dict | None = None,\n max_chunk_bytes: int | None = 1 * 1024 * 1024,\n *,\n is_aoss: bool = False,\n ) -> list[str]:\n \"\"\"Efficiently ingest multiple documents with embeddings into OpenSearch.\n\n This method uses bulk operations to insert documents with their vector\n embeddings and metadata into the specified OpenSearch index. Each document\n is tagged with the embedding_model name for tracking.\n\n Args:\n client: OpenSearch client instance\n index_name: Target index for document storage\n embeddings: List of vector embeddings for each document\n texts: List of document texts\n metadatas: Optional metadata dictionaries for each document\n ids: Optional document IDs (UUIDs generated if not provided)\n vector_field: Field name for storing vector embeddings\n text_field: Field name for storing document text\n embedding_model: Name of the embedding model used\n mapping: Optional index mapping configuration\n max_chunk_bytes: Maximum size per bulk request chunk\n is_aoss: Whether using Amazon OpenSearch Serverless\n\n Returns:\n List of document IDs that were successfully ingested\n \"\"\"\n if not mapping:\n mapping = {}\n\n requests = []\n return_ids = []\n vector_dimensions = len(embeddings[0]) if embeddings else None\n\n for i, text in enumerate(texts):\n metadata = metadatas[i] if metadatas else {}\n if vector_dimensions is not None and \"embedding_dimensions\" not in metadata:\n metadata = {**metadata, \"embedding_dimensions\": vector_dimensions}\n _id = ids[i] if ids else str(uuid.uuid4())\n request = {\n \"_op_type\": \"index\",\n \"_index\": index_name,\n vector_field: embeddings[i],\n text_field: text,\n \"embedding_model\": embedding_model, # Track which model was used\n **metadata,\n }\n if is_aoss:\n request[\"id\"] = _id\n else:\n request[\"_id\"] = _id\n requests.append(request)\n return_ids.append(_id)\n if metadatas:\n self.log(f\"Sample metadata: {metadatas[0] if metadatas else {}}\")\n helpers.bulk(client, requests, max_chunk_bytes=max_chunk_bytes)\n return return_ids\n\n # ---------- auth / client ----------\n def _build_auth_kwargs(self) -> dict[str, Any]:\n \"\"\"Build authentication configuration for OpenSearch client.\n\n Constructs the appropriate authentication parameters based on the\n selected auth mode (basic username/password or JWT token).\n\n Returns:\n Dictionary containing authentication configuration\n\n Raises:\n ValueError: If required authentication parameters are missing\n \"\"\"\n mode = (self.auth_mode or \"basic\").strip().lower()\n if mode == \"jwt\":\n token = (self.jwt_token or \"\").strip()\n if not token:\n msg = \"Auth Mode is 'jwt' but no jwt_token was provided.\"\n raise ValueError(msg)\n header_name = (self.jwt_header or \"Authorization\").strip()\n header_value = f\"Bearer {token}\" if self.bearer_prefix else token\n return {\"headers\": {header_name: header_value}}\n user = (self.username or \"\").strip()\n pwd = (self.password or \"\").strip()\n if not user or not pwd:\n msg = \"Auth Mode is 'basic' but username/password are missing.\"\n raise ValueError(msg)\n return {\"http_auth\": (user, pwd)}\n\n def build_client(self) -> OpenSearch:\n \"\"\"Create and configure an OpenSearch client instance.\n\n Returns:\n Configured OpenSearch client ready for operations\n \"\"\"\n auth_kwargs = self._build_auth_kwargs()\n return OpenSearch(\n hosts=[self.opensearch_url],\n use_ssl=self.use_ssl,\n verify_certs=self.verify_certs,\n ssl_assert_hostname=False,\n ssl_show_warn=False,\n **auth_kwargs,\n )\n\n @check_cached_vector_store\n def build_vector_store(self) -> OpenSearch:\n # Return raw OpenSearch client as our \"vector store.\"\n self.log(self.ingest_data)\n client = self.build_client()\n self._add_documents_to_vector_store(client=client)\n return client\n\n # ---------- ingest ----------\n def _add_documents_to_vector_store(self, client: OpenSearch) -> None:\n \"\"\"Process and ingest documents into the OpenSearch vector store.\n\n This method handles the complete document ingestion pipeline:\n - Prepares document data and metadata\n - Generates vector embeddings\n - Creates appropriate index mappings with dynamic field names\n - Bulk inserts documents with vectors and model tracking\n\n Args:\n client: OpenSearch client for performing operations\n \"\"\"\n # Convert DataFrame to Data if needed using parent's method\n self.ingest_data = self._prepare_ingest_data()\n\n docs = self.ingest_data or []\n if not docs:\n self.log(\"No documents to ingest.\")\n return\n\n # Get embedding model name\n embedding_model = self._get_embedding_model_name()\n dynamic_field_name = get_embedding_field_name(embedding_model)\n\n self.log(f\"Using embedding model: {embedding_model}\")\n self.log(f\"Dynamic vector field: {dynamic_field_name}\")\n\n # Extract texts and metadata from documents\n texts = []\n metadatas = []\n # Process docs_metadata table input into a dict\n additional_metadata = {}\n if hasattr(self, \"docs_metadata\") and self.docs_metadata:\n logger.info(f\"[LF] Docs metadata {self.docs_metadata}\")\n if isinstance(self.docs_metadata[-1], Data):\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n self.docs_metadata = self.docs_metadata[-1].data\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n additional_metadata.update(self.docs_metadata)\n else:\n for item in self.docs_metadata:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n additional_metadata[item[\"key\"]] = item[\"value\"]\n # Replace string \"None\" values with actual None\n for key, value in additional_metadata.items():\n if value == \"None\":\n additional_metadata[key] = None\n logger.info(f\"[LF] Additional metadata {additional_metadata}\")\n for doc_obj in docs:\n data_copy = json.loads(doc_obj.model_dump_json())\n text = data_copy.pop(doc_obj.text_key, doc_obj.default_value)\n texts.append(text)\n\n # Merge additional metadata from table input\n data_copy.update(additional_metadata)\n\n metadatas.append(data_copy)\n self.log(metadatas)\n if not self.embedding:\n msg = \"Embedding handle is required to embed documents.\"\n raise ValueError(msg)\n\n # Generate embeddings\n vectors = self.embedding.embed_documents(texts)\n\n if not vectors:\n self.log(\"No vectors generated from documents.\")\n return\n\n # Get vector dimension for mapping\n dim = len(vectors[0]) if vectors else 768 # default fallback\n\n # Check for AOSS\n auth_kwargs = self._build_auth_kwargs()\n is_aoss = self._is_aoss_enabled(auth_kwargs.get(\"http_auth\"))\n\n # Validate engine with AOSS\n engine = getattr(self, \"engine\", \"jvector\")\n self._validate_aoss_with_engines(is_aoss=is_aoss, engine=engine)\n\n # Create mapping with proper KNN settings\n space_type = getattr(self, \"space_type\", \"l2\")\n ef_construction = getattr(self, \"ef_construction\", 512)\n m = getattr(self, \"m\", 16)\n\n mapping = self._default_text_mapping(\n dim=dim,\n engine=engine,\n space_type=space_type,\n ef_construction=ef_construction,\n m=m,\n vector_field=dynamic_field_name, # Use dynamic field name\n )\n\n # Ensure index exists with baseline mapping\n try:\n if not client.indices.exists(index=self.index_name):\n self.log(f\"Creating index '{self.index_name}' with base mapping\")\n client.indices.create(index=self.index_name, body=mapping)\n except RequestError as creation_error:\n if creation_error.error != \"resource_already_exists_exception\":\n logger.warning(\n f\"Failed to create index '{self.index_name}': {creation_error}\"\n )\n\n # Ensure the dynamic field exists in the index\n self._ensure_embedding_field_mapping(\n client=client,\n index_name=self.index_name,\n field_name=dynamic_field_name,\n dim=dim,\n engine=engine,\n space_type=space_type,\n ef_construction=ef_construction,\n m=m,\n )\n\n self.log(f\"Indexing {len(texts)} documents into '{self.index_name}' with model '{embedding_model}'...\")\n\n # Use the bulk ingestion with model tracking\n return_ids = self._bulk_ingest_embeddings(\n client=client,\n index_name=self.index_name,\n embeddings=vectors,\n texts=texts,\n metadatas=metadatas,\n vector_field=dynamic_field_name, # Use dynamic field name\n text_field=\"text\",\n embedding_model=embedding_model, # Track the model\n mapping=mapping,\n is_aoss=is_aoss,\n )\n self.log(metadatas)\n\n self.log(f\"Successfully indexed {len(return_ids)} documents with model {embedding_model}.\")\n\n # ---------- helpers for filters ----------\n def _is_placeholder_term(self, term_obj: dict) -> bool:\n # term_obj like {\"filename\": \"__IMPOSSIBLE_VALUE__\"}\n return any(v == \"__IMPOSSIBLE_VALUE__\" for v in term_obj.values())\n\n def _coerce_filter_clauses(self, filter_obj: dict | None) -> list[dict]:\n \"\"\"Convert filter expressions into OpenSearch-compatible filter clauses.\n\n This method accepts two filter formats and converts them to standardized\n OpenSearch query clauses:\n\n Format A - Explicit filters:\n {\"filter\": [{\"term\": {\"field\": \"value\"}}, {\"terms\": {\"field\": [\"val1\", \"val2\"]}}],\n \"limit\": 10, \"score_threshold\": 1.5}\n\n Format B - Context-style mapping:\n {\"data_sources\": [\"file1.pdf\"], \"document_types\": [\"pdf\"], \"owners\": [\"user1\"]}\n\n Args:\n filter_obj: Filter configuration dictionary or None\n\n Returns:\n List of OpenSearch filter clauses (term/terms objects)\n Placeholder values with \"__IMPOSSIBLE_VALUE__\" are ignored\n \"\"\"\n if not filter_obj:\n return []\n\n # If it is a string, try to parse it once\n if isinstance(filter_obj, str):\n try:\n filter_obj = json.loads(filter_obj)\n except json.JSONDecodeError:\n # Not valid JSON - treat as no filters\n return []\n\n # Case A: already an explicit list/dict under \"filter\"\n if \"filter\" in filter_obj:\n raw = filter_obj[\"filter\"]\n if isinstance(raw, dict):\n raw = [raw]\n explicit_clauses: list[dict] = []\n for f in raw or []:\n if \"term\" in f and isinstance(f[\"term\"], dict) and not self._is_placeholder_term(f[\"term\"]):\n explicit_clauses.append(f)\n elif \"terms\" in f and isinstance(f[\"terms\"], dict):\n field, vals = next(iter(f[\"terms\"].items()))\n if isinstance(vals, list) and len(vals) > 0:\n explicit_clauses.append(f)\n return explicit_clauses\n\n # Case B: convert context-style maps into clauses\n field_mapping = {\n \"data_sources\": \"filename\",\n \"document_types\": \"mimetype\",\n \"owners\": \"owner\",\n }\n context_clauses: list[dict] = []\n for k, values in filter_obj.items():\n if not isinstance(values, list):\n continue\n field = field_mapping.get(k, k)\n if len(values) == 0:\n # Match-nothing placeholder (kept to mirror your tool semantics)\n context_clauses.append({\"term\": {field: \"__IMPOSSIBLE_VALUE__\"}})\n elif len(values) == 1:\n if values[0] != \"__IMPOSSIBLE_VALUE__\":\n context_clauses.append({\"term\": {field: values[0]}})\n else:\n context_clauses.append({\"terms\": {field: values}})\n return context_clauses\n\n def _detect_available_models(self, client: OpenSearch, filter_clauses: list[dict] = None) -> list[str]:\n \"\"\"Detect which embedding models have documents in the index.\n\n Uses aggregation to find all unique embedding_model values, optionally\n filtered to only documents matching the user's filter criteria.\n\n Args:\n client: OpenSearch client instance\n filter_clauses: Optional filter clauses to scope model detection\n\n Returns:\n List of embedding model names found in the index\n \"\"\"\n try:\n agg_query = {\n \"size\": 0,\n \"aggs\": {\n \"embedding_models\": {\n \"terms\": {\n \"field\": \"embedding_model\",\n \"size\": 10\n }\n }\n }\n }\n\n # Apply filters to model detection if any exist\n if filter_clauses:\n agg_query[\"query\"] = {\n \"bool\": {\n \"filter\": filter_clauses\n }\n }\n\n result = client.search(index=self.index_name, body=agg_query)\n buckets = result.get(\"aggregations\", {}).get(\"embedding_models\", {}).get(\"buckets\", [])\n models = [b[\"key\"] for b in buckets if b[\"key\"]]\n\n logger.info(\n f\"Detected embedding models in corpus: {models}\"\n + (f\" (with {len(filter_clauses)} filters)\" if filter_clauses else \"\")\n )\n return models\n except Exception as e:\n logger.warning(f\"Failed to detect embedding models: {e}\")\n # Fallback to current model\n return [self._get_embedding_model_name()]\n\n def _get_index_properties(self, client: OpenSearch) -> dict[str, Any] | None:\n \"\"\"Retrieve flattened mapping properties for the current index.\"\"\"\n try:\n mapping = client.indices.get_mapping(index=self.index_name)\n except Exception as e:\n logger.warning(\n f\"Failed to fetch mapping for index '{self.index_name}': {e}. Proceeding without mapping metadata.\"\n )\n return None\n\n properties: dict[str, Any] = {}\n for index_data in mapping.values():\n props = index_data.get(\"mappings\", {}).get(\"properties\", {})\n if isinstance(props, dict):\n properties.update(props)\n return properties\n\n def _is_knn_vector_field(self, properties: dict[str, Any] | None, field_name: str) -> bool:\n \"\"\"Check whether the field is mapped as a knn_vector.\"\"\"\n if not field_name:\n return False\n if properties is None:\n logger.warning(\n f\"Mapping metadata unavailable; assuming field '{field_name}' is usable.\"\n )\n return True\n field_def = properties.get(field_name)\n if not isinstance(field_def, dict):\n return False\n if field_def.get(\"type\") == \"knn_vector\":\n return True\n\n nested_props = field_def.get(\"properties\")\n if isinstance(nested_props, dict) and nested_props.get(\"type\") == \"knn_vector\":\n return True\n\n return False\n\n # ---------- search (multi-model hybrid) ----------\n def search(self, query: str | None = None) -> list[dict[str, Any]]:\n \"\"\"Perform multi-model hybrid search combining multiple vector similarities and keyword matching.\n\n This method executes a sophisticated search that:\n 1. Auto-detects all embedding models present in the index\n 2. Generates query embeddings for ALL detected models in parallel\n 3. Combines multiple KNN queries using dis_max (picks best match)\n 4. Adds keyword search with fuzzy matching (30% weight)\n 5. Applies optional filtering and score thresholds\n 6. Returns aggregations for faceted search\n\n Search weights:\n - Semantic search (dis_max across all models): 70%\n - Keyword search: 30%\n\n Args:\n query: Search query string (used for both vector embedding and keyword search)\n\n Returns:\n List of search results with page_content, metadata, and relevance scores\n\n Raises:\n ValueError: If embedding component is not provided or filter JSON is invalid\n \"\"\"\n logger.info(self.ingest_data)\n client = self.build_client()\n q = (query or \"\").strip()\n\n # Parse optional filter expression\n filter_obj = None\n if getattr(self, \"filter_expression\", \"\") and self.filter_expression.strip():\n try:\n filter_obj = json.loads(self.filter_expression)\n except json.JSONDecodeError as e:\n msg = f\"Invalid filter_expression JSON: {e}\"\n raise ValueError(msg) from e\n\n if not self.embedding:\n msg = \"Embedding is required to run hybrid search (KNN + keyword).\"\n raise ValueError(msg)\n\n # Build filter clauses first so we can use them in model detection\n filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n # Detect available embedding models in the index (scoped by filters)\n available_models = self._detect_available_models(client, filter_clauses)\n\n if not available_models:\n logger.warning(\"No embedding models found in index, using current model\")\n available_models = [self._get_embedding_model_name()]\n\n # Generate embeddings for ALL detected models in parallel\n query_embeddings = {}\n\n # Note: Langflow is synchronous, so we can't use true async here\n # But we log the intent for parallel processing\n logger.info(f\"Generating embeddings for {len(available_models)} models\")\n\n for model_name in available_models:\n try:\n # In a real async environment, these would run in parallel\n # For now, they run sequentially\n vec = self.embedding.embed_query(q)\n query_embeddings[model_name] = vec\n logger.info(f\"Generated embedding for model: {model_name}\")\n except Exception as e:\n logger.error(f\"Failed to generate embedding for {model_name}: {e}\")\n\n if not query_embeddings:\n msg = \"Failed to generate embeddings for any model\"\n raise ValueError(msg)\n\n index_properties = self._get_index_properties(client)\n legacy_vector_field = getattr(self, \"vector_field\", \"chunk_embedding\")\n\n # Build KNN queries for each model\n embedding_fields: list[str] = []\n knn_queries_with_candidates = []\n knn_queries_without_candidates = []\n\n raw_num_candidates = getattr(self, \"num_candidates\", 1000)\n try:\n num_candidates = int(raw_num_candidates) if raw_num_candidates is not None else 0\n except (TypeError, ValueError):\n num_candidates = 0\n use_num_candidates = num_candidates > 0\n\n for model_name, embedding_vector in query_embeddings.items():\n field_name = get_embedding_field_name(model_name)\n selected_field = field_name\n\n if not self._is_knn_vector_field(index_properties, selected_field):\n if legacy_vector_field and self._is_knn_vector_field(index_properties, legacy_vector_field):\n logger.warning(\n f\"Model {model_name} missing dynamic knn_vector field '{field_name}'. \"\n f\"Falling back to legacy field '{legacy_vector_field}'.\"\n )\n selected_field = legacy_vector_field\n else:\n logger.warning(\n f\"Skipping model {model_name}: field '{field_name}' is not mapped as knn_vector.\"\n )\n continue\n\n embedding_fields.append(selected_field)\n\n base_query = {\n \"knn\": {\n selected_field: {\n \"vector\": embedding_vector,\n \"k\": 50,\n }\n }\n }\n\n if use_num_candidates:\n query_with_candidates = copy.deepcopy(base_query)\n query_with_candidates[\"knn\"][selected_field][\"num_candidates\"] = num_candidates\n else:\n query_with_candidates = base_query\n\n knn_queries_with_candidates.append(query_with_candidates)\n knn_queries_without_candidates.append(base_query)\n\n if not knn_queries_with_candidates:\n msg = (\n \"No valid knn_vector fields were found for detected embedding models. \"\n \"Ensure documents are re-ingested with multi-model support or update index mappings.\"\n )\n logger.error(msg)\n raise ValueError(msg)\n\n # Build exists filter - document must have at least one embedding field\n exists_any_embedding = {\n \"bool\": {\n \"should\": [{\"exists\": {\"field\": f}} for f in set(embedding_fields)],\n \"minimum_should_match\": 1\n }\n }\n\n # Combine user filters with exists filter\n all_filters = [*filter_clauses, exists_any_embedding]\n\n # Get limit and score threshold\n limit = (filter_obj or {}).get(\"limit\", self.number_of_results)\n score_threshold = (filter_obj or {}).get(\"score_threshold\", 0)\n\n # Build multi-model hybrid query\n body = {\n \"query\": {\n \"bool\": {\n \"should\": [\n {\n \"dis_max\": {\n \"tie_breaker\": 0.0, # Take only the best match, no blending\n \"boost\": 0.7, # 70% weight for semantic search\n \"queries\": knn_queries_with_candidates\n }\n },\n {\n \"multi_match\": {\n \"query\": q,\n \"fields\": [\"text^2\", \"filename^1.5\"],\n \"type\": \"best_fields\",\n \"fuzziness\": \"AUTO\",\n \"boost\": 0.3, # 30% weight for keyword search\n }\n },\n ],\n \"minimum_should_match\": 1,\n \"filter\": all_filters,\n }\n },\n \"aggs\": {\n \"data_sources\": {\"terms\": {\"field\": \"filename\", \"size\": 20}},\n \"document_types\": {\"terms\": {\"field\": \"mimetype\", \"size\": 10}},\n \"owners\": {\"terms\": {\"field\": \"owner\", \"size\": 10}},\n \"embedding_models\": {\"terms\": {\"field\": \"embedding_model.keyword\", \"size\": 10}},\n },\n \"_source\": [\n \"filename\",\n \"mimetype\",\n \"page\",\n \"text\",\n \"source_url\",\n \"owner\",\n \"embedding_model\",\n \"allowed_users\",\n \"allowed_groups\",\n ],\n \"size\": limit,\n }\n\n if isinstance(score_threshold, (int, float)) and score_threshold > 0:\n body[\"min_score\"] = score_threshold\n\n logger.info(\n f\"Executing multi-model hybrid search with {len(knn_queries_with_candidates)} embedding models\"\n )\n\n try:\n resp = client.search(index=self.index_name, body=body)\n except RequestError as e:\n error_message = str(e)\n lowered = error_message.lower()\n if use_num_candidates and \"num_candidates\" in lowered:\n logger.warning(\n \"Retrying search without num_candidates parameter due to cluster capabilities\",\n error=error_message,\n )\n fallback_body = copy.deepcopy(body)\n try:\n fallback_body[\"query\"][\"bool\"][\"should\"][0][\"dis_max\"][\"queries\"] = knn_queries_without_candidates\n except (KeyError, IndexError, TypeError) as inner_err:\n raise e from inner_err\n resp = client.search(index=self.index_name, body=fallback_body)\n elif \"knn_vector\" in lowered or (\"field\" in lowered and \"knn\" in lowered):\n fallback_vector = next(iter(query_embeddings.values()), None)\n if fallback_vector is None:\n raise\n fallback_field = legacy_vector_field or \"chunk_embedding\"\n logger.warning(\n \"KNN search failed for dynamic fields; falling back to legacy field '%s'.\",\n fallback_field,\n )\n fallback_body = copy.deepcopy(body)\n fallback_body[\"query\"][\"bool\"][\"filter\"] = filter_clauses\n knn_fallback = {\n \"knn\": {\n fallback_field: {\n \"vector\": fallback_vector,\n \"k\": 50,\n }\n }\n }\n if use_num_candidates:\n knn_fallback[\"knn\"][fallback_field][\"num_candidates\"] = num_candidates\n fallback_body[\"query\"][\"bool\"][\"should\"][0][\"dis_max\"][\"queries\"] = [knn_fallback]\n resp = client.search(index=self.index_name, body=fallback_body)\n else:\n raise\n hits = resp.get(\"hits\", {}).get(\"hits\", [])\n\n logger.info(f\"Found {len(hits)} results\")\n\n return [\n {\n \"page_content\": hit[\"_source\"].get(\"text\", \"\"),\n \"metadata\": {k: v for k, v in hit[\"_source\"].items() if k != \"text\"},\n \"score\": hit.get(\"_score\"),\n }\n for hit in hits\n ]\n\n def search_documents(self) -> list[Data]:\n \"\"\"Search documents and return results as Data objects.\n\n This is the main interface method that performs the multi-model search using the\n configured search_query and returns results in Langflow's Data format.\n\n Returns:\n List of Data objects containing search results with text and metadata\n\n Raises:\n Exception: If search operation fails\n \"\"\"\n try:\n raw = self.search(self.search_query or \"\")\n return [Data(text=hit[\"page_content\"], **hit[\"metadata\"]) for hit in raw]\n self.log(self.ingest_data)\n except Exception as e:\n self.log(f\"search_documents error: {e}\")\n raise\n\n # -------- dynamic UI handling (auth switch) --------\n async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n \"\"\"Dynamically update component configuration based on field changes.\n\n This method handles real-time UI updates, particularly for authentication\n mode changes that show/hide relevant input fields.\n\n Args:\n build_config: Current component configuration\n field_value: New value for the changed field\n field_name: Name of the field that changed\n\n Returns:\n Updated build configuration with appropriate field visibility\n \"\"\"\n try:\n if field_name == \"auth_mode\":\n mode = (field_value or \"basic\").strip().lower()\n is_basic = mode == \"basic\"\n is_jwt = mode == \"jwt\"\n\n build_config[\"username\"][\"show\"] = is_basic\n build_config[\"password\"][\"show\"] = is_basic\n\n build_config[\"jwt_token\"][\"show\"] = is_jwt\n build_config[\"jwt_header\"][\"show\"] = is_jwt\n build_config[\"bearer_prefix\"][\"show\"] = is_jwt\n\n build_config[\"username\"][\"required\"] = is_basic\n build_config[\"password\"][\"required\"] = is_basic\n\n build_config[\"jwt_token\"][\"required\"] = is_jwt\n build_config[\"jwt_header\"][\"required\"] = is_jwt\n build_config[\"bearer_prefix\"][\"required\"] = False\n\n if is_basic:\n build_config[\"jwt_token\"][\"value\"] = \"\"\n\n return build_config\n\n except (KeyError, ValueError) as e:\n self.log(f\"update_build_config error: {e}\")\n\n return build_config\n" }, "docs_metadata": { "_input_type": "TableInput", @@ -850,6 +851,25 @@ "type": "other", "value": "" }, + "embedding_model_name": { + "_input_type": "StrInput", + "advanced": false, + "display_name": "Embedding Model Name", + "dynamic": false, + "info": "Name of the embedding model being used (e.g., 'text-embedding-3-small'). Used to create dynamic vector field names and track which model embedded each document. Auto-detected from embedding component if not specified.", + "list": false, + "list_add_label": "Add More", + "load_from_db": false, + "name": "embedding_model_name", + "placeholder": "", + "required": false, + "show": true, + "title_case": false, + "tool_mode": false, + "trace_as_metadata": true, + "type": "str", + "value": "" + }, "engine": { "_input_type": "DropdownInput", "advanced": true, @@ -954,8 +974,8 @@ "load_from_db": false, "name": "jwt_header", "placeholder": "", - "required": false, - "show": false, + "required": true, + "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, @@ -973,11 +993,11 @@ "name": "jwt_token", "password": true, "placeholder": "", - "required": false, + "required": true, "show": true, "title_case": false, "type": "str", - "value": "" + "value": "JWT" }, "m": { "_input_type": "IntInput", @@ -1161,9 +1181,9 @@ "vector_field": { "_input_type": "StrInput", "advanced": true, - "display_name": "Vector Field Name", + "display_name": "Legacy Vector Field Name", "dynamic": false, - "info": "Name of the field in OpenSearch documents that stores the vector embeddings for similarity search.", + "info": "Legacy field name for backward compatibility. New documents use dynamic fields (chunk_embedding_{model_name}) based on the embedding_model_name.", "list": false, "list_add_label": "Add More", "load_from_db": false, @@ -1205,14 +1225,14 @@ "dragging": false, "id": "OpenSearchHybrid-Ve6bS", "measured": { - "height": 822, + "height": 909, "width": 320 }, "position": { "x": 2218.9287723423276, "y": 1332.2598463956504 }, - "selected": false, + "selected": true, "type": "genericNode" }, { @@ -1245,7 +1265,7 @@ ], "frozen": false, "icon": "binary", - "last_updated": "2025-10-04T02:17:01.272Z", + "last_updated": "2025-10-10T13:34:19.767Z", "legacy": false, "lf_version": "1.6.3.dev0", "metadata": { @@ -1519,7 +1539,7 @@ "dragging": false, "id": "EmbeddingModel-eZ6bT", "measured": { - "height": 369, + "height": 370, "width": 320 }, "position": { @@ -1550,7 +1570,7 @@ ], "frozen": false, "icon": "braces", - "last_updated": "2025-10-04T02:17:01.273Z", + "last_updated": "2025-10-10T13:34:19.770Z", "legacy": false, "lf_version": "1.6.3.dev0", "metadata": {}, @@ -1611,7 +1631,7 @@ "show": true, "title_case": false, "type": "code", - "value": "from typing import Any\r\n\r\nfrom langflow.custom import Component\r\nfrom langflow.io import (\r\n BoolInput,\r\n FloatInput,\r\n HandleInput,\r\n IntInput,\r\n MultilineInput,\r\n Output,\r\n StrInput,\r\n TableInput,\r\n)\r\nfrom langflow.schema.data import Data\r\nfrom langflow.schema.message import Message\r\n\r\n\r\nclass CrateData(Component):\r\n \"\"\"Dynamic Form Component\r\n\r\n This component creates dynamic inputs that can receive data from other components\r\n or be filled manually. It demonstrates advanced dynamic input functionality with\r\n component connectivity.\r\n\r\n ## Features\r\n - **Dynamic Input Generation**: Create inputs based on table configuration\r\n - **Component Connectivity**: Inputs can receive data from other components\r\n - **Multiple Input Types**: Support for text, number, boolean, and handle inputs\r\n - **Flexible Data Sources**: Manual input OR component connections\r\n - **Real-time Updates**: Form fields update immediately when table changes\r\n - **Multiple Output Formats**: Data and formatted Message outputs\r\n - **JSON Output**: Collects all dynamic inputs into a structured JSON response\r\n\r\n ## Use Cases\r\n - Dynamic API parameter collection from multiple sources\r\n - Variable data aggregation from different components\r\n - Flexible pipeline configuration\r\n - Multi-source data processing\r\n\r\n ## Field Types Available\r\n - **text**: Single-line text input (can connect to Text/String outputs)\r\n - **multiline**: Multi-line text input (can connect to Text outputs)\r\n - **number**: Integer input (can connect to Number outputs)\r\n - **float**: Decimal number input (can connect to Number outputs)\r\n - **boolean**: True/false checkbox (can connect to Boolean outputs)\r\n - **handle**: Generic data input (can connect to any component output)\r\n - **data**: Structured data input (can connect to Data outputs)\r\n\r\n ## Input Types for Connections\r\n - **Text**: Text/String data from components\r\n - **Data**: Structured data objects\r\n - **Message**: Message objects with text content\r\n - **Number**: Numeric values\r\n - **Boolean**: True/false values\r\n - **Any**: Accepts any type of connection\r\n - **Combinations**: Text,Message | Data,Text | Text,Data,Message | etc.\r\n \"\"\"\r\n\r\n display_name = \"Create Data\"\r\n description = \"Creates dynamic input fields that can receive data from other components or manual input.\"\r\n icon = \"braces\"\r\n name = \"AdvancedDynamicFormBuilder\"\r\n\r\n def __init__(self, **kwargs):\r\n super().__init__(**kwargs)\r\n self._dynamic_inputs = {}\r\n\r\n inputs = [\r\n TableInput(\r\n name=\"form_fields\",\r\n display_name=\"Input Configuration\",\r\n info=\"Define the dynamic form fields. Each row creates a new input field that can connect to other components.\",\r\n table_schema=[\r\n {\r\n \"name\": \"field_name\",\r\n \"display_name\": \"Field Name\",\r\n \"type\": \"str\",\r\n \"description\": \"Name for the field (used as both internal name and display label)\",\r\n },\r\n {\r\n \"name\": \"field_type\",\r\n \"display_name\": \"Field Type\",\r\n \"type\": \"str\",\r\n \"description\": \"Type of input field to create\",\r\n \"options\": [\"Text\", \"Data\", \"Number\", \"Handle\", \"Boolean\"],\r\n \"value\": \"Text\",\r\n },\r\n ],\r\n value=[{\"field_name\": \"field_name\", \"field_type\": \"Text\"}],\r\n real_time_refresh=True,\r\n ),\r\n BoolInput(\r\n name=\"include_metadata\",\r\n display_name=\"Include Metadata\",\r\n info=\"Include form configuration metadata in the output.\",\r\n value=False,\r\n advanced=True,\r\n ),\r\n ]\r\n\r\n outputs = [\r\n Output(display_name=\"Data\", name=\"form_data\", method=\"process_form\"),\r\n Output(display_name=\"Message\", name=\"message\", method=\"get_message\"),\r\n ]\r\n\r\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str = None) -> dict:\r\n \"\"\"Update build configuration to add dynamic inputs that can connect to other components.\"\"\"\r\n if field_name == \"form_fields\":\r\n # Store current values before clearing dynamic inputs\r\n current_values = {}\r\n keys_to_remove = [key for key in build_config if key.startswith(\"dynamic_\")]\r\n for key in keys_to_remove:\r\n # Preserve the current value before deletion\r\n if hasattr(self, key):\r\n current_values[key] = getattr(self, key)\r\n del build_config[key]\r\n\r\n # Add dynamic inputs based on table configuration\r\n # Safety check to ensure field_value is not None and is iterable\r\n if field_value is None:\r\n field_value = []\r\n\r\n for i, field_config in enumerate(field_value):\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", f\"field_{i}\")\r\n display_name = field_name # Use field_name as display_name\r\n field_type_option = field_config.get(\"field_type\", \"Text\")\r\n default_value = \"\" # All fields have empty default value\r\n required = False # All fields are optional by default\r\n help_text = \"\" # All fields have empty help text\r\n\r\n # Map field type options to actual field types and input types\r\n field_type_mapping = {\r\n \"Text\": {\"field_type\": \"multiline\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Data\": {\"field_type\": \"data\", \"input_types\": [\"Data\"]},\r\n \"Number\": {\"field_type\": \"number\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Handle\": {\"field_type\": \"handle\", \"input_types\": [\"Text\", \"Data\", \"Message\"]},\r\n \"Boolean\": {\"field_type\": \"boolean\", \"input_types\": None},\r\n }\r\n\r\n field_config_mapped = field_type_mapping.get(\r\n field_type_option, {\"field_type\": \"text\", \"input_types\": []}\r\n )\r\n field_type = field_config_mapped[\"field_type\"]\r\n input_types_list = field_config_mapped[\"input_types\"]\r\n\r\n # Create the appropriate input type based on field_type\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n\r\n if field_type == \"text\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"multiline\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"number\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_int = int(current_value)\r\n else:\r\n current_int = 0\r\n except (ValueError, TypeError):\r\n try:\r\n current_int = int(default_value) if default_value else 0\r\n except ValueError:\r\n current_int = 0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_int,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_int,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"float\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_float = float(current_value)\r\n else:\r\n current_float = 0.0\r\n except (ValueError, TypeError):\r\n try:\r\n current_float = float(default_value) if default_value else 0.0\r\n except ValueError:\r\n current_float = 0.0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_float,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_float,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"boolean\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n # Convert current value to boolean\r\n if isinstance(current_value, bool):\r\n current_bool = current_value\r\n else:\r\n current_bool = str(current_value).lower() in [\"true\", \"1\", \"yes\"] if current_value else False\r\n\r\n # Boolean fields don't use input_types parameter to avoid errors\r\n build_config[dynamic_input_name] = BoolInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_bool,\r\n input_types=[],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"handle\":\r\n # HandleInput for generic data connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Accepts: {', '.join(input_types_list) if input_types_list else 'Any'})\",\r\n input_types=input_types_list if input_types_list else [\"Data\", \"Text\", \"Message\"],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"data\":\r\n # Specialized for Data type connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Data input)\",\r\n input_types=[\"Data\"] if not input_types_list else input_types_list,\r\n required=required,\r\n )\r\n\r\n else:\r\n # Default to text input for unknown types\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Unknown type '{field_type}', defaulting to text)\",\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n return build_config\r\n\r\n def get_dynamic_values(self) -> dict[str, Any]:\r\n \"\"\"Extract simple values from all dynamic inputs, handling both manual and connected inputs.\"\"\"\r\n dynamic_values = {}\r\n connection_info = {}\r\n form_fields = getattr(self, \"form_fields\", [])\r\n\r\n for field_config in form_fields:\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", \"\")\r\n if field_name:\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n value = getattr(self, dynamic_input_name, None)\r\n\r\n # Extract simple values from connections or manual input\r\n if value is not None:\r\n try:\r\n extracted_value = self._extract_simple_value(value)\r\n dynamic_values[field_name] = extracted_value\r\n\r\n # Determine connection type for status\r\n if hasattr(value, \"text\") and hasattr(value, \"timestamp\"):\r\n connection_info[field_name] = \"Connected (Message)\"\r\n elif hasattr(value, \"data\"):\r\n connection_info[field_name] = \"Connected (Data)\"\r\n elif isinstance(value, (str, int, float, bool, list, dict)):\r\n connection_info[field_name] = \"Manual input\"\r\n else:\r\n connection_info[field_name] = \"Connected (Object)\"\r\n\r\n except Exception:\r\n # Fallback to string representation if all else fails\r\n dynamic_values[field_name] = str(value)\r\n connection_info[field_name] = \"Error\"\r\n else:\r\n # Use empty default value if nothing connected\r\n dynamic_values[field_name] = \"\"\r\n connection_info[field_name] = \"Empty default\"\r\n\r\n # Store connection info for status output\r\n self._connection_info = connection_info\r\n return dynamic_values\r\n\r\n def _extract_simple_value(self, value: Any) -> Any:\r\n \"\"\"Extract the simplest, most useful value from any input type.\"\"\"\r\n # Handle None\r\n if value is None:\r\n return None\r\n\r\n # Handle simple types directly\r\n if isinstance(value, (str, int, float, bool)):\r\n return value\r\n\r\n # Handle lists and tuples - keep simple\r\n if isinstance(value, (list, tuple)):\r\n return [self._extract_simple_value(item) for item in value]\r\n\r\n # Handle dictionaries - keep simple\r\n if isinstance(value, dict):\r\n return {str(k): self._extract_simple_value(v) for k, v in value.items()}\r\n\r\n # Handle Message objects - extract only the text\r\n if hasattr(value, \"text\"):\r\n return str(value.text) if value.text is not None else \"\"\r\n\r\n # Handle Data objects - extract the data content\r\n if hasattr(value, \"data\") and value.data is not None:\r\n return self._extract_simple_value(value.data)\r\n\r\n # For any other object, convert to string\r\n return str(value)\r\n\r\n def process_form(self) -> Data:\r\n \"\"\"Process all dynamic form inputs and return clean data with just field values.\"\"\"\r\n # Get all dynamic values (just the key:value pairs)\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n # Update status with connection info\r\n connected_fields = len([v for v in getattr(self, \"_connection_info\", {}).values() if \"Connected\" in v])\r\n total_fields = len(dynamic_values)\r\n\r\n self.status = f\"Form processed successfully. {connected_fields}/{total_fields} fields connected to components.\"\r\n\r\n # Return clean Data object with just the field values\r\n return Data(data=dynamic_values)\r\n\r\n def get_message(self) -> Message:\r\n \"\"\"Return form data as a formatted text message.\"\"\"\r\n # Get all dynamic values\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n if not dynamic_values:\r\n return Message(text=\"No form data available\")\r\n\r\n # Format as text message\r\n message_lines = [\"📋 Form Data:\"]\r\n message_lines.append(\"=\" * 40)\r\n\r\n for field_name, value in dynamic_values.items():\r\n # Use field_name as display_name\r\n display_name = field_name\r\n\r\n message_lines.append(f\"• {display_name}: {value}\")\r\n\r\n message_lines.append(\"=\" * 40)\r\n message_lines.append(f\"Total fields: {len(dynamic_values)}\")\r\n\r\n message_text = \"\\n\".join(message_lines)\r\n self.status = f\"Message formatted with {len(dynamic_values)} fields\"\r\n\r\n return Message(text=message_text)" + "value": "from typing import Any\r\n\r\nfrom langflow.custom import Component\r\nfrom langflow.io import (\r\n BoolInput,\r\n FloatInput,\r\n HandleInput,\r\n IntInput,\r\n MultilineInput,\r\n Output,\r\n StrInput,\r\n TableInput,\r\n)\r\nfrom langflow.schema.data import Data\r\nfrom langflow.schema.message import Message\r\n\r\n\r\nclass CrateData(Component):\r\n \"\"\"Dynamic Form Component\r\n\r\n This component creates dynamic inputs that can receive data from other components\r\n or be filled manually. It demonstrates advanced dynamic input functionality with\r\n component connectivity.\r\n\r\n ## Features\r\n - **Dynamic Input Generation**: Create inputs based on table configuration\r\n - **Component Connectivity**: Inputs can receive data from other components\r\n - **Multiple Input Types**: Support for text, number, boolean, and handle inputs\r\n - **Flexible Data Sources**: Manual input OR component connections\r\n - **Real-time Updates**: Form fields update immediately when table changes\r\n - **Multiple Output Formats**: Data and formatted Message outputs\r\n - **JSON Output**: Collects all dynamic inputs into a structured JSON response\r\n\r\n ## Use Cases\r\n - Dynamic API parameter collection from multiple sources\r\n - Variable data aggregation from different components\r\n - Flexible pipeline configuration\r\n - Multi-source data processing\r\n\r\n ## Field Types Available\r\n - **text**: Single-line text input (can connect to Text/String outputs)\r\n - **multiline**: Multi-line text input (can connect to Text outputs)\r\n - **number**: Integer input (can connect to Number outputs)\r\n - **float**: Decimal number input (can connect to Number outputs)\r\n - **boolean**: True/false checkbox (can connect to Boolean outputs)\r\n - **handle**: Generic data input (can connect to any component output)\r\n - **data**: Structured data input (can connect to Data outputs)\r\n\r\n ## Input Types for Connections\r\n - **Text**: Text/String data from components\r\n - **Data**: Structured data objects\r\n - **Message**: Message objects with text content\r\n - **Number**: Numeric values\r\n - **Boolean**: True/false values\r\n - **Any**: Accepts any type of connection\r\n - **Combinations**: Text,Message | Data,Text | Text,Data,Message | etc.\r\n \"\"\"\r\n\r\n display_name = \"Create Data\"\r\n description = \"Creates dynamic input fields that can receive data from other components or manual input.\"\r\n icon = \"braces\"\r\n name = \"AdvancedDynamicFormBuilder\"\r\n\r\n def __init__(self, **kwargs):\r\n super().__init__(**kwargs)\r\n self._dynamic_inputs = {}\r\n\r\n inputs = [\r\n TableInput(\r\n name=\"form_fields\",\r\n display_name=\"Input Configuration\",\r\n info=\"Define the dynamic form fields. Each row creates a new input field that can connect to other components.\",\r\n table_schema=[\r\n {\r\n \"name\": \"field_name\",\r\n \"display_name\": \"Field Name\",\r\n \"type\": \"str\",\r\n \"description\": \"Name for the field (used as both internal name and display label)\",\r\n },\r\n {\r\n \"name\": \"field_type\",\r\n \"display_name\": \"Field Type\",\r\n \"type\": \"str\",\r\n \"description\": \"Type of input field to create\",\r\n \"options\": [\"Text\", \"Data\", \"Number\", \"Handle\", \"Boolean\"],\r\n \"value\": \"Text\",\r\n },\r\n ],\r\n value=[{\"field_name\": \"field_name\", \"field_type\": \"Text\"}],\r\n real_time_refresh=True,\r\n ),\r\n BoolInput(\r\n name=\"include_metadata\",\r\n display_name=\"Include Metadata\",\r\n info=\"Include form configuration metadata in the output.\",\r\n value=False,\r\n advanced=True,\r\n ),\r\n ]\r\n\r\n outputs = [\r\n Output(display_name=\"Data\", name=\"form_data\", method=\"process_form\"),\r\n Output(display_name=\"Message\", name=\"message\", method=\"get_message\"),\r\n ]\r\n\r\n def update_build_config(self, build_config: dict, field_value: Any, field_name: str = None) -> dict:\r\n \"\"\"Update build configuration to add dynamic inputs that can connect to other components.\"\"\"\r\n if field_name == \"form_fields\":\r\n # Store current values before clearing dynamic inputs\r\n current_values = {}\r\n keys_to_remove = [key for key in build_config if key.startswith(\"dynamic_\")]\r\n for key in keys_to_remove:\r\n # Preserve the current value before deletion\r\n if hasattr(self, key):\r\n current_values[key] = getattr(self, key)\r\n del build_config[key]\r\n\r\n # Add dynamic inputs based on table configuration\r\n # Safety check to ensure field_value is not None and is iterable\r\n if field_value is None:\r\n field_value = []\r\n\r\n for i, field_config in enumerate(field_value):\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", f\"field_{i}\")\r\n display_name = field_name # Use field_name as display_name\r\n field_type_option = field_config.get(\"field_type\", \"Text\")\r\n default_value = \"\" # All fields have empty default value\r\n required = False # All fields are optional by default\r\n help_text = \"\" # All fields have empty help text\r\n\r\n # Map field type options to actual field types and input types\r\n field_type_mapping = {\r\n \"Text\": {\"field_type\": \"multiline\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Data\": {\"field_type\": \"data\", \"input_types\": [\"Data\"]},\r\n \"Number\": {\"field_type\": \"number\", \"input_types\": [\"Text\", \"Message\"]},\r\n \"Handle\": {\"field_type\": \"handle\", \"input_types\": [\"Text\", \"Data\", \"Message\"]},\r\n \"Boolean\": {\"field_type\": \"boolean\", \"input_types\": None},\r\n }\r\n\r\n field_config_mapped = field_type_mapping.get(\r\n field_type_option, {\"field_type\": \"text\", \"input_types\": []}\r\n )\r\n field_type = field_config_mapped[\"field_type\"]\r\n input_types_list = field_config_mapped[\"input_types\"]\r\n\r\n # Create the appropriate input type based on field_type\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n\r\n if field_type == \"text\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"multiline\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n if input_types_list:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_value,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = MultilineInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"number\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_int = int(current_value)\r\n else:\r\n current_int = 0\r\n except (ValueError, TypeError):\r\n try:\r\n current_int = int(default_value) if default_value else 0\r\n except ValueError:\r\n current_int = 0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_int,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = IntInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_int,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"float\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n try:\r\n if current_value:\r\n current_float = float(current_value)\r\n else:\r\n current_float = 0.0\r\n except (ValueError, TypeError):\r\n try:\r\n current_float = float(default_value) if default_value else 0.0\r\n except ValueError:\r\n current_float = 0.0\r\n\r\n if input_types_list:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Can connect to: {', '.join(input_types_list)})\",\r\n value=current_float,\r\n required=required,\r\n input_types=input_types_list,\r\n )\r\n else:\r\n build_config[dynamic_input_name] = FloatInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_float,\r\n required=required,\r\n )\r\n\r\n elif field_type == \"boolean\":\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n # Convert current value to boolean\r\n if isinstance(current_value, bool):\r\n current_bool = current_value\r\n else:\r\n current_bool = str(current_value).lower() in [\"true\", \"1\", \"yes\"] if current_value else False\r\n\r\n # Boolean fields don't use input_types parameter to avoid errors\r\n build_config[dynamic_input_name] = BoolInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=help_text,\r\n value=current_bool,\r\n input_types=[],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"handle\":\r\n # HandleInput for generic data connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Accepts: {', '.join(input_types_list) if input_types_list else 'Any'})\",\r\n input_types=input_types_list if input_types_list else [\"Data\", \"Text\", \"Message\"],\r\n required=required,\r\n )\r\n\r\n elif field_type == \"data\":\r\n # Specialized for Data type connections\r\n build_config[dynamic_input_name] = HandleInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Data input)\",\r\n input_types=[\"Data\"] if not input_types_list else input_types_list,\r\n required=required,\r\n )\r\n\r\n else:\r\n # Default to text input for unknown types\r\n # Use preserved value if available, otherwise use default\r\n current_value = current_values.get(dynamic_input_name, default_value)\r\n if current_value is None:\r\n current_value = default_value\r\n \r\n build_config[dynamic_input_name] = StrInput(\r\n name=dynamic_input_name,\r\n display_name=display_name,\r\n info=f\"{help_text} (Unknown type '{field_type}', defaulting to text)\",\r\n value=current_value,\r\n required=required,\r\n )\r\n\r\n return build_config\r\n\r\n def get_dynamic_values(self) -> dict[str, Any]:\r\n \"\"\"Extract simple values from all dynamic inputs, handling both manual and connected inputs.\"\"\"\r\n dynamic_values = {}\r\n connection_info = {}\r\n form_fields = getattr(self, \"form_fields\", [])\r\n\r\n for field_config in form_fields:\r\n # Safety check to ensure field_config is not None\r\n if field_config is None:\r\n continue\r\n\r\n field_name = field_config.get(\"field_name\", \"\")\r\n if field_name:\r\n dynamic_input_name = f\"dynamic_{field_name}\"\r\n value = getattr(self, dynamic_input_name, None)\r\n\r\n # Extract simple values from connections or manual input\r\n if value is not None:\r\n try:\r\n extracted_value = self._extract_simple_value(value)\r\n dynamic_values[field_name] = extracted_value\r\n\r\n # Determine connection type for status\r\n if hasattr(value, \"text\") and hasattr(value, \"timestamp\"):\r\n connection_info[field_name] = \"Connected (Message)\"\r\n elif hasattr(value, \"data\"):\r\n connection_info[field_name] = \"Connected (Data)\"\r\n elif isinstance(value, (str, int, float, bool, list, dict)):\r\n connection_info[field_name] = \"Manual input\"\r\n else:\r\n connection_info[field_name] = \"Connected (Object)\"\r\n\r\n except Exception:\r\n # Fallback to string representation if all else fails\r\n dynamic_values[field_name] = str(value)\r\n connection_info[field_name] = \"Error\"\r\n else:\r\n # Use empty default value if nothing connected\r\n dynamic_values[field_name] = \"\"\r\n connection_info[field_name] = \"Empty default\"\r\n\r\n # Store connection info for status output\r\n self._connection_info = connection_info\r\n return dynamic_values\r\n\r\n def _extract_simple_value(self, value: Any) -> Any:\r\n \"\"\"Extract the simplest, most useful value from any input type.\"\"\"\r\n # Handle None\r\n if value is None:\r\n return None\r\n\r\n # Handle simple types directly\r\n if isinstance(value, (str, int, float, bool)):\r\n return value\r\n\r\n # Handle lists and tuples - keep simple\r\n if isinstance(value, (list, tuple)):\r\n return [self._extract_simple_value(item) for item in value]\r\n\r\n # Handle dictionaries - keep simple\r\n if isinstance(value, dict):\r\n return {str(k): self._extract_simple_value(v) for k, v in value.items()}\r\n\r\n # Handle Message objects - extract only the text\r\n if hasattr(value, \"text\"):\r\n return str(value.text) if value.text is not None else \"\"\r\n\r\n # Handle Data objects - extract the data content\r\n if hasattr(value, \"data\") and value.data is not None:\r\n return self._extract_simple_value(value.data)\r\n\r\n # For any other object, convert to string\r\n return str(value)\r\n\r\n def process_form(self) -> Data:\r\n \"\"\"Process all dynamic form inputs and return clean data with just field values.\"\"\"\r\n # Get all dynamic values (just the key:value pairs)\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n # Update status with connection info\r\n connected_fields = len([v for v in getattr(self, \"_connection_info\", {}).values() if \"Connected\" in v])\r\n total_fields = len(dynamic_values)\r\n\r\n self.status = f\"Form processed successfully. {connected_fields}/{total_fields} fields connected to components.\"\r\n\r\n # Return clean Data object with just the field values\r\n return Data(data=dynamic_values)\r\n\r\n def get_message(self) -> Message:\r\n \"\"\"Return form data as a formatted text message.\"\"\"\r\n # Get all dynamic values\r\n dynamic_values = self.get_dynamic_values()\r\n\r\n if not dynamic_values:\r\n return Message(text=\"No form data available\")\r\n\r\n # Format as text message\r\n message_lines = [\"\ud83d\udccb Form Data:\"]\r\n message_lines.append(\"=\" * 40)\r\n\r\n for field_name, value in dynamic_values.items():\r\n # Use field_name as display_name\r\n display_name = field_name\r\n\r\n message_lines.append(f\"\u2022 {display_name}: {value}\")\r\n\r\n message_lines.append(\"=\" * 40)\r\n message_lines.append(f\"Total fields: {len(dynamic_values)}\")\r\n\r\n message_text = \"\\n\".join(message_lines)\r\n self.status = f\"Message formatted with {len(dynamic_values)} fields\"\r\n\r\n return Message(text=message_text)" }, "dynamic_connector_type": { "_input_type": "MultilineInput", @@ -1838,7 +1858,7 @@ "dragging": false, "id": "AdvancedDynamicFormBuilder-81Exw", "measured": { - "height": 552, + "height": 554, "width": 320 }, "position": { @@ -2615,7 +2635,7 @@ "dragging": false, "id": "DoclingRemote-Dp3PX", "measured": { - "height": 475, + "height": 477, "width": 320 }, "position": { @@ -2872,7 +2892,7 @@ "dragging": false, "id": "ExportDoclingDocument-zZdRg", "measured": { - "height": 347, + "height": 348, "width": 320 }, "position": { @@ -2912,7 +2932,7 @@ ], "frozen": false, "icon": "table", - "last_updated": "2025-10-04T02:17:01.354Z", + "last_updated": "2025-10-10T13:34:19.877Z", "legacy": false, "lf_version": "1.6.3.dev0", "metadata": { @@ -3288,7 +3308,7 @@ "dragging": false, "id": "DataFrameOperations-1BWXB", "measured": { - "height": 399, + "height": 401, "width": 320 }, "position": { @@ -3328,7 +3348,7 @@ ], "frozen": false, "icon": "table", - "last_updated": "2025-10-04T02:17:01.355Z", + "last_updated": "2025-10-10T13:34:19.878Z", "legacy": false, "lf_version": "1.6.3.dev0", "metadata": { @@ -3704,7 +3724,7 @@ "dragging": false, "id": "DataFrameOperations-N80fC", "measured": { - "height": 399, + "height": 401, "width": 320 }, "position": { @@ -3744,7 +3764,7 @@ ], "frozen": false, "icon": "table", - "last_updated": "2025-10-04T02:17:01.355Z", + "last_updated": "2025-10-10T13:34:19.878Z", "legacy": false, "lf_version": "1.6.3.dev0", "metadata": { @@ -4120,7 +4140,7 @@ "dragging": false, "id": "DataFrameOperations-9vMrp", "measured": { - "height": 399, + "height": 401, "width": 320 }, "position": { @@ -4132,16 +4152,16 @@ } ], "viewport": { - "x": 227.3737875665738, - "y": -299.1651660660417, - "zoom": 0.43587407227641217 + "x": -418.8241631881149, + "y": -563.2891507884635, + "zoom": 0.6194861362488232 } }, "description": "Load your data for chat context with Retrieval Augmented Generation.", "endpoint_name": null, "id": "5488df7c-b93f-4f87-a446-b67028bc0813", "is_component": false, - "last_tested_version": "1.6.3.dev0", + "last_tested_version": "1.6.3.dev1", "name": "OpenSearch Ingestion Flow", "tags": [ "openai", diff --git a/securityconfig/roles.yml b/securityconfig/roles.yml index 07532bfb..163bcb4c 100644 --- a/securityconfig/roles.yml +++ b/securityconfig/roles.yml @@ -21,10 +21,13 @@ openrag_user_role: allowed_actions: - crud - create_index + - indices:admin/mappings/get + - indices:admin/mappings/put + - indices:admin/exists + - indices:admin/get dls: > {"bool":{"should":[ {"term":{"owner":"${user.name}"}}, {"term":{"allowed_users":"${user.name}"}}, {"bool":{"must_not":{"exists":{"field":"owner"}}}} ],"minimum_should_match":1}} - diff --git a/src/services/search_service.py b/src/services/search_service.py index e3e5833b..287f1219 100644 --- a/src/services/search_service.py +++ b/src/services/search_service.py @@ -268,7 +268,7 @@ class SearchService: "document_types": {"terms": {"field": "mimetype", "size": 10}}, "owners": {"terms": {"field": "owner_name.keyword", "size": 10}}, "connector_types": {"terms": {"field": "connector_type", "size": 10}}, - "embedding_models": {"terms": {"field": "embedding_model", "size": 10}}, + "embedding_models": {"terms": {"field": "embedding_model.keyword", "size": 10}}, }, "_source": [ "filename",