Vectorize a document and ingest it into Azure SQL using Azure Logic Apps

azure-logic-app-vectorize-document.json

{
    "definition": {
        "$schema": "https://schema.management.azure.com/providers/Microsoft.Logic/schemas/2016-06-01/workflowdefinition.json#",
        "actions": {
            "Chunk_text": {
                "type": "ChunkText",
                "inputs": {
                    "chunkingStrategy": "TokenSize",
                    "text": "@body('Parse_a_document')?['text']",
                    "EncodingModel": "cl100k_base",
                    "PageOverlapLength": 0,
                    "TokenSize": 5000
                },
                "runAfter": {
                    "Parse_a_document": [
                        "SUCCEEDED"
                    ]
                }
            },
            "Azure_OpenAI_-_Get_multiple_embeddings": {
                "type": "ServiceProvider",
                "inputs": {
                    "parameters": {
                        "deploymentId": "@parameters('OpenAI_TextEmbedding_Deployment_Identifier_ingesttosql')",
                        "input": "@body('Chunk_text')?['value']"
                    },
                    "serviceProviderConfiguration": {
                        "connectionName": "openai",
                        "operationId": "getArrayEmbeddings",
                        "serviceProviderId": "/serviceProviders/openai"
                    }
                },
                "runAfter": {
                    "Chunk_text": [
                        "SUCCEEDED"
                    ]
                }
            },
            "Parse_a_document": {
                "type": "ParseDocument",
                "inputs": {
                    "content": "@body('Azure_Blob_-_Read_blob_content')?['content']"
                },
                "runAfter": {
                    "Azure_Blob_-_Read_blob_content": [
                        "SUCCEEDED"
                    ]
                }
            },
            "Azure_Blob_-_Read_blob_content": {
                "type": "ServiceProvider",
                "inputs": {
                    "parameters": {
                        "containerName": "@parameters('BlobPath')",
                        "blobName": "@triggerBody()?['name']"
                    },
                    "serviceProviderConfiguration": {
                        "connectionName": "AzureBlob",
                        "operationId": "readBlob",
                        "serviceProviderId": "/serviceProviders/AzureBlob"
                    }
                },
                "runAfter": {}
            },
            "Select_embeddings_and_map_to_AI_Search_schema": {
                "type": "Select",
                "inputs": {
                    "from": "@range(0, length(body('Chunk_text')['value']))",
                    "select": {
                        "chunk": "@body('Chunk_text')['value'][item()]",
                        "filename": "@triggerBody()?['name']",
                        "embedding": "@body('Azure_OpenAI_-_Get_multiple_embeddings')['embeddings'][item()]",
                        "chunkid": "@concat(triggerBody()?['name'], item())"
                    }
                },
                "runAfter": {
                    "Azure_OpenAI_-_Get_multiple_embeddings": [
                        "SUCCEEDED"
                    ]
                }
            },
            "For_each": {
                "type": "Foreach",
                "foreach": "@body('Select_embeddings_and_map_to_AI_Search_schema')",
                "actions": {
                    "SQL_-_Insert_vectors_in_table": {
                        "type": "ServiceProvider",
                        "description": "This step inserts the vector embeddings, content and other metadata into the SQL vector database. Update the Query and Query parameters based on your SQL table schema",
                        "inputs": {
                            "parameters": {
                                "query": "INSERT INTO resumedocs (chunkid, filename, chunk, embedding)\n    VALUES (@chunkid, @filename, @chunk, CAST(@embedding as VECTOR(1536)))",
                                "queryParameters": {
                                    "chunkid": "@{item()['chunkid']}",
                                    "filename": "@{item()['filename']}",
                                    "chunk": "@{item()['chunk']}",
                                    "embedding": "@{item()['embedding']}"
                                }
                            },
                            "serviceProviderConfiguration": {
                                "connectionName": "sql",
                                "operationId": "executeQuery",
                                "serviceProviderId": "/serviceProviders/sql"
                            }
                        }
                    }
                },
                "runAfter": {
                    "Select_embeddings_and_map_to_AI_Search_schema": [
                        "SUCCEEDED"
                    ]
                }
            }
        },
        "contentVersion": "1.0.0.0",
        "outputs": {},
        "triggers": {
            "Azure_Blob_-_When_a_blob_is_added_or_updated": {
                "type": "ServiceProvider",
                "inputs": {
                    "parameters": {
                        "path": "@parameters('BlobPath')"
                    },
                    "serviceProviderConfiguration": {
                        "connectionName": "AzureBlob",
                        "operationId": "whenABlobIsAddedOrModified",
                        "serviceProviderId": "/serviceProviders/AzureBlob"
                    }
                }
            }
        }
    },
    "kind": "stateful"
}