Preface
Introduction to Azure AI Search Ingestion Automation with ADLS recipe
- Azure AI Search Ingestion Automation with ADLS recipe contents
  - Azure AI Search Ingestion Automation with ADLS recipe assets
Using the Azure AI Search Ingestion Automation with ADLS recipe

Azure AI Search Ingestion Automation with ADLS

Back Next

Step 4. Invoke the process

You can invoke the Azure AI Search Ingestion Automation with ADLS process to create an index, data source, skillset, and indexer for the existing files in Azure Data Lake Storage (ADLS), populate the index with the data, and then return the documents that meet the search criteria.

You can pass input through REST or SOAP API endpoints in any API client such as cURL, Postman, SOAP UI, or through any programming language.

For example:

Open the Azure AI search ingestion Automation with ADLS
process and click

Actions

Properties Details

Copy Service URL

Open Postman.

Select the HTTP verb as POST and specify the generated REST service URL and payload as shown in the following image:

The image shows the HTTP verb, REST service URL and the request
payload.

Here is the sample payload:

{
    "inputIndexName": "reviews",
    "inputApiVersion": "2024-07-01",
    "inputSearchDetails": {
    },
    "inputIndexDetails": {
        "name": "reviews",
        "fields": [
            {
                "name": "id",
                "type": "Edm.String",
                "searchable": true,
                "filterable": true,
                "retrievable": true,
                "stored": true,
                "sortable": true,
                "facetable": true,
                "key": true
            },
            {
                "name": "Location",
                "type": "Edm.String",
                "searchable": true,
                "filterable": true,
                "retrievable": true,
                "stored": true,
                "sortable": true,
                "facetable": true
            },
            {
                "name": "Review",
                "type": "Edm.String",
                "searchable": true,
                "filterable": true,
                "retrievable": true,
                "stored": true,
                "sortable": true,
                "facetable": true
            },
            {
                "name": "Date",
                "type": "Edm.String",
                "searchable": true,
                "filterable": true,
                "retrievable": true,
                "stored": true,
                "sortable": true,
                "facetable": true
            },
            {
                "name": "vectorcontent",
                "type": "Collection(Edm.Single)",
                "searchable": true,
                "filterable": false,
                "retrievable": true,
                "stored": true,
                "sortable": false,
                "facetable": false,
                "key": false,
                "dimensions": 1536,
                "vectorSearchProfile": "vector-profile-1727966526693"
            }
        ],
        "similarity": {
            "@odataType": "#Microsoft.Azure.Search.BM25Similarity"
        },
        "semantic": {
            "configurations": [
                {
                    "name": "default",
                    "prioritizedFields": {
                        "titleField": {
                            "fieldName": "Review"
                        },
                        "prioritizedContentFields": [
                            {
                                "fieldName": "Review"
                            }
                        ],
                        "prioritizedKeywordsFields": []
                    }
                }
            ]
        },
        "vectorSearch": {
            "algorithms": [
                {
                    "name": "vector-config-1727966528896",
                    "kind": "hnsw",
                    "hnswParameters": {
                        "metric": "cosine",
                        "m": 4,
                        "efConstruction": 400,
                        "efSearch": 500
                    }
                }
            ],
            "profiles": [
                {
                    "name": "vector-profile-1727966526693",
                    "algorithm": "vector-config-1727966528896",
                    "vectorizer": "vectorizer-1727966531637",
                    "compression": "vector-1727966521527-compressor"
                }
            ],
            "vectorizers": [
                {
                    "name": "vectorizer-1727966531637",
                    "kind": "azureOpenAI",
                    "azureOpenAIParameters": {
                        "resourceUri": "https://chatgptopenaiseas.openai.azure.com",
                        "deploymentId": "adavectordb",
                        "apiKey": "5df4e4f520ed4e6f810f0eb070a09680",
                        "modelName": "text-embedding-ada-002"
                    }
                }
            ],
            "compressions": [
                {
                    "name": "vector-1727966521527-compressor",
                    "kind": "scalarQuantization",
                    "rerankWithOriginalVectors": true,
                    "defaultOversampling": 4,
                    "scalarQuantizationParameters": {
                        "quantizedDataType": "int8"
                    }
                }
            ]
        }
    },
    "inputDataSourceDetails": {
        "name": "reviews-datasource",
        "description": "review datasource",
        "type": "adlsgen2",
        "credentials": {
            "connectionString": "DefaultEndpointsProtocol=https;AccountName=<Search_Index_Host>;AccountKey=<Account_Key>;EndpointSuffix=core.windows.net"
        },
        "container": {
            "name": "reviews"
        }
    },
    "inputIndexerDetails": {
        "name": "review-indexer",
        "description": "review indexer",
        "dataSourceName": "reviews-datasource",
        "targetIndexName": "reviews",
        "parameters": {
            "configuration": {
                "dataToExtract": "contentAndMetadata",
                "parsingMode": "default"
            }
        }
    }
}

For more information about the index, indexer, skillset, and data source, see the Azure documentation.

Enter the user account details on the Authorization
tab.

Click Send
.

You can also invoke the process using the Run Using option.

Using the Azure AI Search Ingestion Automation with ADLS recipe

Download Guide

Watch

Comments

Cloud Application Integration Homepage

Free Trial

Communities

Knowledge Base