Azure AI Search client library for Python

Overview

The Azure AI Search client library for Python allows developers to build rich search experiences and generative AI apps that combine large language models with enterprise data.

Key Features

• Consolidate varied content types into a single searchable index
• Populate an index with JSON documents or use an indexer to pull in data from Azure
• Attach skillsets to an indexer to create searchable content from images and unstructured documents
• Implement query logic and user experiences similar to commercial web search engines and chat-style apps

Getting Started

Install the Azure AI Search client library

Install the Azure AI Search client library for Python using pip:

pip install azure-search-documents

Prerequisites

• Python 3.8 or later is required to use this package.
• You need an Azure subscription and an Azure AI Search service to use this package.

Authenticating the Client

To interact with the search service, you'll need to create an instance of the appropriate client class: SearchClient for searching indexed documents, SearchIndexClient for managing indexes, or SearchIndexerClient for crawling data sources and loading search documents into an index. To instantiate a client object, you'll need an endpoint and Azure roles or an API key.

Creating a SearchClient

To create a SearchClient instance, you'll need the endpoint, API key, and index name. You can use the following code:

from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient

service_endpoint = os.environ["AZURE_SEARCH_SERVICE_ENDPOINT"]
index_name = os.environ["AZURE_SEARCH_INDEX_NAME"]
key = os.environ["AZURE_SEARCH_API_KEY"]

search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))

Retrieving a Specific Document

In addition to querying for documents using keywords and optional filters, you can retrieve a specific document from your index if you already know the key. You can use the following code:

from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient

search_client = SearchClient(service_endpoint, index_name, AzureKeyCredential(key))
result = search_client.get_document(key="23")

Retrieving Multiple Documents

You can upload, merge, merge or upload, and delete multiple documents from an index in a single batched request. You can use the following code:

from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient

documents = [
    {
        "category": "Hotel",
        "hotelId": "1000",
        "rating": 4.0,
        "rooms": [],
        "hotelName": "Azure Inn",
    }
]

result = search_client.upload_documents(documents=[document])

Examples

The Azure AI Search client library for Python includes several examples in the samples directory. These examples demonstrate how to use the client library to search for documents, create indexes, add documents to indexes, and retrieve specific documents.

Troubleshooting

The Azure AI Search client will raise exceptions defined in Azure Core. You can troubleshoot issues by checking the error message and the status code returned by the API. You can also use the logging feature of the client library to log detailed information about the HTTP sessions.

Next Steps

To learn more about the Azure AI Search client library for Python and how to use it, please refer to the Azure AI Search documentation. You can also explore the azure-azure.ai-search-python-sample project on GitHub, which provides a sample implementation of the client library.

Contributing

See CONTRIBUTING.md for details on building, testing, and contributing to this library.