Azure AI Search SDK for Python

Full-text, vector, and hybrid search with AI enrichment capabilities.

Installation

pip install azure-search-documents

Environment Variables

AZURE_SEARCH_ENDPOINT=https://<service-name>.search.windows.net
AZURE_SEARCH_API_KEY=<your-api-key>
AZURE_SEARCH_INDEX_NAME=<your-index-name>

Authentication

API Key

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

client = SearchClient(
    endpoint=os.environ["AZURE_SEARCH_ENDPOINT"],
    index_name=os.environ["AZURE_SEARCH_INDEX_NAME"],
    credential=AzureKeyCredential(os.environ["AZURE_SEARCH_API_KEY"])
)

Entra ID (Recommended)

from azure.search.documents import SearchClient
from azure.identity import DefaultAzureCredential

client = SearchClient(
    endpoint=os.environ["AZURE_SEARCH_ENDPOINT"],
    index_name=os.environ["AZURE_SEARCH_INDEX_NAME"],
    credential=DefaultAzureCredential()
)

Client Types

Create Index with Vector Field

from azure.search.documents.indexes import SearchIndexClient
from azure.search.documents.indexes.models import (
    SearchIndex,
    SearchField,
    SearchFieldDataType,
    VectorSearch,
    HnswAlgorithmConfiguration,
    VectorSearchProfile,
    SearchableField,
    SimpleField
)

index_client = SearchIndexClient(endpoint, AzureKeyCredential(key))

fields = [
    SimpleField(name="id", type=SearchFieldDataType.String, key=True),
    SearchableField(name="title", type=SearchFieldDataType.String),
    SearchableField(name="content", type=SearchFieldDataType.String),
    SearchField(
        name="content_vector",
        type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
        searchable=True,
        vector_search_dimensions=1536,
        vector_search_profile_name="my-vector-profile"
    )
]

vector_search = VectorSearch(
    algorithms=[
        HnswAlgorithmConfiguration(name="my-hnsw")
    ],
    profiles=[
        VectorSearchProfile(
            name="my-vector-profile",
            algorithm_configuration_name="my-hnsw"
        )
    ]
)

index = SearchIndex(
    name="my-index",
    fields=fields,
    vector_search=vector_search
)

index_client.create_or_update_index(index)

Upload Documents

from azure.search.documents import SearchClient

client = SearchClient(endpoint, "my-index", AzureKeyCredential(key))

documents = [
    {
        "id": "1",
        "title": "Azure AI Search",
        "content": "Full-text and vector search service",
        "content_vector": [0.1, 0.2, ...]  # 1536 dimensions
    }
]

result = client.upload_documents(documents)
print(f"Uploaded {len(result)} documents")

Keyword Search

results = client.search(
    search_text="azure search",
    select=["id", "title", "content"],
    top=10
)

for result in results:
    print(f"{result['title']}: {result['@search.score']}")

Vector Search

from azure.search.documents.models import VectorizedQuery

# Your query embedding (1536 dimensions)
query_vector = get_embedding("semantic search capabilities")

vector_query = VectorizedQuery(
    vector=query_vector,
    k_nearest_neighbors=10,
    fields="content_vector"
)

results = client.search(
    vector_queries=[vector_query],
    select=["id", "title", "content"]
)

for result in results:
    print(f"{result['title']}: {result['@search.score']}")

Hybrid Search (Vector + Keyword)

from azure.search.documents.models import VectorizedQuery

vector_query = VectorizedQuery(
    vector=query_vector,
    k_nearest_neighbors=10,
    fields="content_vector"
)

results = client.search(
    search_text="azure search",
    vector_queries=[vector_query],
    select=["id", "title", "content"],
    top=10
)

Semantic Ranking

from azure.search.documents.models import QueryType

results = client.search(
    search_text="what is azure search",
    query_type=QueryType.SEMANTIC,
    semantic_configuration_name="my-semantic-config",
    select=["id", "title", "content"],
    top=10
)

for result in results:
    print(f"{result['title']}")
    if result.get("@search.captions"):
        print(f"  Caption: {result['@search.captions'][0].text}")

Filters

results = client.search(
    search_text="*",
    filter="category eq 'Technology' and rating gt 4",
    order_by=["rating desc"],
    select=["id", "title", "category", "rating"]
)

Facets

results = client.search(
    search_text="*",
    facets=["category,count:10", "rating"],
    top=0  # Only get facets, no documents
)

for facet_name, facet_values in results.get_facets().items():
    print(f"{facet_name}:")
    for facet in facet_values:
        print(f"  {facet['value']}: {facet['count']}")

Autocomplete & Suggest

# Autocomplete
results = client.autocomplete(
    search_text="sea",
    suggester_name="my-suggester",
    mode="twoTerms"
)

# Suggest
results = client.suggest(
    search_text="sea",
    suggester_name="my-suggester",
    select=["title"]
)

Indexer with Skillset

from azure.search.documents.indexes import SearchIndexerClient
from azure.search.documents.indexes.models import (
    SearchIndexer,
    SearchIndexerDataSourceConnection,
    SearchIndexerSkillset,
    EntityRecognitionSkill,
    InputFieldMappingEntry,
    OutputFieldMappingEntry
)

indexer_client = SearchIndexerClient(endpoint, AzureKeyCredential(key))

# Create data source
data_source = SearchIndexerDataSourceConnection(
    name="my-datasource",
    type="azureblob",
    connection_string=connection_string,
    container={"name": "documents"}
)
indexer_client.create_or_update_data_source_connection(data_source)

# Create skillset
skillset = SearchIndexerSkillset(
    name="my-skillset",
    skills=[
        EntityRecognitionSkill(
            inputs=[InputFieldMappingEntry(name="text", source="/document/content")],
            outputs=[OutputFieldMappingEntry(name="organizations", target_name="organizations")]
        )
    ]
)
indexer_client.create_or_update_skillset(skillset)

# Create indexer
indexer = SearchIndexer(
    name="my-indexer",
    data_source_name="my-datasource",
    target_index_name="my-index",
    skillset_name="my-skillset"
)
indexer_client.create_or_update_indexer(indexer)

Best Practices

1. Use hybrid search for best relevance combining vector and keyword
2. Enable semantic ranking for natural language queries
3. Index in batches of 100-1000 documents for efficiency
4. Use filters to narrow results before ranking
5. Configure vector dimensions to match your embedding model
6. Use HNSW algorithm for large-scale vector search
7. Create suggesters at index creation time (cannot add later)

Reference Files

Additional Azure AI Search Patterns

Additional SDK Focus

Write clean, idiomatic Python code for Azure AI Search using azure-search-documents.

Installation for Additional Patterns

pip install azure-search-documents azure-identity

Environment Variables for Additional Patterns

AZURE_SEARCH_ENDPOINT=https://<search-service>.search.windows.net
AZURE_SEARCH_INDEX_NAME=<index-name>
# For API key auth (not recommended for production)
AZURE_SEARCH_API_KEY=<api-key>

Authentication for Additional Patterns

DefaultAzureCredential (preferred):