Package org.springframework.ai.vectorstore.azure

Class AzureVectorStore

java.lang.Object

org.springframework.ai.vectorstore.observation.AbstractObservationVectorStore

org.springframework.ai.vectorstore.azure.AzureVectorStore

All Implemented Interfaces:

Consumer<List<Document>>, DocumentWriter, VectorStore, VectorStoreRetriever, org.springframework.beans.factory.InitializingBean

public class AzureVectorStore
extends AbstractObservationVectorStore
implements org.springframework.beans.factory.InitializingBean

Uses Azure Cognitive Search as a backing vector store. Documents can be preloaded into a Cognitive Search index and managed via Azure tools or added and managed through this VectorStore. The underlying index is configured in the provided Azure SearchIndexClient.

Author:

Greg Meyer, Xiangyang Yu, Christian Tzolov, Josh Long, Thomas Vitale, Soby Chacko, Jinwoo Lee

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AzureVectorStore.Builder	Builder class for creating AzureVectorStore instances.
static final record	AzureVectorStore.MetadataField

Field Summary

Fields

Modifier and Type	Field	Description
static final String	DEFAULT_INDEX_NAME

Fields inherited from class org.springframework.ai.vectorstore.observation.AbstractObservationVectorStore

batchingStrategy, embeddingModel

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	AzureVectorStore(AzureVectorStore.Builder builder)	Protected constructor that accepts a builder instance.

Method Summary

Modifier and Type	Method	Description
void	afterPropertiesSet()
static AzureVectorStore.Builder	builder(com.azure.search.documents.indexes.SearchIndexClient searchIndexClient, EmbeddingModel embeddingModel)
VectorStoreObservationContext.Builder	createObservationContextBuilder(String operationName)	Create a new VectorStoreObservationContext.Builder instance.
void	doAdd(List<Document> documents)	Perform the actual add operation.
void	doDelete(List<String> documentIds)	Perform the actual delete operation.
List<Document>	doSimilaritySearch(SearchRequest request)	Perform the actual similarity search operation.
<T> Optional<T>	getNativeClient()	Returns the native client if available in this vector store implementation.
List<Document>	similaritySearch(String query)	Retrieves documents by query embedding similarity using the default SearchRequest's search criteria.

Methods inherited from class org.springframework.ai.vectorstore.observation.AbstractObservationVectorStore

add, delete, delete, doDelete, similaritySearch

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.util.function.Consumer

andThen

Methods inherited from interface org.springframework.ai.document.DocumentWriter

write

Methods inherited from interface org.springframework.ai.vectorstore.VectorStore

accept, delete, getName

Field Details

DEFAULT_INDEX_NAME

public static final String DEFAULT_INDEX_NAME

See Also:

• Constant Field Values

Constructor Details

AzureVectorStore

protected AzureVectorStore(AzureVectorStore.Builder builder)

Protected constructor that accepts a builder instance. This is the preferred way to create new AzureVectorStore instances.

Parameters:

builder - the configured builder instance

Method Details

builder

public static AzureVectorStore.Builder builder(com.azure.search.documents.indexes.SearchIndexClient searchIndexClient,
 EmbeddingModel embeddingModel)

doAdd

public void doAdd(List<Document> documents)

Description copied from class: AbstractObservationVectorStore

Perform the actual add operation.

Specified by:

doAdd in class AbstractObservationVectorStore

Parameters:

documents - the documents to add

doDelete

public void doDelete(List<String> documentIds)

Description copied from class: AbstractObservationVectorStore

Perform the actual delete operation.

Specified by:

doDelete in class AbstractObservationVectorStore

Parameters:

documentIds - the list of document IDs to delete

similaritySearch

public List<Document> similaritySearch(String query)

Description copied from interface: VectorStoreRetriever

Retrieves documents by query embedding similarity using the default SearchRequest's search criteria.

Specified by:

similaritySearch in interface VectorStoreRetriever

Parameters:

query - Text to use for embedding similarity comparison.

Returns:

Returns a list of documents that have embeddings similar to the query text embedding.

doSimilaritySearch

public List<Document> doSimilaritySearch(SearchRequest request)

Description copied from class: AbstractObservationVectorStore

Perform the actual similarity search operation.

Specified by:

doSimilaritySearch in class AbstractObservationVectorStore

Parameters:

request - the search request

Returns:

the list of documents that match the query request conditions

afterPropertiesSet

public void afterPropertiesSet()
                        throws Exception

Specified by:

afterPropertiesSet in interface org.springframework.beans.factory.InitializingBean

Throws:

Exception

createObservationContextBuilder

public VectorStoreObservationContext.Builder createObservationContextBuilder(String operationName)

Description copied from class: AbstractObservationVectorStore

Create a new VectorStoreObservationContext.Builder instance.

Specified by:

createObservationContextBuilder in class AbstractObservationVectorStore

Parameters:

operationName - the operation name

Returns:

the observation context builder

getNativeClient

public <T> Optional<T> getNativeClient()

Description copied from interface: VectorStore

Returns the native client if available in this vector store implementation. Note on usage: 1. Returns empty Optional when no native client is available 2. Due to Java type erasure, runtime type checking is not possible Example usage: When working with implementation with known native client: Optional client = vectorStore.getNativeClient(); Note: Using Optionalinvalid input: '<'?> will return the native client if one exists, rather than an empty Optional. For type safety, prefer using the specific client type.

Specified by:

getNativeClient in interface VectorStore

Type Parameters:

T - The type of the native client

Returns:

Optional containing native client if available, empty Optional otherwise