Package dev.langchain4j.rag.content.retriever.azure.search

Class AzureAiSearchContentRetriever

java.lang.Object

dev.langchain4j.store.embedding.azure.search.AbstractAzureAiSearchEmbeddingStore

dev.langchain4j.rag.content.retriever.azure.search.AzureAiSearchContentRetriever

All Implemented Interfaces:

ContentRetriever, EmbeddingStore<TextSegment>

public class AzureAiSearchContentRetriever
extends AbstractAzureAiSearchEmbeddingStore
implements ContentRetriever

Represents Azure AI Search Service as a ContentRetriever.
This class supports 4 AzureAiSearchQueryTypes:
- VECTOR: Uses the vector search algorithm to find the most similar TextSegments. More details can be found here.
- FULL_TEXT: Uses the full text search to find the most similar TextSegments. More details can be found here.
- HYBRID: Uses the hybrid search (vector + full text) to find the most similar TextSegments. More details can be found here.
- HYBRID_WITH_RERANKING: Uses the hybrid search (vector + full text) to find the most similar TextSegments, and uses the semantic re-ranker algorithm to rank the results. More details can be found here.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AzureAiSearchContentRetriever.Builder

Field Summary

Fields inherited from class dev.langchain4j.store.embedding.azure.search.AbstractAzureAiSearchEmbeddingStore

DEFAULT_FIELD_CONTENT, DEFAULT_FIELD_CONTENT_VECTOR, DEFAULT_FIELD_METADATA, DEFAULT_FIELD_METADATA_ATTRS, DEFAULT_FIELD_METADATA_SOURCE, DEFAULT_INDEX_NAME, filterMapper, searchClient, SEMANTIC_SEARCH_CONFIG_NAME, VECTOR_ALGORITHM_NAME, VECTOR_SEARCH_PROFILE_NAME

Constructor Summary

Constructors

Constructor

Description

AzureAiSearchContentRetriever(String endpoint, com.azure.core.credential.AzureKeyCredential keyCredential, com.azure.core.credential.TokenCredential tokenCredential, boolean createOrUpdateIndex, int dimensions, com.azure.search.documents.indexes.models.SearchIndex index, String indexName, EmbeddingModel embeddingModel, int maxResults, double minScore, AzureAiSearchQueryType azureAiSearchQueryType, AzureAiSearchFilterMapper filterMapper, Filter filter)

Method Summary

Modifier and Type	Method	Description
void	add(Document document)	Add Document to the full text search engine.
void	add(TextSegment segment)	Add TextSegment to the full text search engine.
void	add(String content)	Add content to the full text search engine.
void	add(List<TextSegment> segments)	Add a list of TextSegments to the full text search engine.
static AzureAiSearchContentRetriever.Builder	builder()
List<Content>	retrieve(Query query)	Retrieves relevant Contents using a given Query.

Methods inherited from class dev.langchain4j.store.embedding.azure.search.AbstractAzureAiSearchEmbeddingStore

add, add, add, addAll, addAll, createOrUpdateIndex, deleteIndex, fromAzureScoreToRelevanceScore, fromAzureScoreToRelevanceScore, getEmbeddingMatches, initialize, remove, removeAll, removeAll, removeAll, search

Methods inherited from class java.lang.Object

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

Methods inherited from interface dev.langchain4j.store.embedding.EmbeddingStore

findRelevant, findRelevant, findRelevant, findRelevant

Constructor Details

AzureAiSearchContentRetriever

public AzureAiSearchContentRetriever(String endpoint,
 com.azure.core.credential.AzureKeyCredential keyCredential,
 com.azure.core.credential.TokenCredential tokenCredential,
 boolean createOrUpdateIndex,
 int dimensions,
 com.azure.search.documents.indexes.models.SearchIndex index,
 String indexName,
 EmbeddingModel embeddingModel,
 int maxResults,
 double minScore,
 AzureAiSearchQueryType azureAiSearchQueryType,
 AzureAiSearchFilterMapper filterMapper,
 Filter filter)

Method Details

add

public void add(String content)

Add content to the full text search engine.

add

public void add(Document document)

Add Document to the full text search engine.

add

public void add(TextSegment segment)

Add TextSegment to the full text search engine.

add

public void add(List<TextSegment> segments)

Add a list of TextSegments to the full text search engine.

retrieve

public List<Content> retrieve(Query query)

Description copied from interface: ContentRetriever

Retrieves relevant Contents using a given Query. The Contents are sorted by relevance, with the most relevant Contents appearing at the beginning of the returned List<Content>.

Specified by:

retrieve in interface ContentRetriever

Parameters:

query - The Query to use for retrieval.

Returns:

A list of retrieved Contents.

builder

public static AzureAiSearchContentRetriever.Builder builder()