Class AbstractElasticsearchEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.elasticsearch.AbstractElasticsearchEmbeddingStore

All Implemented Interfaces:

dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

Direct Known Subclasses:

ElasticsearchContentRetriever, ElasticsearchEmbeddingStore

public abstract class AbstractElasticsearchEmbeddingStore
extends Object
implements dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

Represents an Elasticsearch index as an embedding store.

See Also:

• for the exact brute force implementation (slower - 100% accurate)
• for the knn search implementation (faster - approximative)
• for full text search (non vector)
• for hybrid search (semantic and text search combined)
  Supports storing Metadata and filtering by it using Filter (provided inside EmbeddingSearchRequest).

Field Summary

Fields

Modifier and Type	Field	Description
protected co.elastic.clients.elasticsearch.ElasticsearchClient	client
protected ElasticsearchConfiguration	configuration
protected String	indexName

Constructor Summary

Constructors

Constructor	Description
AbstractElasticsearchEmbeddingStore()

Method Summary

Modifier and Type	Method	Description
String	add(dev.langchain4j.data.embedding.Embedding embedding)
String	add(dev.langchain4j.data.embedding.Embedding embedding, dev.langchain4j.data.segment.TextSegment textSegment)
String	add(String text)
void	add(String id, dev.langchain4j.data.embedding.Embedding embedding)
void	add(String id, String text)
List<String>	addAll(List<dev.langchain4j.data.embedding.Embedding> embeddings)
void	addAll(List<String> ids, List<dev.langchain4j.data.embedding.Embedding> embeddings, List<dev.langchain4j.data.segment.TextSegment> embedded)
List<String>	addAllText(List<String> texts)
List<dev.langchain4j.data.segment.TextSegment>	fullTextSearch(String textQuery)
dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment>	hybridSearch(dev.langchain4j.store.embedding.EmbeddingSearchRequest embeddingSearchRequest, String textQuery)
protected void	initialize(ElasticsearchConfiguration configuration, co.elastic.clients.elasticsearch.ElasticsearchClient client, String indexName)	Initialize using an ElasticsearchClient
protected void	initialize(ElasticsearchConfiguration configuration, org.elasticsearch.client.RestClient restClient, String indexName)	Deprecated, for removal: This API element is subject to removal in a future version. Use now initialize(ElasticsearchConfiguration, ElasticsearchClient, String)
void	removeAll()	The Elasticsearch implementation will simply drop the index instead of removing all documents one by one.
void	removeAll(dev.langchain4j.store.embedding.filter.Filter filter)
void	removeAll(Collection<String> ids)
dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment>	search(dev.langchain4j.store.embedding.EmbeddingSearchRequest embeddingSearchRequest)

Methods inherited from class Object

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

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

addAll, addListener, addListeners, generateIds, remove

Field Details

configuration

protected ElasticsearchConfiguration configuration

client

protected co.elastic.clients.elasticsearch.ElasticsearchClient client

indexName

protected String indexName

Constructor Details

AbstractElasticsearchEmbeddingStore

public AbstractElasticsearchEmbeddingStore()

Method Details

initialize

@Deprecated(forRemoval=true)
protected void initialize(ElasticsearchConfiguration configuration,
 org.elasticsearch.client.RestClient restClient,
 String indexName)

Deprecated, for removal: This API element is subject to removal in a future version.

Use now initialize(ElasticsearchConfiguration, ElasticsearchClient, String)

Initialize using a RestClient

Parameters:

configuration - Elasticsearch configuration to use (Knn, Script, FullText or Hybrid)

restClient - Elasticsearch Rest Client (mandatory)

indexName - Elasticsearch index name (optional). Default value: "default". Index will be created automatically if not exists.

initialize

protected void initialize(ElasticsearchConfiguration configuration,
 co.elastic.clients.elasticsearch.ElasticsearchClient client,
 String indexName)

Initialize using an ElasticsearchClient

Parameters:

configuration - Elasticsearch configuration to use (Knn or Script)

client - Elasticsearch Client (mandatory)

indexName - Elasticsearch index name (optional). Default value: "default". Index will be created automatically if not exists.

add

public String add(dev.langchain4j.data.embedding.Embedding embedding)

Specified by:

add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

add

public void add(String id,
 dev.langchain4j.data.embedding.Embedding embedding)

Specified by:

add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

add

public String add(String text)

add

public void add(String id,
 String text)

addAllText

public List<String> addAllText(List<String> texts)

add

public String add(dev.langchain4j.data.embedding.Embedding embedding,
 dev.langchain4j.data.segment.TextSegment textSegment)

Specified by:

add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

addAll

public List<String> addAll(List<dev.langchain4j.data.embedding.Embedding> embeddings)

Specified by:

addAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

search

public dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment> search(dev.langchain4j.store.embedding.EmbeddingSearchRequest embeddingSearchRequest)

Specified by:

search in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

hybridSearch

public dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment> hybridSearch(dev.langchain4j.store.embedding.EmbeddingSearchRequest embeddingSearchRequest,
 String textQuery)

fullTextSearch

public List<dev.langchain4j.data.segment.TextSegment> fullTextSearch(String textQuery)

removeAll

public void removeAll(Collection<String> ids)

Specified by:

removeAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

removeAll

public void removeAll(dev.langchain4j.store.embedding.filter.Filter filter)

Specified by:

removeAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

removeAll

public void removeAll()

The Elasticsearch implementation will simply drop the index instead of removing all documents one by one.

Specified by:

removeAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

addAll

public void addAll(List<String> ids,
 List<dev.langchain4j.data.embedding.Embedding> embeddings,
 List<dev.langchain4j.data.segment.TextSegment> embedded)

Specified by:

addAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>