Class AbstractElasticsearchEmbeddingStore

java.lang.Object

dev.langchain4j.store.embedding.elasticsearch.AbstractElasticsearchEmbeddingStore

All Implemented Interfaces:

EmbeddingStore<TextSegment>

Direct Known Subclasses:

ElasticsearchContentRetriever, ElasticsearchEmbeddingStore

public abstract class AbstractElasticsearchEmbeddingStore
extends Object
implements EmbeddingStore<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(Embedding embedding)	Adds a given embedding to the store.
String	add(Embedding embedding, TextSegment textSegment)	Adds a given embedding and the corresponding content that has been embedded to the store.
String	add(String text)
void	add(String id, Embedding embedding)	Adds a given embedding to the store.
void	add(String id, String text)
List<String>	addAll(List<Embedding> embeddings)	Adds multiple embeddings to the store.
void	addAll(List<String> ids, List<Embedding> embeddings, List<TextSegment> embedded)	Adds multiple embeddings and their corresponding contents that have been embedded to the store.
List<String>	addAllText(List<String> texts)
List<TextSegment>	fullTextSearch(String textQuery)
EmbeddingSearchResult<TextSegment>	hybridSearch(EmbeddingSearchRequest embeddingSearchRequest, String textQuery)
protected void	initialize(ElasticsearchConfiguration configuration, org.elasticsearch.client.RestClient restClient, String indexName)	Initialize using a RestClient
void	removeAll()	The Elasticsearch implementation will simply drop the index instead of removing all documents one by one.
void	removeAll(Filter filter)	Removes all embeddings that match the specified Filter from the store.
void	removeAll(Collection<String> ids)	Removes all embeddings that match the specified IDs from the store.
EmbeddingSearchResult<TextSegment>	search(EmbeddingSearchRequest embeddingSearchRequest)	Searches for the most similar (closest in the embedding space) Embeddings.

Methods inherited from class Object

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

Methods inherited from interface 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

protected void initialize(ElasticsearchConfiguration configuration,
 org.elasticsearch.client.RestClient restClient,
 String indexName)

Initialize using a RestClient

Parameters:

configuration - Elasticsearch configuration to use (Knn or Script)

restClient - Elasticsearch Rest Client (mandatory)

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

add

public String add(Embedding embedding)

Description copied from interface: EmbeddingStore

Adds a given embedding to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - The embedding to be added to the store.

Returns:

The auto-generated ID associated with the added embedding.

add

public void add(String id,
 Embedding embedding)

Description copied from interface: EmbeddingStore

Adds a given embedding to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

id - The unique identifier for the embedding to be added.

embedding - The embedding to be added to the store.

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(Embedding embedding,
 TextSegment textSegment)

Description copied from interface: EmbeddingStore

Adds a given embedding and the corresponding content that has been embedded to the store.

Specified by:

add in interface EmbeddingStore<TextSegment>

Parameters:

embedding - The embedding to be added to the store.

textSegment - Original content that was embedded.

Returns:

The auto-generated ID associated with the added embedding.

addAll

public List<String> addAll(List<Embedding> embeddings)

Description copied from interface: EmbeddingStore

Adds multiple embeddings to the store.

Specified by:

addAll in interface EmbeddingStore<TextSegment>

Parameters:

embeddings - A list of embeddings to be added to the store.

Returns:

A list of auto-generated IDs associated with the added embeddings.

search

public EmbeddingSearchResult<TextSegment> search(EmbeddingSearchRequest embeddingSearchRequest)

Description copied from interface: EmbeddingStore

Searches for the most similar (closest in the embedding space) Embeddings.
All search criteria are defined inside the EmbeddingSearchRequest.
EmbeddingSearchRequest.filter() can be used to filter by various metadata entries (e.g., user/memory ID). Please note that not all EmbeddingStore implementations support Filtering.

Specified by:

search in interface EmbeddingStore<TextSegment>

Parameters:

embeddingSearchRequest - A request to search in an EmbeddingStore. Contains all search criteria.

Returns:

An EmbeddingSearchResult containing all found Embeddings.

hybridSearch

public EmbeddingSearchResult<TextSegment> hybridSearch(EmbeddingSearchRequest embeddingSearchRequest,
 String textQuery)

fullTextSearch

public List<TextSegment> fullTextSearch(String textQuery)

removeAll

public void removeAll(Collection<String> ids)

Description copied from interface: EmbeddingStore

Removes all embeddings that match the specified IDs from the store.

Specified by:

removeAll in interface EmbeddingStore<TextSegment>

Parameters:

ids - A collection of unique IDs of the embeddings to be removed.

removeAll

public void removeAll(Filter filter)

Description copied from interface: EmbeddingStore

Removes all embeddings that match the specified Filter from the store.

Specified by:

removeAll in interface EmbeddingStore<TextSegment>

Parameters:

filter - The filter to be applied to the Metadata of the TextSegment during removal. Only embeddings whose TextSegment's Metadata match the Filter will be removed.

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 EmbeddingStore<TextSegment>

addAll

public void addAll(List<String> ids,
 List<Embedding> embeddings,
 List<TextSegment> embedded)

Description copied from interface: EmbeddingStore

Adds multiple embeddings and their corresponding contents that have been embedded to the store.

Specified by:

addAll in interface EmbeddingStore<TextSegment>

Parameters:

ids - A list of IDs associated with the added embeddings.

embeddings - A list of embeddings to be added to the store.

embedded - A list of original contents that were embedded.