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:
-
Field Summary
FieldsModifier and TypeFieldDescriptionprotected co.elastic.clients.elasticsearch.ElasticsearchClientprotected ElasticsearchConfigurationprotected String -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionAdds a given embedding to the store.add(Embedding embedding, TextSegment textSegment) Adds a given embedding and the corresponding content that has been embedded to the store.voidAdds a given embedding to the store.voidAdds multiple embeddings to the store.voidAdds multiple embeddings and their corresponding contents that have been embedded to the store.addAllText(List<String> texts) fullTextSearch(String textQuery) hybridSearch(EmbeddingSearchRequest embeddingSearchRequest, String textQuery) protected voidinitialize(ElasticsearchConfiguration configuration, org.elasticsearch.client.RestClient restClient, String indexName) Initialize using a RestClientvoidThe Elasticsearch implementation will simply drop the index instead of removing all documents one by one.voidRemoves all embeddings that match the specifiedFilterfrom the store.voidremoveAll(Collection<String> ids) Removes all embeddings that match the specified IDs from the store.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, waitMethods inherited from interface EmbeddingStore
addAll, addListener, addListeners, generateIds, remove
-
Field Details
-
configuration
-
client
protected co.elastic.clients.elasticsearch.ElasticsearchClient client -
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
Description copied from interface:EmbeddingStoreAdds a given embedding to the store.- Specified by:
addin interfaceEmbeddingStore<TextSegment>- Parameters:
embedding- The embedding to be added to the store.- Returns:
- The auto-generated ID associated with the added embedding.
-
add
Description copied from interface:EmbeddingStoreAdds a given embedding to the store.- Specified by:
addin interfaceEmbeddingStore<TextSegment>- Parameters:
id- The unique identifier for the embedding to be added.embedding- The embedding to be added to the store.
-
add
-
add
-
addAllText
-
add
Description copied from interface:EmbeddingStoreAdds a given embedding and the corresponding content that has been embedded to the store.- Specified by:
addin interfaceEmbeddingStore<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
Description copied from interface:EmbeddingStoreAdds multiple embeddings to the store.- Specified by:
addAllin interfaceEmbeddingStore<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
Description copied from interface:EmbeddingStoreSearches for the most similar (closest in the embedding space)Embeddings.
All search criteria are defined inside theEmbeddingSearchRequest.
EmbeddingSearchRequest.filter()can be used to filter by various metadata entries (e.g., user/memory ID). Please note that not allEmbeddingStoreimplementations supportFiltering.- Specified by:
searchin interfaceEmbeddingStore<TextSegment>- Parameters:
embeddingSearchRequest- A request to search in anEmbeddingStore. Contains all search criteria.- Returns:
- An
EmbeddingSearchResultcontaining all foundEmbeddings.
-
hybridSearch
public EmbeddingSearchResult<TextSegment> hybridSearch(EmbeddingSearchRequest embeddingSearchRequest, String textQuery) -
fullTextSearch
-
removeAll
Description copied from interface:EmbeddingStoreRemoves all embeddings that match the specified IDs from the store.- Specified by:
removeAllin interfaceEmbeddingStore<TextSegment>- Parameters:
ids- A collection of unique IDs of the embeddings to be removed.
-
removeAll
Description copied from interface:EmbeddingStoreRemoves all embeddings that match the specifiedFilterfrom the store.- Specified by:
removeAllin interfaceEmbeddingStore<TextSegment>- Parameters:
filter- The filter to be applied to theMetadataof theTextSegmentduring removal. Only embeddings whoseTextSegment'sMetadatamatch theFilterwill be removed.
-
removeAll
public void removeAll()The Elasticsearch implementation will simply drop the index instead of removing all documents one by one.- Specified by:
removeAllin interfaceEmbeddingStore<TextSegment>
-
addAll
Description copied from interface:EmbeddingStoreAdds multiple embeddings and their corresponding contents that have been embedded to the store.- Specified by:
addAllin interfaceEmbeddingStore<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.
-