Package dev.langchain4j.store.embedding

Interface EmbeddingStore<Embedded>

Type Parameters:
Embedded - The class of the object that has been embedded. Typically, this is TextSegment.
All Known Implementing Classes:
AbstractAzureAiSearchEmbeddingStore, AstraDbEmbeddingStore, AzureAiSearchContentRetriever, AzureAiSearchEmbeddingStore, AzureCosmosDbMongoVCoreEmbeddingStore, AzureCosmosDbNoSqlEmbeddingStore, CassandraEmbeddingStore, ChromaEmbeddingStore, CoherenceEmbeddingStore, CouchbaseEmbeddingStore, ElasticsearchEmbeddingStore, InfinispanEmbeddingStore, InMemoryEmbeddingStore, MilvusEmbeddingStore, MongoDbEmbeddingStore, Neo4jEmbeddingStore, OpenSearchEmbeddingStore, OracleEmbeddingStore, PgVectorEmbeddingStore, PineconeEmbeddingStore, QdrantEmbeddingStore, RedisEmbeddingStore, TablestoreEmbeddingStore, VespaEmbeddingStore, WeaviateEmbeddingStore
public interface EmbeddingStore<Embedded>
Represents a store for embeddings, also known as a vector database.

  • Method Details

    • add

      String add(Embedding embedding)
      Adds a given embedding to the store.
      Parameters:
      embedding - The embedding to be added to the store.
      Returns:
      The auto-generated ID associated with the added embedding.

    • add

      void add(String id, Embedding embedding)
      Adds a given embedding to the store.
      Parameters:
      id - The unique identifier for the embedding to be added.
      embedding - The embedding to be added to the store.

    • add

      String add(Embedding embedding, Embedded embedded)
      Adds a given embedding and the corresponding content that has been embedded to the store.
      Parameters:
      embedding - The embedding to be added to the store.
      embedded - Original content that was embedded.
      Returns:
      The auto-generated ID associated with the added embedding.

    • addAll

      List<String> addAll(List<Embedding> embeddings)
      Adds multiple embeddings to the store.
      Parameters:
      embeddings - A list of embeddings to be added to the store.
      Returns:
      A list of auto-generated IDs associated with the added embeddings.

    • addAll

      default List<String> addAll(List<Embedding> embeddings, List<Embedded> embedded)
      Adds multiple embeddings and their corresponding contents that have been embedded to the store.
      Parameters:
      embeddings - A list of embeddings to be added to the store.
      embedded - A list of original contents that were embedded.
      Returns:
      A list of auto-generated IDs associated with the added embeddings.

    • addAll

      default void addAll(List<String> ids, List<Embedding> embeddings, List<Embedded> embedded)
      Adds multiple embeddings and their corresponding contents that have been embedded to the store.
      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.

    • remove

      default void remove(String id)
      Removes a single embedding from the store by ID.
      Parameters:
      id - The unique ID of the embedding to be removed.

    • removeAll

      default void removeAll(Collection<String> ids)
      Removes all embeddings that match the specified IDs from the store.
      Parameters:
      ids - A collection of unique IDs of the embeddings to be removed.

    • removeAll

      default void removeAll(Filter filter)
      Removes all embeddings that match the specified Filter from the store.
      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

      default void removeAll()
      Removes all embeddings from the store.

    • generateIds

      default List<String> generateIds(int n)
      Generates list of UUID strings
      Parameters:
      n - - dimension of list

    • search

      default EmbeddingSearchResult<Embedded> search(EmbeddingSearchRequest request)
      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.
      Parameters:
      request - A request to search in an EmbeddingStore. Contains all search criteria.
      Returns:
      An EmbeddingSearchResult containing all found Embeddings.

    • findRelevant

      @Deprecated(forRemoval=true) default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults)
      Deprecated, for removal: This API element is subject to removal in a future version.
      as of 0.31.0, use search(EmbeddingSearchRequest) instead.
      Finds the most relevant (closest in space) embeddings to the provided reference embedding. By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
      Parameters:
      referenceEmbedding - The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
      maxResults - The maximum number of embeddings to be returned.
      Returns:
      A list of embedding matches. Each embedding match includes a relevance score (derivative of cosine distance), ranging from 0 (not relevant) to 1 (highly relevant).

    • findRelevant

      @Deprecated(forRemoval=true) default List<EmbeddingMatch<Embedded>> findRelevant(Embedding referenceEmbedding, int maxResults, double minScore)
      Deprecated, for removal: This API element is subject to removal in a future version.
      as of 0.31.0, use search(EmbeddingSearchRequest) instead.
      Finds the most relevant (closest in space) embeddings to the provided reference embedding.
      Parameters:
      referenceEmbedding - The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
      maxResults - The maximum number of embeddings to be returned.
      minScore - The minimum relevance score, ranging from 0 to 1 (inclusive). Only embeddings with a score of this value or higher will be returned.
      Returns:
      A list of embedding matches. Each embedding match includes a relevance score (derivative of cosine distance), ranging from 0 (not relevant) to 1 (highly relevant).

    • findRelevant

      @Deprecated(forRemoval=true) default List<EmbeddingMatch<Embedded>> findRelevant(Object memoryId, Embedding referenceEmbedding, int maxResults)
      Deprecated, for removal: This API element is subject to removal in a future version.
      as of 0.31.0, use search(EmbeddingSearchRequest) instead.
      Finds the most relevant (closest in space) embeddings to the provided reference embedding. By default, minScore is set to 0, which means that the results may include embeddings with low relevance.
      Parameters:
      memoryId - The memoryId used Distinguishing query requests from different users.
      referenceEmbedding - The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
      maxResults - The maximum number of embeddings to be returned.
      Returns:
      A list of embedding matches. Each embedding match includes a relevance score (derivative of cosine distance), ranging from 0 (not relevant) to 1 (highly relevant).

    • findRelevant

      @Deprecated(forRemoval=true) default List<EmbeddingMatch<Embedded>> findRelevant(Object memoryId, Embedding referenceEmbedding, int maxResults, double minScore)
      Deprecated, for removal: This API element is subject to removal in a future version.
      as of 0.31.0, use search(EmbeddingSearchRequest) instead.
      Finds the most relevant (closest in space) embeddings to the provided reference embedding.
      Parameters:
      memoryId - The memoryId used Distinguishing query requests from different users.
      referenceEmbedding - The embedding used as a reference. Returned embeddings should be relevant (closest) to this one.
      maxResults - The maximum number of embeddings to be returned.
      minScore - The minimum relevance score, ranging from 0 to 1 (inclusive). Only embeddings with a score of this value or higher will be returned.
      Returns:
      A list of embedding matches. Each embedding match includes a relevance score (derivative of cosine distance), ranging from 0 (not relevant) to 1 (highly relevant).