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 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(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)

    • fullTextSearchMatches

      @Deprecated(forRemoval=true) public List<EmbeddingMatch<TextSegment>> fullTextSearchMatches(String textQuery)
      Deprecated, for removal: This API element is subject to removal in a future version.
      Use fullTextSearchMatches(FullTextSearchRequest) instead. It also applies the maxResults, minScore and filter of the request.
      Searches the index with a full text (non-vector) query.
      Parameters:
      textQuery - the text to search for
      Returns:
      the matching documents, each carrying its Elasticsearch document ID and relevance score

    • fullTextSearchMatches

      public List<EmbeddingMatch<TextSegment>> fullTextSearchMatches(FullTextSearchRequest request)
      Searches the index with a full text (non-vector) query.
      Parameters:
      request - the full text search request
      Returns:
      the matching documents, each carrying its Elasticsearch document ID and relevance score

    • fullTextSearch

      @Deprecated(forRemoval=true) public List<TextSegment> fullTextSearch(String textQuery)
      Deprecated, for removal: This API element is subject to removal in a future version.
      Use fullTextSearchMatches(FullTextSearchRequest) instead. It returns the same text segments, but also the Elasticsearch document ID and the relevance score of each match.

    • removeAll

      public void removeAll(Collection<String> ids)
      Description copied from interface: EmbeddingStore
      Removes all embeddings that match the specified IDs from the store.

      Having nothing to remove is a no-op: an empty or null collection of IDs leaves the store unchanged and throws nothing, in the same way that adding no embeddings stores nothing.

      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.

      The lists are positional: the i-th ID, the i-th embedding and the i-th embedded content belong together. ids and embeddings must therefore have the same size, and embedded, when provided, must have that size as well. A null list of IDs or embeddings counts as an empty list, so passing embeddings without IDs (or the other way around) is a size mismatch, not an empty input. ValidationUtils.ensureConsistentSizes(List, List, List) implements these rules and should be used by implementations.

      Passing no embeddings at all (an empty or null embeddings together with an empty or null ids, and no embedded contents) is a no-op: nothing is stored and no exception is thrown.

      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, or null if they were not provided.