Class OpenSearchEmbeddingStore

java.lang.Object
dev.langchain4j.store.embedding.opensearch.OpenSearchEmbeddingStore
All Implemented Interfaces:
EmbeddingStore<TextSegment>
public class OpenSearchEmbeddingStore extends Object implements EmbeddingStore<TextSegment>
Represents an OpenSearch index as an embedding store. This implementation uses K-NN and the cosinesimil space type.

  • Constructor Details

    • OpenSearchEmbeddingStore

      public OpenSearchEmbeddingStore(String serverUrl, String apiKey, String userName, String password, String indexName)
      Creates an instance of OpenSearchEmbeddingStore to connect with OpenSearch clusters running locally and network reachable.
      Parameters:
      serverUrl - OpenSearch Server URL.
      apiKey - OpenSearch API key (optional)
      userName - OpenSearch username (optional)
      password - OpenSearch password (optional)
      indexName - OpenSearch index name.

    • OpenSearchEmbeddingStore

      public OpenSearchEmbeddingStore(String serverUrl, String serviceName, String region, org.opensearch.client.transport.aws.AwsSdk2TransportOptions options, String indexName)
      Creates an instance of OpenSearchEmbeddingStore to connect with OpenSearch clusters running as a fully managed service at AWS.
      Parameters:
      serverUrl - OpenSearch Server URL.
      serviceName - The AWS signing service name, one of `es` (Amazon OpenSearch) or `aoss` (Amazon OpenSearch Serverless).
      region - The AWS region for which requests will be signed. This should typically match the region in `serverUrl`.
      options - The options to establish connection with the service. It must include which credentials should be used.
      indexName - OpenSearch index name.

    • OpenSearchEmbeddingStore

      public OpenSearchEmbeddingStore(org.opensearch.client.opensearch.OpenSearchClient openSearchClient, String indexName)
      Creates an instance of OpenSearchEmbeddingStore using provided OpenSearchClient
      Parameters:
      openSearchClient - OpenSearch client provided
      indexName - OpenSearch index name.

  • Method Details

    • builder

      public static OpenSearchEmbeddingStore.Builder builder()

    • 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(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 request)
      This implementation uses the exact k-NN with scoring script to calculate See https://opensearch.org/docs/latest/search-plugins/knn/knn-score-script/
      Specified by:
      search in interface EmbeddingStore<TextSegment>
      Parameters:
      request - A request to search in an EmbeddingStore. Contains all search criteria.
      Returns:
      An EmbeddingSearchResult containing all found Embeddings.

    • 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.

    • 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 OpenSearch implementation will simply drop the index instead of removing all documents one by one.
      Specified by:
      removeAll in interface EmbeddingStore<TextSegment>