Class CassandraEmbeddingStore

java.lang.Object
dev.langchain4j.store.embedding.cassandra.CassandraEmbeddingStore
All Implemented Interfaces:
dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
public class CassandraEmbeddingStore extends Object implements dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
Implementation of EmbeddingStore using Cassandra.
See Also:
  • EmbeddingStore
  • MetadataVectorTable

  • Nested Class Summary

    Nested Classes
    Modifier and Type
    Class
    Description
    static class 
    CassandraEmbeddingStore.Builder
     
    static class 
    CassandraEmbeddingStore.BuilderAstra
     

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    protected com.datastax.oss.driver.api.core.CqlSession
    cassandraSession
    Cassandra question.
    protected com.dtsx.astra.sdk.cassio.MetadataVectorTable
    embeddingTable
    Represents an embedding table in Cassandra, it is a table with a vector column.

  • Constructor Summary

    Constructors
    Constructor
    Description
    CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension)
    Embedding Store.
    CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension, com.dtsx.astra.sdk.cassio.CassandraSimilarityMetric metric)
    Embedding Store.

  • Method Summary

    Modifier and Type
    Method
    Description
    String
    add(@NonNull dev.langchain4j.data.embedding.Embedding embedding)
    Add a new embedding to the store. - the row id is generated - text and metadata are not stored
    String
    add(@NonNull dev.langchain4j.data.embedding.Embedding embedding, dev.langchain4j.data.segment.TextSegment textSegment)
    Add a new embedding to the store. - the row id is generated - text and metadata coming from the text Segment
    void
    add(@NonNull String rowId, @NonNull dev.langchain4j.data.embedding.Embedding embedding)
    Add a new embedding to the store.
    List<String>
    addAll(List<dev.langchain4j.data.embedding.Embedding> embeddingList)
    Add multiple embeddings as a single action.
    void
    addAll(List<String> ids, List<dev.langchain4j.data.embedding.Embedding> embeddingList, List<dev.langchain4j.data.segment.TextSegment> textSegmentList)
     
    static CassandraEmbeddingStore.Builder
    builder()
     
    static CassandraEmbeddingStore.BuilderAstra
    builderAstra()
     
    void
    clear()
    Delete all rows.
    void
    delete()
    Delete the table.
    List<dev.langchain4j.store.embedding.EmbeddingMatch<dev.langchain4j.data.segment.TextSegment>>
    findRelevant(dev.langchain4j.data.embedding.Embedding embedding, int maxResults, double minScore)
     
    List<dev.langchain4j.store.embedding.EmbeddingMatch<dev.langchain4j.data.segment.TextSegment>>
    findRelevant(dev.langchain4j.data.embedding.Embedding embedding, int maxResults, double minScore, dev.langchain4j.data.document.Metadata metadata)
    Similarity Search ANN based on the embedding.
    com.datastax.oss.driver.api.core.CqlSession
    getCassandraSession()
     
    dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment>
    search(dev.langchain4j.store.embedding.EmbeddingSearchRequest request)
     

    Methods inherited from class Object

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

    Methods inherited from interface dev.langchain4j.store.embedding.EmbeddingStore

    addAll, addListener, addListeners, generateIds, remove, removeAll, removeAll, removeAll

  • Field Details

    • embeddingTable

      protected com.dtsx.astra.sdk.cassio.MetadataVectorTable embeddingTable
      Represents an embedding table in Cassandra, it is a table with a vector column.

    • cassandraSession

      protected com.datastax.oss.driver.api.core.CqlSession cassandraSession
      Cassandra question.

  • Constructor Details

    • CassandraEmbeddingStore

      public CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension)
      Embedding Store.
      Parameters:
      session - cassandra Session
      tableName - table name
      dimension - dimension

    • CassandraEmbeddingStore

      public CassandraEmbeddingStore(com.datastax.oss.driver.api.core.CqlSession session, String tableName, int dimension, com.dtsx.astra.sdk.cassio.CassandraSimilarityMetric metric)
      Embedding Store.
      Parameters:
      session - cassandra Session
      tableName - table name
      dimension - dimension
      metric - metric

  • Method Details

    • delete

      public void delete()
      Delete the table.

    • clear

      public void clear()
      Delete all rows.

    • getCassandraSession

      public com.datastax.oss.driver.api.core.CqlSession getCassandraSession()

    • builder

      public static CassandraEmbeddingStore.Builder builder()

    • builderAstra

      public static CassandraEmbeddingStore.BuilderAstra builderAstra()

    • add

      public String add(@NonNull dev.langchain4j.data.embedding.Embedding embedding)
      Add a new embedding to the store. - the row id is generated - text and metadata are not stored
      Specified by:
      add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
      Parameters:
      embedding - representation of the list of floats
      Returns:
      newly created row id

    • add

      public String add(@NonNull dev.langchain4j.data.embedding.Embedding embedding, dev.langchain4j.data.segment.TextSegment textSegment)
      Add a new embedding to the store. - the row id is generated - text and metadata coming from the text Segment
      Specified by:
      add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
      Parameters:
      embedding - representation of the list of floats
      textSegment - text content and metadata
      Returns:
      newly created row id

    • add

      public void add(@NonNull String rowId, @NonNull dev.langchain4j.data.embedding.Embedding embedding)
      Add a new embedding to the store.
      Specified by:
      add in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
      Parameters:
      rowId - the row id
      embedding - representation of the list of floats

    • addAll

      public List<String> addAll(List<dev.langchain4j.data.embedding.Embedding> embeddingList)
      Add multiple embeddings as a single action.
      Specified by:
      addAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>
      Parameters:
      embeddingList - embeddings list
      Returns:
      list of new row if (same order as the input)

    • addAll

      public void addAll(List<String> ids, List<dev.langchain4j.data.embedding.Embedding> embeddingList, List<dev.langchain4j.data.segment.TextSegment> textSegmentList)
      Specified by:
      addAll in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

    • search

      public dev.langchain4j.store.embedding.EmbeddingSearchResult<dev.langchain4j.data.segment.TextSegment> search(dev.langchain4j.store.embedding.EmbeddingSearchRequest request)
      Specified by:
      search in interface dev.langchain4j.store.embedding.EmbeddingStore<dev.langchain4j.data.segment.TextSegment>

    • findRelevant

      public List<dev.langchain4j.store.embedding.EmbeddingMatch<dev.langchain4j.data.segment.TextSegment>> findRelevant(dev.langchain4j.data.embedding.Embedding embedding, int maxResults, double minScore)

    • findRelevant

      public List<dev.langchain4j.store.embedding.EmbeddingMatch<dev.langchain4j.data.segment.TextSegment>> findRelevant(dev.langchain4j.data.embedding.Embedding embedding, int maxResults, double minScore, dev.langchain4j.data.document.Metadata metadata)
      Similarity Search ANN based on the embedding.
      Parameters:
      embedding - vector
      maxResults - max number of results
      minScore - score minScore
      metadata - map key-value to build a metadata filter
      Returns:
      list of matching results