Package io.quarkiverse.langchain4j.infinispan.runtime

Interface InfinispanEmbeddingStoreConfig

@ConfigRoot(phase=RUN_TIME) @ConfigMapping(prefix="quarkus.langchain4j.infinispan") public interface InfinispanEmbeddingStoreConfig
Configuration of the Infinispan embedding store.

  • Method Summary

    Modifier and Type
    Method
    Description
    String
    cacheName()
    Name of the cache that will be used in Infinispan when searching for related embeddings.
    Long
    dimension()
    The dimension of the embedding vectors.
    Integer
    distance()
    The maximum distance.

  • Method Details

    • dimension

      Long dimension()
      The dimension of the embedding vectors. This has to be the same as the dimension of vectors produced by the embedding model that you use. For example, AllMiniLmL6V2QuantizedEmbeddingModel produces vectors of dimension 384. OpenAI's text-embedding-ada-002 produces vectors of dimension 1536.

    • cacheName

      @WithDefault("embeddings-cache") String cacheName()
      Name of the cache that will be used in Infinispan when searching for related embeddings. If this cache doesn't exist, it will be created.

    • distance

      @WithDefault("3") Integer distance()
      The maximum distance. The most distance between vectors is how close or far apart two embeddings are.