Package io.quarkiverse.langchain4j.neo4j.runtime

Interface Neo4jRuntimeConfig

@ConfigRoot(phase=RUN_TIME) @ConfigMapping(prefix="quarkus.langchain4j.neo4j") public interface Neo4jRuntimeConfig

  • Method Details

    • dimension

      Integer dimension()
      Dimension of the embeddings that will be stored in the Neo4j store.

    • label

      @WithDefault("Document") String label()
      Label for the created nodes.

    • embeddingProperty

      @WithDefault("embedding") String embeddingProperty()
      Name of the property to store the embedding vectors.

    • idProperty

      @WithDefault("id") String idProperty()
      Name of the property to store embedding IDs.

    • metadataPrefix

      Optional<String> metadataPrefix()
      Prefix to be added to the metadata keys. By default, no prefix is used.

    • textProperty

      @WithDefault("text") String textProperty()
      Name of the property to store the embedding text.

    • indexName

      @WithDefault("vector") String indexName()
      Name of the index to be created for vector search.

    • databaseName

      @WithDefault("neo4j") String databaseName()
      Name of the database to connect to.

    • retrievalQuery

      @WithDefault("RETURN properties(node) AS metadata, node.${quarkus.langchain4j.neo4j.id-property} AS ${quarkus.langchain4j.neo4j.id-property}, node.${quarkus.langchain4j.neo4j.text-property} AS ${quarkus.langchain4j.neo4j.text-property}, node.${quarkus.langchain4j.neo4j.embedding-property} AS ${quarkus.langchain4j.neo4j.embedding-property}, score") String retrievalQuery()
      The query to use when retrieving embeddings. This query has to return the following columns:
      • metadata
      • score
      • column of the same name as the 'id-property' value
      • column of the same name as the 'text-property' value
      • column of the same name as the 'embedding-property' value