Class OracleEmbeddingModel

java.lang.Object
dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel
dev.langchain4j.model.oracle.OracleEmbeddingModel
All Implemented Interfaces:
EmbeddingModel

public class OracleEmbeddingModel extends DimensionAwareEmbeddingModel
Embed documents Use dbms_vector_chain.utl_to_embeddings to get embeddings. You can specify which provider to use such as an ONNX model or a third-party provider via a REST call. Some example preferences To use an ONNX model: { "provider": "database", "model": "database" } To use a third-party provider: { "provider": "ocigenai", "credential_name": "OCI_CRED", "url": "https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/embedText", "model": "cohere.embed-english-light-v3.0" }
  • Constructor Details

    • OracleEmbeddingModel

      public OracleEmbeddingModel(Connection conn, String pref)
      Create an embedding model
    • OracleEmbeddingModel

      public OracleEmbeddingModel(Connection conn, String pref, String proxy)
      Create an embedding model with a proxy
  • Method Details

    • setBatching

      public void setBatching(boolean batching)
    • getBatching

      public boolean getBatching()
    • loadOnnxModel

      public static boolean loadOnnxModel(Connection conn, String dir, String onnxFile, String modelName) throws SQLException
      load an ONNX model located on the server into the database
      Parameters:
      conn - connection
      dir - directory alias from create directory
      onnxFile - ONNX file
      modelName - model name
      Throws:
      SQLException
    • embedAll

      public Response<List<Embedding>> embedAll(List<TextSegment> textSegments)
      get embeddings for a list of text segments
      Parameters:
      textSegments - the text segments to embed.
      Returns:
      the embeddings.