Class BgeSmallEnQuantizedEmbeddingModel

java.lang.Object
dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel
dev.langchain4j.model.embedding.onnx.AbstractInProcessEmbeddingModel
dev.langchain4j.model.embedding.onnx.bgesmallenq.BgeSmallEnQuantizedEmbeddingModel
All Implemented Interfaces:
dev.langchain4j.model.embedding.EmbeddingModel

public class BgeSmallEnQuantizedEmbeddingModel extends dev.langchain4j.model.embedding.onnx.AbstractInProcessEmbeddingModel
Quantized BAAI bge-small-en embedding model that runs within your Java application's process.

Maximum length of text (in tokens) that can be embedded at once: unlimited. However, while you can embed very long texts, the quality of the embedding degrades as the text lengthens. It is recommended to embed segments of no more than 512 tokens long.

Embedding dimensions: 384

It is recommended to add "Represent this sentence for searching relevant passages:" prefix to a query.

Uses an Executor to parallelize the embedding process. By default, uses a cached thread pool with the number of threads equal to the number of available processors. Threads are cached for 1 second.

More details here

  • Field Summary

    Fields inherited from class dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel

    dimension
  • Constructor Summary

    Constructors
    Constructor
    Description
    Creates an instance of an BgeSmallEnQuantizedEmbeddingModel.
    Creates an instance of an BgeSmallEnQuantizedEmbeddingModel.
  • Method Summary

    Modifier and Type
    Method
    Description
    protected Integer
     
    protected dev.langchain4j.model.embedding.onnx.OnnxBertBiEncoder
     

    Methods inherited from class dev.langchain4j.model.embedding.onnx.AbstractInProcessEmbeddingModel

    embedAll, loadFromJar

    Methods inherited from class dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel

    dimension

    Methods inherited from class Object

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

    Methods inherited from interface dev.langchain4j.model.embedding.EmbeddingModel

    addListener, addListeners, embed, embed, modelName
  • Constructor Details

    • BgeSmallEnQuantizedEmbeddingModel

      public BgeSmallEnQuantizedEmbeddingModel()
      Creates an instance of an BgeSmallEnQuantizedEmbeddingModel. Uses a cached thread pool with the number of threads equal to the number of available processors. Threads are cached for 1 second.
    • BgeSmallEnQuantizedEmbeddingModel

      public BgeSmallEnQuantizedEmbeddingModel(Executor executor)
      Creates an instance of an BgeSmallEnQuantizedEmbeddingModel.
      Parameters:
      executor - The executor to use to parallelize the embedding process.
  • Method Details

    • model

      protected dev.langchain4j.model.embedding.onnx.OnnxBertBiEncoder model()
      Specified by:
      model in class dev.langchain4j.model.embedding.onnx.AbstractInProcessEmbeddingModel
    • knownDimension

      protected Integer knownDimension()
      Overrides:
      knownDimension in class dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel