Package dev.langchain4j.model.embedding.onnx.bgesmallenq

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, dev.langchain4j.model.embedding.TokenCountEstimator

public class BgeSmallEnQuantizedEmbeddingModel
extends 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
BgeSmallEnQuantizedEmbeddingModel()	Creates an instance of an BgeSmallEnQuantizedEmbeddingModel.
BgeSmallEnQuantizedEmbeddingModel(Executor executor)	Creates an instance of an BgeSmallEnQuantizedEmbeddingModel.

Method Summary

Modifier and Type	Method	Description
protected Integer	knownDimension()
protected OnnxBertBiEncoder	model()

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

embedAll, estimateTokenCount, loadFromJar

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

dimension

Methods inherited from class java.lang.Object

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

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

embed, embed

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

estimateTokenCount, estimateTokenCount

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 OnnxBertBiEncoder model()

Specified by:

model in class AbstractInProcessEmbeddingModel

knownDimension

protected Integer knownDimension()

Overrides:

knownDimension in class dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel