dev.langchain4j.model.embedding

Class OnnxEmbeddingModel

java.lang.Object

dev.langchain4j.model.embedding.AbstractInProcessEmbeddingModel

dev.langchain4j.model.embedding.OnnxEmbeddingModel

All Implemented Interfaces:

dev.langchain4j.model.embedding.EmbeddingModel, dev.langchain4j.model.embedding.TokenCountEstimator

public class OnnxEmbeddingModel
extends AbstractInProcessEmbeddingModel

An embedding model that runs within your Java application's process. Any BERT-based model (e.g., from HuggingFace) can be used, as long as it is in ONNX format. Information on how to convert models into ONNX format can be found here. Many models already converted to ONNX format are available here.

Constructor Summary

Constructors

Constructor and Description
OnnxEmbeddingModel(Path pathToModel)
OnnxEmbeddingModel(String pathToModel)

Method Summary

Modifier and Type	Method and Description
protected OnnxBertBiEncoder	model()

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

embedAll, estimateTokenCount

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 Detail

OnnxEmbeddingModel

public OnnxEmbeddingModel(Path pathToModel)

Parameters:

pathToModel - The path to the .onnx model file (e.g., "/home/me/model.onnx").

OnnxEmbeddingModel

public OnnxEmbeddingModel(String pathToModel)

Parameters:

pathToModel - The path to the .onnx model file (e.g., "/home/me/model.onnx").

Method Detail

model

protected OnnxBertBiEncoder model()

Specified by:

model in class AbstractInProcessEmbeddingModel