dev.langchain4j.model.embedding.onnx.allminilml6v2

Class AllMiniLmL6V2EmbeddingModel

java.lang.Object

dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel

dev.langchain4j.model.embedding.onnx.AbstractInProcessEmbeddingModel

dev.langchain4j.model.embedding.onnx.allminilml6v2.AllMiniLmL6V2EmbeddingModel

All Implemented Interfaces:

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

public class AllMiniLmL6V2EmbeddingModel
extends AbstractInProcessEmbeddingModel

SentenceTransformers all-MiniLM-L6-v2 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 256 tokens.

Embedding dimensions: 384

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 and here

Field Summary

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

dimension

Constructor Summary

Constructors

Constructor and Description
AllMiniLmL6V2EmbeddingModel() Creates an instance of an AllMiniLmL6V2EmbeddingModel.
AllMiniLmL6V2EmbeddingModel(Executor executor) Creates an instance of an AllMiniLmL6V2EmbeddingModel.

Method Summary

Modifier and Type	Method and 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.TokenCountEstimator

estimateTokenCount, estimateTokenCount

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

embed, embed

Constructor Detail

AllMiniLmL6V2EmbeddingModel

public AllMiniLmL6V2EmbeddingModel()

Creates an instance of an AllMiniLmL6V2EmbeddingModel. Uses a cached thread pool with the number of threads equal to the number of available processors.

AllMiniLmL6V2EmbeddingModel

public AllMiniLmL6V2EmbeddingModel(Executor executor)

Creates an instance of an AllMiniLmL6V2EmbeddingModel.

Parameters:

executor - The executor to use to parallelize the embedding process.

Method Detail

model

protected OnnxBertBiEncoder model()

Specified by:

model in class AbstractInProcessEmbeddingModel

knownDimension

protected Integer knownDimension()

Overrides:

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