dev.langchain4j.model.embedding

Class E5SmallV2QuantizedEmbeddingModel

java.lang.Object

dev.langchain4j.model.embedding.AbstractInProcessEmbeddingModel

dev.langchain4j.model.embedding.E5SmallV2QuantizedEmbeddingModel

All Implemented Interfaces:

EmbeddingModel, TokenCountEstimator

public class E5SmallV2QuantizedEmbeddingModel
extends AbstractInProcessEmbeddingModel

Quantized Microsoft E5-small-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 512 tokens long.

Embedding dimensions: 384

It is recommended to use the "query:" prefix for queries and the "passage:" prefix for segments.

More details here

Constructor Summary

Constructors

Constructor and Description
E5SmallV2QuantizedEmbeddingModel()

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

E5SmallV2QuantizedEmbeddingModel

public E5SmallV2QuantizedEmbeddingModel()

Method Detail

model

protected OnnxBertBiEncoder model()

Specified by:

model in class AbstractInProcessEmbeddingModel