Package dev.langchain4j.model.vertexai

Class VertexAiEmbeddingModel

java.lang.Object

dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel

dev.langchain4j.model.vertexai.VertexAiEmbeddingModel

All Implemented Interfaces:

dev.langchain4j.model.embedding.EmbeddingModel

public class VertexAiEmbeddingModel
extends dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel

Represents a Google Vertex AI embedding model, such as textembedding-gecko. See details here.

This embedding model transparently handles call batching, however the underlying API has imposes a maximum of 250 embeddings per call, with a max of 20,000 tokens per call. You can tweak those two parameters with the maxSegmentsPerBatch() and maxTokensPerBatch() builder methods. For example, if you hit the 20,000 error, set maxTokensPerBatch(18_000).

For authentication and authorization, please follow these steps before using this model:
1. Authentication
When developing locally, you can use one of:
a) Google Cloud SDK
b) Service account When using service account, ensure that GOOGLE_APPLICATION_CREDENTIALS environment variable points to your JSON service account key.
2. Authorization
3. Prerequisites

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	VertexAiEmbeddingModel.Builder
static enum	VertexAiEmbeddingModel.TaskType

Field Summary

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

dimension

Constructor Summary

Constructors

Constructor	Description
VertexAiEmbeddingModel(String endpoint, String project, String location, String publisher, String modelName, Integer maxRetries, Integer maxSegmentsPerBatch, Integer maxTokensPerBatch, VertexAiEmbeddingModel.TaskType taskType, String titleMetadataKey, Integer outputDimensionality, Boolean autoTruncate)

Method Summary

Modifier and Type	Method	Description
static VertexAiEmbeddingModel.Builder	builder()
List<Integer>	calculateTokensCounts(List<dev.langchain4j.data.segment.TextSegment> segments)	Calculates the number of tokens for each segment in the input list.
dev.langchain4j.model.output.Response<List<dev.langchain4j.data.embedding.Embedding>>	embedAll(List<dev.langchain4j.data.segment.TextSegment> segments)
protected Integer	knownDimension()

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

Constructor Details

VertexAiEmbeddingModel

public VertexAiEmbeddingModel(String endpoint,
 String project,
 String location,
 String publisher,
 String modelName,
 Integer maxRetries,
 Integer maxSegmentsPerBatch,
 Integer maxTokensPerBatch,
 VertexAiEmbeddingModel.TaskType taskType,
 String titleMetadataKey,
 Integer outputDimensionality,
 Boolean autoTruncate)

Method Details

embedAll

public dev.langchain4j.model.output.Response<List<dev.langchain4j.data.embedding.Embedding>> embedAll(List<dev.langchain4j.data.segment.TextSegment> segments)

calculateTokensCounts

public List<Integer> calculateTokensCounts(List<dev.langchain4j.data.segment.TextSegment> segments)

Calculates the number of tokens for each segment in the input list.

Parameters:

segments - a list of TextSegments

Returns:

a list of tokens counts for each segment

knownDimension

protected Integer knownDimension()

Overrides:

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

builder

public static VertexAiEmbeddingModel.Builder builder()