tessl/maven-dev-langchain4j--langchain4j-vertex-ai
LangChain4j integration for Google Vertex AI models including chat, language, embedding, image, and scoring capabilities
—
Pending
Quality
Pending
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
overview.mddocs/models/embedding/
Embedding Model Overview
Text embeddings using Google Vertex AI embedding models for semantic search, retrieval, and similarity. Extends LangChain4j DimensionAwareEmbeddingModel.
Class
public class VertexAiEmbeddingModel extends DimensionAwareEmbeddingModel {
public Response<List<Embedding>> embedAll(List<TextSegment> segments);
public String modelName();
public List<Integer> calculateTokensCounts(List<TextSegment> segments);
public static Builder builder();
// Public constants
public static final Integer DEFAULT_MAX_SEGMENTS_PER_BATCH = 250;
public static final Integer DEFAULT_MAX_TOKENS_PER_BATCH = 20000;
}Imports
import dev.langchain4j.model.vertexai.VertexAiEmbeddingModel;
import dev.langchain4j.model.vertexai.VertexAiEmbeddingModel.TaskType;
import dev.langchain4j.model.vertexai.VertexAiEmbeddingModelName;
import dev.langchain4j.data.segment.TextSegment;
import dev.langchain4j.data.embedding.Embedding;
import dev.langchain4j.model.output.Response;Minimal Example
VertexAiEmbeddingModel model = VertexAiEmbeddingModel.builder()
.endpoint("us-central1-aiplatform.googleapis.com:443")
.project("your-project-id")
.location("us-central1")
.publisher("google")
.modelName("text-embedding-004")
.build();
List<TextSegment> segments = List.of(
TextSegment.from("First document"),
TextSegment.from("Second document")
);
Response<List<Embedding>> response = model.embedAll(segments);
List<Embedding> embeddings = response.content();Supported Models
text-embedding-004- Latest, 768 dimensionstextembedding-gecko@001/002/003- Gecko models, 768 dimensionstext-multilingual-embedding-002- Multilingual, 768 dimensionsmultimodalembedding- Multimodal, 1408 dimensions
Configuration Parameters
Required
endpoint- API endpoint (different format:{region}-aiplatform.googleapis.com:443)project- Google Cloud Project IDlocation- GCP regionpublisher- Model publisher ("google")modelName- Model name/version
Optional
maxRetries(Integer) - Retry attempts (default: 2)maxSegmentsPerBatch(Integer) - Max segments per API call (default: 250)maxTokensPerBatch(Integer) - Max tokens per batch (default: 20,000)taskType(TaskType) - Optimization for specific taskstitleMetadataKey(String) - Metadata key for titles (default: "title")autoTruncate(Boolean) - Auto-truncate long texts (default: false)outputDimensionality(Integer) - Custom embedding dimensioncredentials(GoogleCredentials) - Custom auth
Task Types
public enum TaskType {
RETRIEVAL_QUERY, // Query for retrieval
RETRIEVAL_DOCUMENT, // Document for retrieval
SEMANTIC_SIMILARITY, // Similarity comparison
CLASSIFICATION, // Text classification
CLUSTERING, // Text clustering
QUESTION_ANSWERING, // Question answering
FACT_VERIFICATION, // Fact verification
CODE_RETRIEVAL_QUERY // Code retrieval
}Usage: Use RETRIEVAL_DOCUMENT for indexing, RETRIEVAL_QUERY for searching.
Use Cases
- Semantic search and retrieval
- Document similarity
- Recommendation systems
- Clustering and classification
- Retrieval Augmented Generation (RAG)
See Also
- Examples - Detailed usage examples
- API Reference - Complete API documentation
Install with Tessl CLI
npx tessl i tessl/maven-dev-langchain4j--langchain4j-vertex-ai