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/scoring/
Scoring Model Overview
Text ranking and scoring using Google Vertex AI Ranking API. Scores and ranks text segments by relevance to queries. Implements LangChain4j ScoringModel.
Class
public class VertexAiScoringModel implements ScoringModel {
public Response<List<Double>> scoreAll(List<TextSegment> segments, String query);
public static Builder builder();
}Imports
import dev.langchain4j.model.vertexai.VertexAiScoringModel;
import dev.langchain4j.data.segment.TextSegment;
import dev.langchain4j.model.scoring.ScoringModel;
import dev.langchain4j.model.output.Response;Minimal Example
VertexAiScoringModel model = VertexAiScoringModel.builder()
.projectId("your-project-id")
.projectNumber("123456789012")
.location("us-central1")
.model("semantic-ranker-512@latest")
.build();
String query = "What is machine learning?";
List<TextSegment> documents = List.of(
TextSegment.from("Machine learning is a branch of AI..."),
TextSegment.from("Deep learning uses neural networks..."),
TextSegment.from("Supervised learning requires labels...")
);
Response<List<Double>> response = model.scoreAll(documents, query);
List<Double> scores = response.content(); // Relevance scoresSupported Models
semantic-ranker-512@latest- Semantic ranking model (512 dimensions)
Configuration Parameters
Required
projectId(String) - Google Cloud Project IDprojectNumber(String) - Google Cloud Project number (12-digit)location(String) - GCP regionmodel(String) - Ranking model name
Optional
titleMetadataKey(String) - Metadata key for document titles (default: "title")
Note: Configuration differs from other models - requires both projectId and projectNumber.
Finding Project Number
# Via gcloud CLI
gcloud projects describe PROJECT_ID --format="value(projectNumber)"
# Or check Google Cloud Console project dashboardUse Cases
- Search result re-ranking
- Retrieval Augmented Generation (RAG)
- Document recommendation
- Relevance scoring
- Query-document matching
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@1.11.0