Language Model Overview

Text generation using Google Vertex AI language models (text-bison). Implements LangChain4j LanguageModel interface for simple text completion.

Class

public class VertexAiLanguageModel implements LanguageModel {
    public Response<String> generate(String prompt);
    public static Builder builder();
}

Imports

import dev.langchain4j.model.vertexai.VertexAiLanguageModel;
import dev.langchain4j.model.language.LanguageModel;
import dev.langchain4j.model.output.Response;

Minimal Example

VertexAiLanguageModel model = VertexAiLanguageModel.builder()
    .endpoint("https://us-central1-aiplatform.googleapis.com/v1/")
    .project("your-project-id")
    .location("us-central1")
    .publisher("google")
    .modelName("text-bison@001")
    .build();

Response<String> response = model.generate("Write a short poem about clouds");
System.out.println(response.content());

Supported Models

• text-bison@001 - PaLM 2 text generation
• text-bison@002 - PaLM 2 text generation (updated)
• text-bison-32k - Extended context version (32k tokens)

Configuration Parameters

Required

• endpoint - API endpoint URL
• project - Google Cloud Project ID
• location - GCP region
• publisher - Model publisher ("google")
• modelName - Model name/version

Optional

• temperature (Double) - Randomness 0.0-1.0 (default: varies by model)
• maxOutputTokens (Integer) - Max response length (default: 200)
• topK (Integer) - Top-K sampling
• topP (Double) - Nucleus sampling 0.0-1.0
• maxRetries (Integer) - Retry attempts (default: 3)

Language Model vs Chat Model

LanguageModel: Simple text completion with generate(String prompt) method. Single-turn generation.

ChatModel: Conversation interface with message history. Multi-turn conversations.

Use LanguageModel for:

• Simple text completion
• Code generation
• Text summarization
• Single-turn Q&A
• Content generation

Use ChatModel for:

• Multi-turn conversations
• Chatbots
• Interactive assistants
• Context-aware dialogues

Use Cases

• Text completion and generation
• Code snippet generation
• Content summarization
• Question answering (single turn)
• Creative writing assistance
• Documentation generation

See Also

• Examples - Detailed usage examples
• API Reference - Complete API documentation
• Chat Model - For conversational use cases