Skip to content
TruthVouch Docs

Spring AI Integration

The TruthVouch Spring AI integration provides chat client and embedding client implementations that route all AI calls through TruthVouch Firewall for governance.

Status: Coming Soon (Q2 2026)

Installation

<dependency>
  <groupId>com.truthvouch</groupId>
  <artifactId>truthvouch-spring-ai-starter</artifactId>
  <version>1.0.0</version>
</dependency>

Or with Gradle:

implementation 'com.truthvouch:truthvouch-spring-ai-starter:1.0.0'

Planned Features

  • ChatClient implementation with TruthVouch Firewall
  • EmbeddingClient with vector caching
  • Spring Boot auto-configuration with @EnableTruthVouch
  • Configuration via application.yml
  • Full governance pipeline
  • Streaming support
  • Circuit breaker and retry logic

Planned Configuration

application.yml

truthvouch:
  api-key: ${TRUTHVOUCH_API_KEY}
  gateway-url: https://gateway.truthvouch.com
  timeout-seconds: 30
  fail-mode: open


  spring-ai:
    model: gpt-4o  # Default model
    temperature: 0.7

Enable in Code

@Configuration
@EnableTruthVouch
public class AiConfig {
    // Auto-configured beans provided
}

Planned Usage

Inject ChatClient

@RestController
public class ChatController {
    private final ChatClient chatClient;


    public ChatController(ChatClient chatClient) {
        this.chatClient = chatClient;
    }


    @PostMapping("/ask")
    public ResponseEntity<String> ask(@RequestBody String question) {
        String response = chatClient.prompt()
            .user(question)
            .call()
            .content();


        // Automatically governed, fact-checked, audit-logged
        return ResponseEntity.ok(response);
    }
}

Streaming Responses

@GetMapping("/ask-stream")
public ResponseEntity<String> askStream(@RequestBody String question) {
    chatClient.prompt()
        .user(question)
        .stream()
        .content()
        .forEach(System.out::print);


    return ResponseEntity.ok("done");
}

With Embeddings

@Service
public class RagService {
    private final ChatClient chatClient;
    private final EmbeddingClient embeddingClient;


    public String answerQuestion(String question) {
        // Generate embedding for the question
        float[] questionEmbedding = embeddingClient.embed(question);


        // Retrieve relevant documents from vector store
        List<String> relevantDocs = vectorStore.search(questionEmbedding, 5);


        // Build context
        String context = String.join("\n", relevantDocs);


        // Query with context
        String response = chatClient.prompt()
            .user(String.format(
                "Context:\n%s\n\nQuestion: %s",
                context,
                question
            ))
            .call()
            .content();


        return response;
        // All calls governed by TruthVouch
    }
}

Timeline

  • Q2 2026: Public beta release
  • Q3 2026: GA release with full feature parity

Next Steps