PricingLoginStart free
Spring Boot 4 Complete Guide · Aula

Pipelines de Geração Aumentada por Recuperação

Monte fluxos RAG que fundamentem as respostas do modelo no contexto dos documentos recuperados.

Aula 3 de 413 etapas

Pipelines de Geração Aumentada por Recuperação é uma aula grátis de Spring Boot 4 Complete Guide no CoddyKit. Esta é a aula 3 de 4. Você pode ler a aula completa abaixo gratuitamente — depois pratica ao vivo no navegador com um editor de código integrado e um tutor de IA 24/7. Faz parte do caminho de aprendizado de Spring Boot 4 Complete Guide, e seu progresso é sincronizado entre a web e o app CoddyKit. O curso de Spring Boot 4 Complete Guide inclui 4 aulas no total.

Partes desta aula ainda não foram traduzidas e aparecem em inglês.

Why RAG?

Retrieval-Augmented Generation (RAG) grounds an LLM's answers in your own documents instead of relying solely on what the model memorized during training.

  • Fresh & private data — answer questions about internal docs the model never saw.
  • Less hallucination — the model cites retrieved context rather than inventing facts.
  • Cheaper than fine-tuning — you update a vector store, not model weights.

A Spring AI RAG pipeline has two phases: an ingestion phase (read → split → embed → store) and a query phase (embed question → retrieve → augment prompt → generate).

The Pipeline at a Glance

Spring AI gives you composable building blocks for both phases. The core types you will assemble are:

  • DocumentReader — loads raw sources (PDF, Markdown, JSON, web pages).
  • DocumentTransformer — splits documents into chunks (e.g. TokenTextSplitter).
  • EmbeddingModel — turns text into vectors.
  • VectorStore — stores and similarity-searches those vectors.
  • ChatClient with a RAG advisor — wires retrieval into the prompt automatically.

The first three feed ingestion; the last two power querying.

Ingestion: Read and Split

During ingestion you read source files and split them into chunks small enough to fit the model's context window while staying semantically coherent. TokenTextSplitter chunks by token count with overlap so meaning isn't cut mid-sentence.

Below, a Markdown file is read and split into ~800-token chunks before storage.

@Component
class DocumentIngestor {

    private final VectorStore vectorStore;

    DocumentIngestor(VectorStore vectorStore) {
        this.vectorStore = vectorStore;
    }

    void ingest(Resource markdown) {
        var reader = new TextReader(markdown);
        List<Document> raw = reader.get();

        var splitter = new TokenTextSplitter(800, 350, 5, 10000, true);
        List<Document> chunks = splitter.apply(raw);

        vectorStore.add(chunks);
    }
}

Embeddings: Text to Vectors

An embedding is a dense vector that captures the meaning of text. Two passages about the same topic land close together in vector space, which is what makes similarity search work.

Spring AI auto-configures an EmbeddingModel based on your starter (OpenAI, Azure, Ollama, etc.). You rarely call it directly — the VectorStore uses it internally — but you can:

@Service
class EmbeddingDemo {

    private final EmbeddingModel embeddingModel;

    EmbeddingDemo(EmbeddingModel embeddingModel) {
        this.embeddingModel = embeddingModel;
    }

    float[] embed(String text) {
        return embeddingModel.embed(text);
    }

    int dimensions() {
        return embeddingModel.dimensions();
    }
}

Configuring a VectorStore

The VectorStore persists embeddings and runs similarity searches. Spring AI ships adapters for PgVector, Redis, Chroma, Qdrant, Milvus, and a simple in-memory store.

With the spring-ai-starter-vector-store-pgvector dependency, a bean is auto-configured from properties — no manual wiring needed:

spring:
  ai:
    vectorstore:
      pgvector:
        initialize-schema: true
        index-type: HNSW
        distance-type: COSINE_DISTANCE
        dimensions: 1536
  datasource:
    url: jdbc:postgresql://localhost:5432/ragdb
    username: rag
    password: secret

Querying: Similarity Search

At query time you turn the user's question into a vector and ask the store for the nearest chunks. A SearchRequest controls how many results (topK) and a minimum similarityThreshold to filter out weak matches.

List<Document> retrieve(VectorStore store, String question) {
    var request = SearchRequest.builder()
            .query(question)
            .topK(4)
            .similarityThreshold(0.7)
            .build();

    List<Document> hits = store.similaritySearch(request);
    return hits;
}

Augmenting the Prompt Manually

Before reaching for advisors, it helps to see the mechanic. RAG simply stuffs the retrieved text into the prompt and instructs the model to answer only from it. This is the "augment" step:

String answer(ChatClient chat, VectorStore store, String question) {
    List<Document> docs = store.similaritySearch(
            SearchRequest.builder().query(question).topK(4).build());

    String context = docs.stream()
            .map(Document::getText)
            .collect(Collectors.joining("\n---\n"));

    return chat.prompt()
            .system("Answer using ONLY the context. If unknown, say you don't know.")
            .user(u -> u.text("Context:\n{ctx}\n\nQuestion: {q}")
                        .param("ctx", context)
                        .param("q", question))
            .call()
            .content();
}

The QuestionAnswerAdvisor

Spring AI packages that manual pattern as the QuestionAnswerAdvisor. You attach it to a ChatClient and it transparently runs the similarity search and injects context for every call.

This is the idiomatic, declarative way to do RAG in Spring Boot 4:

@Service
class RagAssistant {

    private final ChatClient chatClient;

    RagAssistant(ChatClient.Builder builder, VectorStore vectorStore) {
        this.chatClient = builder
                .defaultAdvisors(new QuestionAnswerAdvisor(vectorStore))
                .build();
    }

    String ask(String question) {
        return chatClient.prompt()
                .user(question)
                .call()
                .content();
    }
}

Per-Request Retrieval Tuning

Defaults are convenient, but real apps tune retrieval per request — a focused FAQ may need topK=2, a broad research query topK=8. Pass an advisor at call time and override its SearchRequest, plus metadata filters to scope to a tenant or document set:

String ask(ChatClient chatClient, VectorStore store, String q, String tenant) {
    var advisor = QuestionAnswerAdvisor.builder(store)
            .searchRequest(SearchRequest.builder()
                    .topK(6)
                    .similarityThreshold(0.75)
                    .filterExpression("tenant == '" + tenant + "'")
                    .build())
            .build();

    return chatClient.prompt()
            .advisors(advisor)
            .user(q)
            .call()
            .content();
}

Modular RAG with RetrievalAugmentationAdvisor

For advanced pipelines, Spring AI 1.0 offers the Modular RAG API via RetrievalAugmentationAdvisor. It exposes each stage as a swappable component:

  • QueryTransformer — rewrite, compress, or translate the query.
  • DocumentRetriever — the source of chunks (e.g. VectorStoreDocumentRetriever).
  • QueryAugmenter — control how context is merged and how empty-context is handled.
var retriever = VectorStoreDocumentRetriever.builder()
        .vectorStore(vectorStore)
        .similarityThreshold(0.72)
        .topK(5)
        .build();

var ragAdvisor = RetrievalAugmentationAdvisor.builder()
        .queryTransformers(RewriteQueryTransformer.builder()
                .chatClientBuilder(chatClientBuilder)
                .build())
        .documentRetriever(retriever)
        .build();

String answer = chatClient.prompt()
        .advisors(ragAdvisor)
        .user(question)
        .call()
        .content();

Guarding Against Empty Context

A subtle RAG failure: when retrieval finds nothing relevant, a naive prompt lets the model fall back to its training data and hallucinate. The ContextualQueryAugmenter lets you decide that policy explicitly.

Set allowEmptyContext(false) to force a graceful "I don't have information on that" instead of a confident guess:

var augmenter = ContextualQueryAugmenter.builder()
        .allowEmptyContext(false)
        .build();

var ragAdvisor = RetrievalAugmentationAdvisor.builder()
        .documentRetriever(retriever)
        .queryAugmenter(augmenter)
        .build();

// With no matching documents, the model returns a safe
// "no answer available" response instead of fabricating one.

Quick Check

You build a RAG assistant. When a user asks something outside your knowledge base, similarity search returns no chunks above the threshold, yet the model still answers confidently with made-up facts. Which change best fixes this?

Responda na aula interativa

Recap

You assembled a complete RAG pipeline in Spring AI:

  • Ingestion — DocumentReader → TokenTextSplitter → EmbeddingModel → VectorStore.add().
  • Query — embed the question, similaritySearch with topK and similarityThreshold, then augment the prompt.
  • Declarative RAG — QuestionAnswerAdvisor wires retrieval into a ChatClient automatically; tune it per request with custom SearchRequest and metadata filters.
  • Modular RAG — RetrievalAugmentationAdvisor with query transformers, retrievers, and augmenters for advanced control.
  • Safety — ContextualQueryAugmenter.allowEmptyContext(false) prevents hallucination when nothing relevant is retrieved.

Grounding model output in retrieved context is the single most effective way to make LLM features trustworthy.

Grátis para começar

Aprenda Java com um tutor de IA — grátis

Escreva e execute código real no seu navegador, obtenha ajuda instantânea de um tutor de IA 24/7 e continue de onde parou na web ou no app.

Cursos
21
Aulas
84
Começar a aprender grátisVer o curso completo

Perguntas Frequentes

A aula “Pipelines de Geração Aumentada por Recuperação” é grátis?

Sim — o texto completo de “Pipelines de Geração Aumentada por Recuperação” é grátis para ler aqui na web. Para praticá-la interativamente (um editor de código integrado e um tutor de IA 24/7) e desbloquear o restante do curso de Spring Boot 4 Complete Guide, atualize para CoddyKit PRO. O curso de Spring Boot 4 Complete Guide inclui 4 aulas no total.

O que vou aprender em “Pipelines de Geração Aumentada por Recuperação”?

Monte fluxos RAG que fundamentem as respostas do modelo no contexto dos documentos recuperados. Você pratica Spring Boot 4 Complete Guide com código prático que executa diretamente no navegador, e um tutor de IA 24/7 responde suas dúvidas enquanto trabalha na aula.

Preciso ter experiência prévia para começar Spring Boot 4 Complete Guide?

Nenhuma experiência prévia é necessária. Spring Boot 4 Complete Guide no CoddyKit é estruturado para alunos iniciantes até avançados, então você pode começar aqui ou desde o início e aprender no seu ritmo. Esta é a aula 3 de 4.

Quanto tempo leva a aula “Pipelines de Geração Aumentada por Recuperação”?

A maioria das aulas CoddyKit leva cerca de 5–10 minutos. Cada uma é compacta e interativa, então você faz progresso constante e retoma exatamente de onde parou entre web e app.

Posso escrever e executar código nesta aula de Spring Boot 4 Complete Guide?

Sim. Cada aula de Spring Boot 4 Complete Guide inclui um editor de código integrado, então você escreve e executa código real direto no navegador e recebe feedback de IA instantaneamente — nenhuma configuração local necessária.

Todas as aulas deste curso

  1. ChatClient, Prompts e Saída Estruturada
  2. Embeddings e Recuperação em Armazenamentos Vetoriais
  3. Pipelines de Geração Aumentada por Recuperação
  4. Chamadas de Ferramentas e Consultores de Agentes
← Voltar para Spring Boot 4 Complete Guide