Knowledge Base & RAG

// Simple document (auto-generated ID)
Document doc = Document.of("This is the document content");

// Document with a single metadata entry
Document doc = Document.of("Product docs...", "source", "docs/product.md");

Document doc = Document.builder()
    .id("doc-001")                          // optional, UUID generated if omitted
    .content("Product documentation...")     // required
    .metadata("source", "docs/product.md")  // single entry
    .metadata("category", "documentation")  // chainable
    .metadata(Map.of("version", "2.0"))     // bulk metadata
    .embedding(embeddingVector)              // optional float[]
    .build();

// Attach an embedding to an existing document (returns a new Document)
Document withVector = doc.withEmbedding(embeddingVector);

List<SearchResult> results = knowledgeBase.search("query", 5);
for (SearchResult result : results) {
    System.out.printf("Score: %.4f | %s%n", result.getScore(), result.getContent());
}

KnowledgeBase kb = new InMemoryKnowledgeBase();

kb.addDocument(Document.of("Java is a programming language"));
kb.addDocument(Document.of("Python is also a programming language"));
kb.addDocument(Document.builder()
    .content("Rust is a systems programming language")
    .metadata("category", "systems")
    .build());

// Keyword search
List<SearchResult> results = kb.search("programming language", 5);

// Filtered search
List<SearchResult> filtered = kb.search("programming", 5,
    Map.of("category", "systems"));

// Embedding search
List<SearchResult> similar = kb.searchByEmbedding(queryEmbedding, 3);

// On a class -- multiple sources via @Repeatable
@KnowledgeSource(
    name = "product-docs",
    type = KnowledgeType.VECTOR_DB,
    provider = "pinecone",
    index = "products",
    topK = 5,
    minSimilarity = 0.8
)
@KnowledgeSource(
    name = "faq",
    type = KnowledgeType.FILE,
    path = "knowledge/faq.json"
)
public class SupportAgent extends Agent { ... }

// On a method
@ActionSpec(type = ActionType.LLM_GENERATION, description = "Answer question")
@KnowledgeSource(name = "product-docs", topK = 3)
public String answerQuestion(String question) {
    // Relevant context is automatically retrieved before the LLM call
}

// Database source
@KnowledgeSource(
    name = "customer-data",
    type = KnowledgeType.DATABASE,
    connection = "jdbc:postgresql://localhost/mydb",
    query = "SELECT content FROM docs WHERE content ILIKE '%${query}%' LIMIT 10"
)

// Web search source with caching
@KnowledgeSource(
    name = "web-context",
    type = KnowledgeType.WEB_SEARCH,
    topK = 3,
    cache = true,
    cacheTTL = 600
)

KnowledgeBase kb = new InMemoryKnowledgeBase();
kb.addDocument(Document.of("Product X supports features A, B, C"));
kb.addDocument(Document.of("Pricing starts at $99/month"));

Agent agent = AgentBuilder.create()
    .llm(llmClient)
    .role(supportRole)
    .knowledgeBase(kb)            // attach the knowledge base
    .knowledgeBaseTopK(3)         // override default top-K (default: 5)
    .build();

// 1. Create and populate knowledge base
KnowledgeBase kb = new InMemoryKnowledgeBase();
kb.addDocuments(List.of(
    Document.builder()
        .content("Product X supports features A, B, and C.")
        .metadata("source", "product-docs")
        .metadata("category", "features")
        .build(),
    Document.builder()
        .content("Pricing starts at $99/month for the Basic plan.")
        .metadata("source", "pricing-page")
        .metadata("category", "pricing")
        .build(),
    Document.builder()
        .content("Enterprise plan includes SSO and dedicated support.")
        .metadata("source", "pricing-page")
        .metadata("category", "pricing")
        .build()
));

// 2. Search for relevant context
String query = "What features does Product X have?";
List<SearchResult> context = kb.search(query, 3);

// 3. Build augmented prompt
String augmentedPrompt = "Context:\n" +
    context.stream()
        .map(r -> r.getContent())
        .collect(Collectors.joining("\n")) +
    "\n\nQuestion: " + query;

// 4. Send to agent
String answer = agent.chat(augmentedPrompt);

// Or use filtered search for specific categories
List<SearchResult> pricingResults = kb.search("plan cost", 3,
    Map.of("category", "pricing"));