LangChain4j Agent

<dependency>
    <groupId>io.quarkiverse.langchain4j</groupId>
    <artifactId>quarkus-langchain4j-oidc-mcp-auth-provider</artifactId>
</dependency>

camel.oauth.keycloak.client-id=camel-client
camel.oauth.keycloak.client-secret=camel-client-secret
camel.oauth.keycloak.token-endpoint=https://keycloak.example.com/realms/camel/protocol/openid-connect/token

String token = OAuthHelper.resolveOAuthToken(getContext(), "azure");

ChatModel chatModel = OpenAiChatModel.builder()
        .apiKey(token)
        .modelName("gpt-4")
        .build();

getContext().getRegistry().bind("myChatModel", chatModel);

from("direct:agent")
    .to("langchain4j-agent:myAgent");

var prompt = "What is Apache Camel";

String response = template.requestBody("direct:chat", prompt, String.class);

var prompt = "What is Apache Camel";
AiAgentBody body = new AiAgentBody(prompt);

String response = template.requestBody("direct:chat", body, String.class);

var userPrompt = "Write a short story about a lost cat.";
var systemPrompt = "You are a whimsical storyteller. Your responses should be imaginative, descriptive, and always include a touch of magic. Start every story with 'Once upon a starlit night...";

String response = template.requestBodyAndHeader("direct:chat",
                userPrompt, "CamelLangChain4jAgentSystemMessage", systemPrompt , String.class);

var userPrompt = "Write a short story about a lost cat.";
var systemPrompt = "You are a whimsical storyteller. Your responses should be imaginative, descriptive, and always include a touch of magic. Start every story with 'Once upon a starlit night...";

AiAgentBody body = new AiAgentBody()
                .withUserMessage(userPrompt)
                .withSystemMessage(systemPrompt);

String response = template.requestBody("direct:chat", body, String.class);

var userPrompt = "Can you tell me the name of user 123 and the weather in New York?";
var systemPrompt = "You are a helpful assistant that can access user database and weather information. Use the available tools to provide accurate information.";

String response = template.requestBodyAndHeader("direct:chat",
                userPrompt, "CamelLangChain4jAgentSystemMessage", systemPrompt , String.class);

// Define Camel route tools
from("langchain4j-tools:weatherService?tags=weather&description=Get current weather information&parameter.location=string")
    .setBody(constant("{\"weather\": \"sunny\", \"location\": \"Current Location\"}"));

// Create custom tool instances
CalculatorTool calculator = new CalculatorTool();
StringTool stringTool = new StringTool();

// Create agent configuration with both types of tools
AgentConfiguration config = new AgentConfiguration()
    .withChatModel(chatModel)
    .withCustomTools(Arrays.asList(calculator, stringTool));

// Create agent
Agent agent = new AgentWithMemory(config);

// Register agent in Camel context
context.getRegistry().bind("mixedToolsAgent", agent);

// Create the retrieval augmentor (shown below)
RetrievalAugmentor retrievalAugmentor = createRetrievalAugmentor();

// Create agent configuration with RAG
AgentConfiguration configuration = new AgentConfiguration()
    .withChatModel(chatModel)
    .withRetrievalAugmentor(retrievalAugmentor)
    .withInputGuardrailClasses(List.of())
    .withOutputGuardrailClasses(List.of());

Agent ragAgent = new AgentWithoutMemory(configuration);
context.getRegistry().bind("ragAgent", ragAgent);

// creating the retrieval Augmentor
EmbeddingStoreContentRetriever contentRetriever = EmbeddingStoreContentRetriever.builder()
                .embeddingStore(embeddingStore) // the embedding store should be defined
                .embeddingModel(embeddingModel) // the embedding model should be defined
                .maxResults(3)
                .minScore(0.6)
                .build();

RetrievalAugmentor retrievalAugmentor = DefaultRetrievalAugmentor.builder()
                .contentRetriever(contentRetriever)
                // other options or steps can be included for Advanced RAG
                .build();

// bind the retrievalAugmentor in the context
context.getRegistry().bind("retrievalAugmentor", retrievalAugmentor);

// using the producer
String response = template.requestBody("direct:chat", body, String.class);

// Example of creating a Chat Memory Provider : Create a message window memory that keeps the last 10 messages
        ChatMemoryProvider chatMemoryProvider = memoryId -> MessageWindowChatMemory.builder()
                .id(memoryId)
                .maxMessages(10)
                .chatMemoryStore(store) // the Chat Memory store is previously created
                .build();

// bind the chat memory provider in the context
context.getRegistry().bind("chatMemoryProvider", chatMemoryProvider);


AiAgentBody request = new AiAgentBody("Hello!", null, "session-123");
String response = template.requestBody("direct:chat", request, String.class);