final

RAG (Retrieval-Augmented Generation)

This project uses Quarkus, the Supersonic Subatomic Java Framework.

If you want to learn more about Quarkus, please visit its website: https://quarkus.io/.

Running the application in dev mode

You can run your application in dev mode that enables live coding using:

./gradlew quarkusDev

NOTE: Quarkus now ships with a Dev UI, which is available in dev mode only at http://localhost:8080/q/dev/.

Packaging and running the application

The application can be packaged using:

./gradlew build

It produces the quarkus-run.jar file in the build/quarkus-app/ directory. Be aware that it’s not an über-jar as the dependencies are copied into the build/quarkus-app/lib/ directory.

The application is now runnable using java -jar build/quarkus-app/quarkus-run.jar.

If you want to build an über-jar, execute the following command:

./gradlew build -Dquarkus.package.jar.type=uber-jar

The application, packaged as an über-jar, is now runnable using java -jar build/*-runner.jar.

Creating a native executable

You can create a native executable using:

./gradlew build -Dquarkus.native.enabled=true

Or, if you don't have GraalVM installed, you can run the native executable build in a container using:

./gradlew build -Dquarkus.native.enabled=true -Dquarkus.native.container-build=true

You can then execute your native executable with: ./build/final-1.0.0-SNAPSHOT-runner

If you want to learn more about building native executables, please consult https://quarkus.io/guides/gradle-tooling.

Related Guides

• LangChain4j Easy RAG (guide): Provides the Easy RAG functionality with LangChain4j
• REST Jackson (guide): Jackson serialization support for Quarkus REST. This extension is not compatible with the quarkus-resteasy extension, or any of the extensions that depend on it
• LangChain4j OpenAI (guide): Provides the basic integration with LangChain4j

Provided Code

LangChain4j Easy RAG

This code is a very basic sample service to start developing with Quarkus LangChain4j using Easy RAG.

This code is set up to use OpenAI as the LLM, thus you need to set the QUARKUS_LANGCHAIN4J_OPENAI_API_KEY environment variable to your OpenAI API key.

In ./easy-rag-catalog/ you can find a set of example documents that will be used to create the RAG index which the bot (src/main/java/org/acme/Bot.java) will ingest.

On first run, the bot will create the RAG index and store it in easy-rag-catalog.json file and reuse it on subsequent runs. This can be disabled by setting the quarkus.langchain4j.easy-rag.reuse-embeddings.enabled property to false.

Add it to a Rest endpoint:

    @Inject
    Bot bot;
    
    @POST
    @Produces(MediaType.TEXT_PLAIN)
    public String chat(String q) {
        return bot.chat(q);
    }

In a more complete example, you would have a web interface and use websockets that would provide more interactive experience, see ChatBot Easy RAG Sample for such an example.

REST

Easily start your REST Web Services

Related guide section...