Speaker: Georgios Andrianakis
Principal Software Engineer @ Red Hat
Speaker: Ioannis Canellos
Senior Principal Software Engineer @ Red Hat
Workshop Description
LLMs are poised to play an important role in our daily lives and as such, place an increasingly large burden on developers to integrate them into the software they build. In this session we will demonstrate how easy it is to create AI powered applications using the combination of Quarkus and Langchain4j.
What will you Learn:
– Basic concepts of integrating Quarkus with Langchain4j
– How to fine tune the AI behavior of your application
– Using patterns like: RAG and Guardrails
– Extend the capabilities of the LLM using your own tools
Level: Beginner to Intermediate
TAGs: #AI #LLMs # Quarkus #Langchain4j
Target audience: Java Developers
Prerequisites on Audience:
For those who want to follow along:
– JDK 17 or 21
– Apache Maven 3.9+ (recommended)
– Docker or Podman (recommended)
– Software
JDK 21.0 or later – Download it from Adoptium
A key for OpenAI API (provided by the workshop organizer)
Podman or Docker – See Podman installation or Docker installation
If you use Podman, Podman Desktop provides a great user experience to manage your containers: Podman Desktop
Git (not mandatory) – See Git installation
An IDE with Java support (IntelliJ, Eclipse, VSCode with the Java extension, etc.)
A terminal
– AI model requirements
A limited number of keys will be provided on site.
– Before attending
Downloading maven artifacts and docker images, using the public internet. Now, that’s a great idea!
Be awesome and get them in advance: https://cescoffier.github.io/quarkus-langchain4j-workshop/requirements/#warming-the-caches
Warmup and verification
To ensure that your environment has all the required tools and dependencies available, please run this before the event:
Mac & Linux :
curl -o code-wtih-quarkus.zip “https://code.quarkus.io/d?j=17&e=io.quarkiverse.langchain4j%3Aquarkus-langchain4j-openai&e=jdbc-postgresql&e=rest-jackson&e=hibernate-orm&cn=code.quarkus.io“
unzip code-with-quarkus
cd code-with-quakrus
./mvnw quarkus:dev
The workshop will use samples from https://github.com/quarkiverse/quarkus-langchain4j and it’s recommended to clone the project beforehand.
git clone https://github.com/quarkiverse/quarkus-langchain4j.git
cd quarkus-langchain4j
./mvnw clean install
Windows :
curl.exe -o code-wtih-quarkus.zip “https://code.quarkus.io/d?j=17&e=io.quarkiverse.langchain4j%3Aquarkus-langchain4j-openai&e=jdbc-postgresql&e=rest-jackson&e=hibernate-orm&cn=code.quarkus.io“
After extracting the project:
cd code-with-quakrus
mvnw.cmd quarkus:dev
The workshop will use samples from https://github.com/quarkiverse/quarkus-langchain4j and it’s recommended to clone the project beforehand.
git clone https://github.com/quarkiverse/quarkus-langchain4j.git
cd quarkus-langchain4j
mvnw.cmd clean install
Schedule:
– Introduction to Quarkus LangChain4j
– Playing with model parameters
– Streaming responses
– Using system messages
– Introduction to the RAG pattern
– Deconstructing the RAG
– Function calling and tools
– Guardrails