--- title: "AI Endpoints - Create your own AI chatbot using LangChain4j and Quarkus" description: "Learn how to build an AI-powered chatbot using LangChain4j, Quarkus, and OVHcloud AI Endpoints" url: https://docs.ovhcloud.com/de/guides/public-cloud/ai-machine-learning/ai-endpoints-chatbot-langchain4j-quarkus lang: de lastUpdated: 2025-12-19 --- # AI Endpoints - Create your own AI chatbot using LangChain4j and Quarkus :::info AI Endpoints is covered by the **[OVHcloud AI Endpoints Conditions](https://storage.gra.cloud.ovh.net/v1/AUTH_325716a587c64897acbef9a4a4726e38/contracts/48743bf-AI_Endpoints-ALL-1.1.pdf)** and the **[OVHcloud Public Cloud Special Conditions](https://storage.gra.cloud.ovh.net/v1/AUTH_325716a587c64897acbef9a4a4726e38/contracts/d2a208c-Conditions_particulieres_OVH_Stack-WE-9.0.pdf)**. ::: ## Introduction Looking to build an AI-powered chatbot with Java? In this tutorial, you will learn how to create a chatbot using **[LangChain4j](https://github.com/langchain4j/langchain4j)**, **[Quarkus](https://github.com/quarkusio/quarkus)**, and **[AI Endpoints](https://www.ovhcloud.com/de/public-cloud/ai-endpoints/)**. ## Objective This tutorial demonstrates how to: - Set up a Quarkus application using LangChain4j - Connect your chatbot to AI Endpoints - Customize prompts with annotations - Expose your chatbot as an API - Test your chatbot using a cURL request ## Definitions - **[LangChain4j](https://github.com/langchain4j/langchain4j)**: Java-based framework inspired by [LangChain](https://github.com/langchain-ai/langchain), designed to simplify the integration of LLMs (Large Language Models) into applications. It offers abstractions and annotations for building intelligent agents and chatbots. Note that LangChain4j is not officially maintained by the LangChain team, despite the similar name. - **[Quarkus](https://quarkus.io/)**: A Kubernetes-native Java framework designed to optimize Java applications for containers and the cloud. In this tutorial we will use the [quarkus-langchain4j](https://github.com/quarkiverse/quarkus-langchain4j/) extension. - **[AI Endpoints](https://www.ovhcloud.com/de/public-cloud/ai-endpoints/)**: A serverless platform by OVHcloud providing easy access to a variety of world-renowned AI models including Mistral, LLaMA, and more. This platform is designed to be simple, secure, and intuitive, with data privacy as a top priority. ## Requirements - A [Public Cloud project](https://www.ovhcloud.com/de/public-cloud/) in your OVHcloud account - An access token for **OVHcloud AI Endpoints**. To create an API token, follow the instructions in the [AI Endpoints - Getting Started](/de/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started.md) guide. - Quarkus CLI installed ## Instructions ### Create a Quarkus project Generate your Quarkus project using the CLI with the LangChain4j Mistral AI extension: ```bash $ quarkus create app com.ovhcloud.examples.aiendpoints:quarkus-langchain4j \ --extension='quarkus-langchain4j-mistral-ai' ``` Here is the tree structure after running the previous command: ```console . ├── .dockerignore ├── .gitignore ├── .mvn │ └── wrapper │ ├── .gitignore │ ├── MavenWrapperDownloader.java │ └── maven-wrapper.properties ├── README.md ├── mvnw ├── mvnw.cmd ├── pom.xml └── src └── main ├── docker │ ├── Dockerfile.jvm │ ├── Dockerfile.legacy-jar │ ├── Dockerfile.native │ └── Dockerfile.native-micro ├── java └── resources └── application.properties ``` After running this command, check your pom.xml for the following dependency: ```xml {/* ... */} io.quarkiverse.langchain4j quarkus-langchain4j-mistral-ai 0.10.4 {/* ... */} ``` ### AI service creation Let’s code our service to create a chatbot, using an annotation: ```java import io.quarkiverse.langchain4j.RegisterAiService; @RegisterAiService public interface ChatBotService { } ``` Now add system and user prompts to your service: ```java import dev.langchain4j.service.SystemMessage; import dev.langchain4j.service.UserMessage; import io.quarkiverse.langchain4j.RegisterAiService; @RegisterAiService public interface ChatBotService { // Scope / context passed to the LLM @SystemMessage("You are a virtual, an AI assistant.") // Prompt (with detailed instructions and variable section) passed to the LLM @UserMessage("Answer as best possible to the following question: {question}. The answer must be in a style of a virtual assistant and add some emojis to make the answer more fun.") String askAQuestion(String question); } ``` 💡 For more details about [@SystemMessage](https://docs.quarkiverse.io/quarkus-langchain4j/dev/ai-services.html#_system_message) and [@UserMessage](https://docs.quarkiverse.io/quarkus-langchain4j/dev/ai-services.html#_user_message_prompt), refer to the Quarkus LangChain4j extension documentation. ### Configure AI Endpoints access Adapt and add the following configuration to your application.properties, to enable AI Endpoints access: ```console ### Global configurations # Base URL for Mistral AI endpoints quarkus.langchain4j.mistralai.base-url=${OVH_AI_ENDPOINTS_URL} # Activate or not the log during the request quarkus.langchain4j.mistralai.log-requests=true # Activate or not the log during the response quarkus.langchain4j.mistralai.log-responses=true # Delay before raising a timeout exception quarkus.langchain4j.mistralai.timeout=60s # No key is needed quarkus.langchain4j.mistralai.api-key=${OVH_AI_ENDPOINTS_ACCESS_TOKEN} # Activate or not the Mistral AI embedding model quarkus.langchain4j.mistralai.embedding-model.enabled=false ### Chat model configurations # Activate or not the Mistral AI chat model quarkus.langchain4j.mistralai.chat-model.enabled=true # Chat model name used quarkus.langchain4j.mistralai.chat-model.model-name=${OVH_AI_ENDPOINTS_MODEL_NAME} # Number of tokens to use quarkus.langchain4j.mistralai.chat-model.max-tokens=1024 ``` **Make sure to replace the token value (`OVH_AI_ENDPOINTS_ACCESS_TOKEN`) by yours.** If you do not have one yet, follow the instructions in the [AI Endpoints - Getting Started](/de/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started.md) guide. You will also have to replace two other environments variables, related to the model you want to use. You can find these model-specific values in the `documentation` tab of each model. For example, if you want to add the `Mistral-7B-Instruct-v0.3` model, the expected environment variables will be: - `OVH_AI_ENDPOINTS_MODEL_NAME`: Mistral-7B-Instruct-v0.3 - `OVH_AI_ENDPOINTS_URL`: [https://oai.endpoints.kepler.ai.cloud.ovh.net/v1](https://oai.endpoints.kepler.ai.cloud.ovh.net/v1) ### Build a REST API to interact with the chatbot First, install the [Quarkus REST extension](https://quarkus.io/extensions/io.quarkus/quarkus-rest/): ```bash $ quarkus ext add io.quarkus:quarkus-rest Looking for the newly published extensions in registry.quarkus.io [SUCCESS] ✅ Extension io.quarkus:quarkus-rest has been installed ``` Then create a REST endpoint: ```java import com.ovhcloud.examples.aiendpoints.services.ChatBotService; import jakarta.inject.Inject; import jakarta.ws.rs.POST; import jakarta.ws.rs.Path; // Endpoint root path @Path("ovhcloud-ai") public class AIEndpointsResource { // AI Service injection to use it later @Inject ChatBotService chatBotService; // ask resource exposition with POST method @Path("ask") @POST public String ask(String question) { // Call the Mistral AI chat model return chatBotService.askAQuestion(question); } } ``` ### Run and test Now it is time to test the AI chatbot API! To start your application and run your API, just use the [Quarkus dev mode](https://quarkus.io/guides/dev-mode-differences), by executing `quarkus dev`: ```console $ quarkus dev --/ __ \/ / / / _ | / _ \/ //_/ / / / __/ -/ /_/ / /_/ / __ |/ , _/ ,< / /_/ /\ \ --\___\_\____/_/ |_/_/|_/_/|_|\____/___/ 2024-04-12 08:51:33,515 INFO [io.quarkus] (Quarkus Main Thread) quarkus-langchain4j 1.0.0-SNAPSHOT on JVM (powered by Quarkus 3.9.3) started in 3.163s. Listening on: http://localhost:8080 2024-04-12 08:51:33,517 INFO [io.quarkus] (Quarkus Main Thread) Profile dev activated. Live Coding activated. 2024-04-12 08:51:33,518 INFO [io.quarkus] (Quarkus Main Thread) Installed features: [awt, cdi, langchain4j, langchain4j-mistralai, poi, qute, rest, rest-client, rest-client-jackson, smallrye-context-propagation, vertx] -- Tests paused Press [e] to edit command line args (currently ''), [r] to resume testing, [o] Toggle test output, [:] for the terminal, [h] for more options> ``` Then, use cURL to interact with your API: ```bash $ curl --header "Content-Type: application/json" \ --request POST \ --data '{"question": "What is OVHcloud?"}' \ http://localhost:8080/ovhcloud-ai/ask ``` For the previous prompt example, here is the result: ```console Answer: «OVHcloud is a global, integrated cloud hosting platform, offering Infrastructure as a Service (IaaS) and Platform as a Service (PaaS). » This answer describes OVHcloud as a global integrated cloud hosting platform offering IaaS and PaaS with optimal and secure services. Emojis were added to the response to make it more fun and engaging. ``` ## Conclusion In just a few steps, you have created your own AI chatbot powered by [LangChain4j](https://github.com/langchain4j/langchain4j), [Quarkus](https://github.com/quarkusio/quarkus), and [OVHcloud AI Endpoints](https://www.ovhcloud.com/de/public-cloud/ai-endpoints/). ## Going further If you want to go further and deploy your web app in the cloud, making your interface accessible to everyone, refer to the following articles and tutorials: - [AI Deploy – Tutorial – Build & use a custom Docker image](/de/guides/public-cloud/ai-machine-learning/ai-deploy-build-use-custom-image.md) - [AI Deploy – Tutorial – Deploy a Gradio app for sketch recognition](/de/guides/public-cloud/ai-machine-learning/ai-deploy-gradio-sketch-recognition.md) If you need training or technical assistance to implement our solutions, contact your sales representative or click on [this link](https://www.ovhcloud.com/de/professional-services/) to get a quote and ask our Professional Services experts for a custom analysis of your project. ## Feedback Please feel free to send us your questions, feedback, and suggestions regarding AI Endpoints and its features: - In the #ai-endpoints channel of the OVHcloud [Discord server](https://discord.gg/ovhcloud), where you can engage with the community and OVHcloud team members.