AI Endpoints - Développer un chatbot avec mémoire en utilisant LangChain4j (EN)

Base de connaissances

KB0067409

AI Endpoints - Développer un chatbot avec mémoire en utilisant LangChain4j (EN)


Icons/System/eye-open Created with Sketch. 113 vues 19.12.2025 AI Endpoints

AI Endpoints is covered by the OVHcloud AI Endpoints Conditions and the OVHcloud Public Cloud Special Conditions.

Introduction

In our other tutorials, chatbots answered one question at a time without remembering anything from the conversation. That’s fine for simple Q&A, but not ideal for real-world interactions.

Indeed, here’s a simple conversation with no memory:

💬: My name is Stéphane.
🤖: Hello Stéphane, how can I assist you today?
💬: What is my name?
🤖: I'm not capable of knowing your personal information...

That’s not very helpful.

In this tutorial, we’ll use LangChain4j to build a chatbot with memory support, allowing it to remember previous messages and provide more natural, contextual answers.

Definitions

  • LangChain4j: Java-based framework inspired by LangChain, designed to simplify the integration of LLMs (Large Language Models) into applications. Note that LangChain4j is not officially maintained by the LangChain team, despite the similar name.
  • 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

Instructions

Configure pom.xml

Add the following configuration to your Maven pom.xml file:

<properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>21</maven.compiler.source>
    <maven.compiler.target>21</maven.compiler.target>
    <maven.compiler.release>21</maven.compiler.release>
    <langchain4j.version>0.31.0</langchain4j.version>
  </properties>

  <dependencies>
    <dependency>
      <groupId>dev.langchain4j</groupId>
      <artifactId>langchain4j</artifactId>
      <version>${langchain4j.version}</version>
    </dependency>

    <dependency>
      <groupId>dev.langchain4j</groupId>
      <artifactId>langchain4j-mistral-ai</artifactId>
      <version>${langchain4j.version}</version>
    </dependency>

    <!-- ... -->
 </dependencies>

Create a memory-enabled chatbot

package com.ovhcloud.examples.aiendpoints;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import dev.langchain4j.memory.ChatMemory;
import dev.langchain4j.memory.chat.MessageWindowChatMemory;
import dev.langchain4j.model.mistralai.MistralAiStreamingChatModel;
import dev.langchain4j.service.AiServices;
import dev.langchain4j.service.TokenStream;

public class MemoryStreamingChatbot {

  private static final Logger _LOG = LoggerFactory.getLogger(MemoryStreamingChatbot.class);
  private static final String OVH_AI_ENDPOINTS_ACCESS_TOKEN = System.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN");
  private static final String OVH_AI_ENDPOINTS_MODEL_NAME = System.getenv("OVH_AI_ENDPOINTS_MODEL_NAME");
  private static final String OVH_AI_ENDPOINTS_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_MODEL_URL");

  interface Assistant {
    TokenStream chat(String message);
  }

  public static void main(String[] args) {
    MistralAiStreamingChatModel streamingChatModel = MistralAiStreamingChatModel.builder()
        .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
        .modelName(OVH_AI_ENDPOINTS_MODEL_NAME)
        .baseUrl(OVH_AI_ENDPOINTS_MODEL_URL)
        .maxTokens(1500)
        .build();

    ChatMemory chatMemory = MessageWindowChatMemory.withMaxMessages(10);

    Assistant assistant = AiServices.builder(Assistant.class)
        .streamingChatLanguageModel(streamingChatModel)
        .chatMemory(chatMemory)
        .build();

    _LOG.info("💬: My name is Stéphane.\n");
    TokenStream tokenStream = assistant.chat("My name is Stéphane.");
    _LOG.info("🤖: ");
    tokenStream
        .onNext(_LOG::info)
        .onComplete(token -> {
          _LOG.info("\n💬: What is my name?\n");
          _LOG.info("🤖: ");
          assistant.chat("What is my name?")
              .onNext(_LOG::info)
              .onError(Throwable::printStackTrace).start();
        })
        .onError(Throwable::printStackTrace).start();



  }
}

Run your chatbot

Make sure your environment variables are set:

export OVH_AI_ENDPOINTS_MODEL_NAME=Mistral-7B-Instruct-v0.3
export OVH_AI_ENDPOINTS_MODEL_URL=https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

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 guide.

Then run your Java application:

💬: My name is Stéphane.
🤖: Hello Stéphane, how can I assist you today?

💬: What is my name?
🤖: Your name is Stéphane.

Conclusion

In just a few steps, you have created your own AI chatbot powered by LangChain4j, Quarkus, and OVHcloud 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:

If you need training or technical assistance to implement our solutions, contact your sales representative or click on this link 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, where you can engage with the community and OVHcloud team members.