@PostMapping("/jlama") // Endpoint for JLama chat functionality
public ResponseEntity chatJlama(@RequestBody ChatPromptRequest request) {
    PromptContext context;
    if (abstractModel.promptSupport().isPresent()) {
        context = abstractModel.promptSupport()
                .get()
                .builder()
                .addSystemMessage("You are a helpful chatbot providing concise answers.")
                .addUserMessage(request.prompt())
                .build();
    } else {
        context = PromptContext.of(request.prompt());
    }

    System.out.println("Prompt: "   context.getPrompt()   "\n");
    Generator.Response response = abstractModel
            .generate(UUID.randomUUID(), context, 0.0f, 256, (s, f) -> {});
    System.out.println(response.responseText);

    return ResponseEntity.ok(new ChatPromptResponse(response.responseText));
}

// Defining the model and directory for downloading (if needed) from Hugging Face
String model = "tjake/Llama-3.2-1B-Instruct-JQ4";
String workingDirectory = "./models";

// Downloading (if necessary) or retrieving the model locally
File localModelPath = new Downloader(workingDirectory, model).huggingFaceModel();

// Loading the model
ModelSupport.loadModel(localModelPath, DType.F32, DType.I8);

تستخدم نقطة النهاية هذه Langchain ، مما يقلل من الكود المطلوب لتفاعل Jlama.

@PostMapping("/langchain")
public ResponseEntity