app backup.py

import gradio as gr
from huggingface_hub import InferenceClient
import os
from dotenv import load_dotenv

# Charger les variables d'environnement
load_dotenv()

# Vérifie si la clé API est définie dans l'environnement
api_token = os.getenv("HF_API_TOKEN")
model_name = "mistralai/Mistral-7B-Instruct-v0.3"

if not api_token:
    raise ValueError("API token is required. Please set it in your .env file.")

# Initialiser le client d'inférence
client = InferenceClient(token=api_token, model=model_name)

# Fonction de réponse
def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    for user, assistant in history:
        if user:
            messages.append({"role": "user", "content": user})
        if assistant:
            messages.append({"role": "assistant", "content": assistant})

    messages.append({"role": "user", "content": message})

    response = ""
    try:
        for message in client.chat_completion(
            messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p
        ):
            token = message.choices[0].delta.content
            response += token
            yield response
    except Exception as e:
        yield f"Error: {str(e)}"

# Interface utilisateur avec Gradio
demo = gr.Blocks()

with demo:
    # Header avec le logo et le slogan
    with gr.Row():
        gr.Image("logo.png", show_label=False, interactive=False, elem_id="logo", scale=1)
        gr.Markdown(
            """
            <div style="text-align: center;">
                <h1 style="color: #0fa86b;">SHAURI</h1>
                <p style="font-size: 16px; color: #000;">Un test avec le modèle Mistral via l'API Hugging Face</p>
            </div>
            """
        )

    # Composant Chatbot
    chatbot = gr.Chatbot(label="Chat History")

    # Zone de saisie utilisateur
    with gr.Row():
        user_input = gr.Textbox(label="Your Message", placeholder="Type your message here...", lines=1)

    # Réglages du système et paramètres
    with gr.Row():
        system_message = gr.Textbox(
            value="You are a friendly Chatbot.",
            label="System Message",
            lines=2,
        )
    with gr.Row():
        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")

    # Interaction entre l'utilisateur et le chatbot
    def handle_message(message, history, system_msg, max_toks, temp, top_p_val):
        if history is None:
            history = []
        for response in respond(message, history, system_msg, max_toks, temp, top_p_val):
            history.append((message, response))
            yield history, ""

    user_input.submit(
        fn=handle_message,
        inputs=[user_input, chatbot, system_message, max_tokens, temperature, top_p],
        outputs=[chatbot, user_input],
    )

if __name__ == "__main__":
    demo.launch()