Changement de modele : Mistral 7B

.gitignore

@@ -0,0 +1 @@
+.env

app backup.py

@@ -0,0 +1,91 @@
+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()

app.py

@@ -1,11 +1,26 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+
+from dotenv import load_dotenv
+load_dotenv()  # Charge les variables depuis .env
 
 """
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+For more information on huggingface_hub Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Vérifie si la clé API est définie dans l'environnement (pour local)
+api_token = os.getenv("HF_API_TOKEN")
+
+if api_token:
+    # Local : Utilise la clé API
+    print("Local key found in .env")
+    client = InferenceClient(token=api_token, model="HuggingFaceH4/zephyr-7b-beta")
+else:
+    # Sur Hugging Face Spaces : Pas besoin de clé
+    print("We are on HF, no need API key")
+    client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
+    
 
 def respond(
     message,
@@ -61,4 +76,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

pyproject.toml

@@ -0,0 +1,22 @@
+[tool.poetry]
+name = "gradio-chatbot-test"
+version = "0.1.0"
+description = "Test huggingface"
+authors = ["Guillaume Soto"]
+license = "Open"
+readme = "README.md"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = "^3.12"
+gradio = "^5.5.0"
+huggingface-hub = "^0.26.2"
+python-dotenv = "^1.0.1"
+langchain = "^0.3.7"
+requests = "^2.32.3"
+
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

test.py

@@ -0,0 +1,26 @@
+import requests
+import os
+from dotenv import load_dotenv
+
+# Charger les variables d'environnement depuis .env
+load_dotenv()
+
+# Récupérer la clé API Hugging Face depuis .env
+HF_API_TOKEN = os.getenv("HF_API_TOKEN")
+
+# URL de l'API d'inférence
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B"
+headers = {"Authorization": f"Bearer {HF_API_TOKEN}"}
+
+# Fonction pour envoyer une requête
+def query(payload):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.json()
+
+# Test du modèle avec un exemple simple
+output = query({
+    "inputs": "What are the benefits of artificial intelligence in education?",
+})
+
+# Afficher le résultat
+print(output)