Update app.py

app.py

@@ -1,5 +1,10 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from gradio_client import Client
+
+
+# Se connecter au Space qui expose le MCP
+mcp_client = Client("HackathonCRA/mcp")
 
 
 def respond(
@@ -12,26 +17,25 @@ def respond(
     hf_token: gr.OAuthToken,
 ):
     """
-    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
+    Chat client qui envoie d'abord au modèle HF, et qui peut ensuite
+    appeler le MCP via gradio_client si besoin.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    llm = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
+    for msg in llm.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = msg.choices
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
@@ -39,10 +43,12 @@ def respond(
         response += token
         yield response
 
+    # 👉 Exemple : appel au MCP (ici on appelle une fn "search_docs" du serveur)
+    # tu adaptes en fonction de ce que ton serveur expose comme endpoints
+    result = mcp_client.predict("ma requête", api_name="/search_docs")
+    yield f"\n\n[MCP result] {result}"
+
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -50,13 +56,7 @@ chatbot = gr.ChatInterface(
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )