Update app.py

app.py

@@ -2,21 +2,10 @@ import gradio as gr
 import os
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
-import subprocess
-import sys
+from fastapi import FastAPI
+from pydantic import BaseModel
+import uvicorn
 
-
-subprocess.run([
-    sys.executable, "-m", "pip", "install",
-    "llama-cpp-python",
-    "--extra-index-url", "https://abetlen.github.io/llama-cpp-python/whl/cpu",
-    "--quiet"
-], check=True)
-
-import gradio as gr
-import os
-from huggingface_hub import hf_hub_download
-from llama_cpp import Llama
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
 SYSTEM_PROMPT = """Tu es l'assistant SAV officiel du Centre Chery Tunisie.
@@ -26,7 +15,7 @@ Réponds uniquement aux questions liées aux véhicules Chery."""
 print("⏳ Downloading GGUF model...")
 model_path = hf_hub_download(
     repo_id="dali4444444/chery-sav-chatbot-gguf",
-    filename="chery-sav-chatbot-q4_k_m.gguf",  # ⚠️ update after checking exact filename
+    filename="chery-sav-chatbot-q4_k_m.gguf",
     token=HF_TOKEN
 )
 
@@ -39,12 +28,14 @@ llm = Llama(
 )
 print("✅ Model ready!")
 
-
 def chat(message, history):
     messages = [{"role": "system", "content": SYSTEM_PROMPT}]
     for h in history:
-        messages.append({"role": "user", "content": h[0]})
-        messages.append({"role": "assistant", "content": h[1]})
+        if isinstance(h, dict):
+            messages.append({"role": h["role"], "content": h["content"]})
+        else:
+            messages.append({"role": "user", "content": h[0]})
+            messages.append({"role": "assistant", "content": h[1]})
     messages.append({"role": "user", "content": message})
 
     response = llm.create_chat_completion(
@@ -55,13 +46,18 @@ def chat(message, history):
     )
     return response["choices"][0]["message"]["content"]
 
+app = FastAPI()
 
-demo = gr.ChatInterface(
-    fn=chat,
-    title="🚗 Chery SAV Assistant",
-    description="Posez vos questions sur vos véhicules Chery en français ou en arabe tunisien."
-)
+class ChatRequest(BaseModel):
+    message: str
+    history: list = []
+
+@app.post("/api/chat")
+async def api_chat(req: ChatRequest):
+    return {"reply": chat(req.message, req.history)}
+
+demo = gr.ChatInterface(fn=chat, title="🚗 Chery SAV Assistant")
+app = gr.mount_gradio_app(app, demo, path="/")
 
 if __name__ == "__main__":
-    port = int(os.environ.get("PORT", 7860))
-    demo.launch(server_name="0.0.0.0", server_port=port)
+    uvicorn.run(app, host="0.0.0.0", port=7860)