Create app.py

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+MODEL_NAME = "dali4444444/chery-sav-chatbot"
+
+print("Loading model...")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float32,  # CPU uses float32
+    device_map="cpu"
+)
+print("✅ Model ready!")
+
+SYSTEM_PROMPT = "Tu es l'assistant SAV officiel du Centre Chery Tunisie. Tu réponds en français ou en arabe dialectal tunisien selon la langue du client."
+
+def chat(message, history):
+    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
+    
+    # Add conversation history
+    for h in history:
+        messages.append({"role": "user", "content": h[0]})
+        messages.append({"role": "assistant", "content": h[1]})
+    
+    messages.append({"role": "user", "content": message})
+    
+    inputs = tokenizer.apply_chat_template(
+        messages, tokenize=True, 
+        add_generation_prompt=True, 
+        return_tensors="pt"
+    )
+    
+    with torch.no_grad():
+        outputs = model.generate(
+            inputs, max_new_tokens=300, 
+            temperature=0.7, do_sample=True
+        )
+    
+    response = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
+    return response
+
+# Also expose as REST API for your app
+import json
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+app_api = FastAPI()
+
+class ChatRequest(BaseModel):
+    message: str
+    history: list = []
+
+@app_api.post("/api/chat")
+async def api_chat(req: ChatRequest):
+    response = chat(req.message, req.history)
+    return {"reply": response}
+
+# Gradio UI (for testing)
+demo = gr.ChatInterface(fn=chat, title="Chery SAV Assistant")
+
+if __name__ == "__main__":
+    demo.launch()