Update app.py

app.py

@@ -1,44 +1,20 @@
-from fastapi import FastAPI, HTTPException, Request
-from fastapi.responses import JSONResponse
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from typing import Optional
-from huggingface_hub import InferenceClient
-import uvicorn
-from fastapi.middleware.cors import CORSMiddleware
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
 app = FastAPI()
 
-# CORS middleware
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],  # หรือระบุเจาะจง ["GET", "POST", "OPTIONS"]
-    allow_headers=["*"],
-)
+# โหลดโมเดลและ tokenizer
+model_name = "scb10x/llama-3-typhoon-v1.5-8b-instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
-# Hugging Face client
-client = InferenceClient("scb10x/llama-3-typhoon-v1.5-8b-instruct")
-
-# Pydantic model for query
 class Query(BaseModel):
     queryResult: Optional[dict] = None
     queryText: Optional[str] = None
 
-# Root route
-@app.get("/")
-async def root():
-    return {"message": "Welcome to the API"}
-
-@app.options("/webhook")
-async def webhook_options():
-    return {"message": "OK"}
-
-@app.get("/test")
-async def test():
-    return {"message": "Test successful"}
-
-# Webhook route
 @app.post("/webhook")
 async def webhook(query: Query):
     try:
@@ -47,24 +23,16 @@ async def webhook(query: Query):
         if not user_query:
             raise HTTPException(status_code=400, detail="No query text provided")
         
-        messages = [
-            {"role": "system", "content": "You are a friendly Chatbot."},
-            {"role": "user", "content": user_query}
-        ]
+        # สร้าง prompt และ generate ข้อความ
+        prompt = f"Human: {user_query}\nAI:"
+        input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
         
-        response = client.chat_completion(
-            messages,
-            max_tokens=512,
-            temperature=0.7,
-            top_p=0.95,
-        )
+        output = model.generate(input_ids, max_new_tokens=100, temperature=0.7)
+        response = tokenizer.decode(output[0], skip_special_tokens=True)
         
-        model_reply = response.choices[0].message.content.strip()
+        # แยกส่วนที่เป็นคำตอบของ AI
+        ai_response = response.split("AI:")[-1].strip()
         
-        return {"fulfillmentText": model_reply}
+        return {"fulfillmentText": ai_response}
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
-
-# Run the app
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+        raise HTTPException(status_code=500, detail=str(e))