Update app.py

app.py

@@ -3,23 +3,34 @@ from pydantic import BaseModel
 from typing import Optional
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
+from transformers import BitsAndBytesConfig  # เพิ่มการ import นี้
+import logging
+
+# ตั้งค่า logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-model_name = "scb10x/llama-3-typhoon-v1.5-8b-instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+try:
+    model_name = "scb10x/llama-3-typhoon-v1.5-8b-instruct"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# ใช้ BitsAndBytes สำหรับ quantization
-config = AutoConfig.from_pretrained(model_name)
-config.quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+    # ใช้ BitsAndBytes สำหรับ quantization
+    config = AutoConfig.from_pretrained(model_name)
+    config.quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
-# โหลดโมเดลด้วย 8-bit quantization
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    config=config,
-    device_map="auto",
-    torch_dtype=torch.float16,
-)
+    # โหลดโมเดลด้วย 8-bit quantization
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        config=config,
+        device_map="auto",
+        torch_dtype=torch.float16,
+    )
+    logger.info("Model loaded successfully")
+except Exception as e:
+    logger.error(f"Error loading model: {str(e)}")
+    raise
 
 class Query(BaseModel):
     queryResult: Optional[dict] = None
@@ -44,6 +55,7 @@ async def webhook(query: Query):
         
         return {"fulfillmentText": ai_response}
     except Exception as e:
+        logger.error(f"Error in webhook: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e))
 
 if __name__ == "__main__":