Update app.py

app.py

@@ -1,26 +1,23 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForCausalLM
+import os
 
 model_name = "meta-llama/Llama-3.1-8B-Instruct"
 
-# Use the Hugging Face token
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
-model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=True)
+# Use the Hugging Face token from the environment variable
+hf_token = os.getenv("HF_TOKEN")
+tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
 
-# Initialize FastAPI
 app = FastAPI()
 
-# Define request and response models
 class Prompt(BaseModel):
     text: str
 
 @app.post("/generate")
 def generate_text(prompt: Prompt):
-    try:
-        inputs = tokenizer(prompt.text, return_tensors="pt")
-        outputs = model.generate(**inputs, max_length=100)
-        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return {"generated_text": generated_text}
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error generating text: {str(e)}")
+    inputs = tokenizer(prompt.text, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=100)
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"generated_text": generated_text}