Update app.py

app.py

@@ -1,25 +1,25 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, Request, HTTPException
+import requests
+import os
 from pydantic import BaseModel
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
 
 app = FastAPI()
 
+
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
+HF_TOKEN = os.getenv("HF_API_KEY")  # Load from environment variable
+headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+
+
 class PromptRequest(BaseModel):
     prompt: str
 
-# Load small LLaMA 3.2B model (or any other compatible)
-MODEL_NAME = "TheBloke/Llama-3-OpenOrca-2.2B-GGUF"
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
-
-@app.get("/")
-def root():
-    return {"message": "LLaMA 3.2B API for QuizForge is live!"}
 
 @app.post("/generate")
-def generate_text(data: PromptRequest):
-    inputs = tokenizer(data.prompt, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=1024)
-    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return {"response": output_text}
+async def generate_text(data: PromptRequest):
+    try:
+        response = requests.post(API_URL, headers=headers, json={"inputs": data.prompt})
+        response.raise_for_status()
+        return response.json()
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))