Update app.py

app.py

@@ -1,10 +1,12 @@
 import os
+import requests as req
 from fastapi import FastAPI
 from pydantic import BaseModel
-from huggingface_hub import InferenceClient
 
 app = FastAPI()
-client = InferenceClient(token=os.environ.get("HF_TOKEN"))
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+API_URL = "https://api-inference.huggingface.co/models/google/flan-t5-large"
 
 class Request(BaseModel):
     prompt: str
@@ -15,9 +17,7 @@ def home():
 
 @app.post("/generate")
 def generate_text(request: Request):
-    response = client.chat_completion(
-        messages=[{"role": "user", "content": request.prompt}],
-        model="HuggingFaceH4/zephyr-7b-beta",
-        max_tokens=256
-    )
-    return {"response": response.choices[0].message.content}
+    headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+    payload = {"inputs": request.prompt}
+    response = req.post(API_URL, headers=headers, json=payload)
+    return {"response": response.json()[0]["generated_text"]}