Update app.py

app.py

@@ -1,9 +1,14 @@
+import os
 from fastapi import FastAPI
 from pydantic import BaseModel
 from fastapi.responses import JSONResponse
 from transformers import pipeline
 
-# Load a small, CPU-friendly instruction-following model
+# ✅ Set writable cache location
+os.environ["TRANSFORMERS_CACHE"] = "/data/cache"
+os.makedirs("/data/cache", exist_ok=True)
+
+# ✅ Load model safely
 pipe = pipeline("text2text-generation", model="google/flan-t5-small", max_new_tokens=100)
 
 app = FastAPI()