Update app.py

app.py

@@ -1,20 +1,21 @@
 from fastapi import FastAPI
 from pydantic import BaseModel
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-# FastAPI uygulaması başlat
 app = FastAPI()
 
-# Modeli sadece CPU'da çalışacak şekilde yükle
-generator = pipeline("text2text-generation", model="memorease/memorease-quizgen", device=-1)
+# MODELİ VE TOKENIZER'I YÜKLE (CPU için)
+model = AutoModelForCausalLM.from_pretrained("memorease/memorease-quizgen")
+tokenizer = AutoTokenizer.from_pretrained("memorease/memorease-quizgen")
 
-# API'ye gönderilecek istek yapısı
 class Memory(BaseModel):
     description: str
 
-# POST endpoint: /generate
 @app.post("/generate")
 def generate(memory: Memory):
     prompt = f"Soru üret: {memory.description}"
-    result = generator(prompt, max_length=64, do_sample=False)
-    return {"question": result[0]["generated_text"]}
+    inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=128)
+    outputs = model.generate(**inputs, max_new_tokens=64)
+    question = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"question": question}