Update app.py

app.py

@@ -1,7 +1,23 @@
 from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
 app = FastAPI()
 
-@app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+# Replace with your actual model repo
+MODEL_NAME = "fansa34/finetunedModel"
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+class AskRequest(BaseModel):
+    question: str
+
+@app.post("/ask")
+def ask(req: AskRequest):
+    inputs = tokenizer(req.question, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"answer": answer}