Update app.py

app.py

@@ -8,14 +8,13 @@ app = FastAPI()
 model = AutoModelForCausalLM.from_pretrained("Hadeel11/fine-tuned-model")
 tokenizer = AutoTokenizer.from_pretrained("Hadeel11/fine-tuned-model")
 
-class Query(BaseModel):
-    question: str
-    contexts: list
 
-@app.post("/predict/")
-async def predict(query: Query):
-    inputs = tokenizer(query.question, return_tensors="pt")
-    outputs = model.generate(**inputs)
-    answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return {"answer": answer}
+
+@app.post("/query/")
+async def query_rag(request: Request):
+    data = await request.json()
+    question = data.get("question", "")
+    contexts = query_qdrant(question, top_k=2)
+    answer = generate_answer(question, contexts)
+    return {"question": question, "contexts": contexts, "answer": answer}