Update app.py

app.py

@@ -62,4 +62,31 @@ def predict(request: QueryRequest):
     return {
         "question": request.question,
         "answer": answer
+    }
+
+
+
+
+@app.get("/answers")
+def predict(question: str = Query(..., description="The question to ask"), max_new_tokens: int = Query(50, description="Max new tokens to generate")):
+    # Tokenize the input question
+    inputs = tokenizer(question, return_tensors="pt")
+
+    # Generate output from model
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        pad_token_id=tokenizer.eos_token_id,
+        return_dict_in_generate=True
+    )
+
+    # Decode output
+    answer = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+
+    return {
+        "question": question,
+        "answer": answer
     }