Update utils/generation.py

utils/generation.py

@@ -66,7 +66,7 @@ def generate_answer(query, retrieved_chunks, model=model, tokenizer=tokenizer):
     
     prompt = (f"You are a telecom regulations expert. Using the following context, answer the question:\n\n"
               f"Context:\n{context}\n\n"
-              f"Question: {query}\nAnswer:")
+              f"Question: {query}\n\n")
               
     model_type = "seq2seq" if getattr(model.config, "is_encoder_decoder", False) else "causal"
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")