Update app.py

app.py

@@ -36,7 +36,7 @@ def generate_response(query):
     relevant_doc = retrieve_relevant_doc(query)
     input_text = f"Document: {relevant_doc}\n\nQuestion: {query}\n\nAnswer:"
     inputs = llama_tokenizer(input_text, return_tensors="pt").to(device)
-    outputs = llama_model.generate(inputs["input_ids"], max_length=150)
+    outputs = llama_model.generate(inputs["input_ids"], max_length=1024)
     response = llama_tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response