Update app.py

app.py

@@ -145,7 +145,7 @@ def generate_llama_response(query, context=None):
         input_text += f"Context: {context}\n"
     input_text += "Answer:"
     inputs = tokenizer(input_text, return_tensors="pt")
-    outputs = model.generate(inputs["input_ids"], max_length=20, temperature=0.7)
+    outputs = model.generate(inputs["input_ids"], max_length=40, temperature=0.7)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response