Update app.py

app.py

@@ -119,7 +119,7 @@ class DocumentRetrievalAndGeneration:
         # prompt = f"Query: {query}\nSolution: {content}\n"
 
         # Encode and prepare inputs
-        messages = [{"role": "user", "content": prompt}]
+        messages = [{"role": "user", "content": prompt2}]
         encodeds = self.llm.tokenizer.apply_chat_template(messages, return_tensors="pt")
         model_inputs = encodeds.to(self.llm.device)