change prompt

utils/generator.py

@@ -191,7 +191,9 @@ async def _call_llm(messages: list) -> str:
     try:
         # Use async invoke for better performance
         response = await chat_model.ainvoke(messages)
-        return response.content.strip()
+        print(response)
+        return response.content
+        #return response.content.strip()
     except Exception as e:
         logging.exception(f"LLM generation failed with provider '{PROVIDER}' and model '{MODEL}': {e}")
         raise
@@ -222,7 +224,7 @@ def build_messages(question: str, context: str) -> list:
                 * Do not just summarize each passage one by one. Group your summaries to highlight the key parts in the explanation.
                 * Use bullet points and lists when it makes sense to improve readability.
                 * You do not need to use every passage. Only use the ones that help answer the question.
-        - Format your response properly: Ensure proper formatting with appropriate line breaks, spacing, and structure. Use markdown formatting when applicable (bullet points, numbered lists, headers) to make your response clear and easy to read.
+        - Format your response properly: Use markdown formatting (bullet points, numbered lists, headers) to make your response clear and easy to read. Example: <br> for linebreaks 
         
         Input Format:
         - Query: {query}