The community member is querying about the use of examples related to Uber/Lyft financials and MSFT/GOOG financials, which they find confusing and counterproductive for their current domain. They are asking if there is a way to avoid this example stage or provide an alternative set of examples.
In the comments, another community member suggests a way to get and update the prompts being used by the query engine, and provides a link to more information on prompt customization.
Uber/Lyft EBITDA/Financials etc. are completely outside the scope of the domain I'm querying.
And these examples are reasonably confusing the question process. So I see prompts being sent to the LLM about financials for MSFT/GOOG. This makes sense if those examples are sent, but counterproductive.
Is there any way to avoid this example stage, or provide an alternative set of examples?
You can get all the prompts being used by your engine like this:
Plain Text
# Get all the prompts being used by your engine
prompts_dict = query_engine.get_prompts()
print(prompts_dict)
# Then you can update the prompt like this
query_engine.update_prompts(
{"response_synthesizer:summary_template": new_summary_tmpl}
)
