Find answers from the community

Updated 3 months ago

Logan M For a QA retrieval query engine

BBorg1903

For a QA retrieval query_engine.query() method, how do I get logs or trace of all the prompts and inputs to the LLM llama index makes when generating the answer. I am using the default response mode btw,
I swear I saw this somewhere before but I am unable to find it now.

3 comments

WWhiteFang_Jr

I think this can help
https://gpt-index.readthedocs.io/en/latest/examples/callbacks/LlamaDebugHandler.html

BBorg1903

Sorry. I just checked the documentation. That should do it.

Thanks a ton for the help. I will try it out.

LLogan M

You can also do

Plain Text

import openai
openai.log = "debug"

Or if you aren't using openai

Plain Text

import llama_index

llama_index.set_global_handler("simple")

Add a reply