Robert Brennan
Robert Brennan
@NancyEdelMary I don't think your `LLM_MODEL` is a valid one. The valid ones are here: https://docs.litellm.ai/docs/providers/azure I would expect to see `LLM_MODEL=azure/gpt-4` or `LLM_MODEL=azure/gpt-3.5-turbo-16k`. Where did you see `gpt35exploration`?
where did the string `gpt-35-turbo` come from? Why is that in the logs?
This is looking great! Seems like a big improvement as-is, so I'd be game to figure out the embedding stuff in a future PR
I'm able to repro. Investigating 👀
@1of13 please try to be a little more polite 😄 we're all working for free here. We are actively discussing what the best package manager is. Python package management is...
OK I think I miscommunicated what I want to see here 😄 I want it to look like the AI is typing live, like it does with ChatGPT 
> i have a small doubt when i create a pull request here and commit to the branch in my forked repo, why does it show like 9 commits ahead...
Would be good to have this behavior for both chat messages and for the terminal
> Ok thanks for the comfirmation so when you merge my pull request the 9 commits head of would disappear right yup exactly
I'd suggest using checkboxes, so we can track our progress over time. Could probably also just use ~~strike~~ to cross off completed items