Allow specifying OPENAI_API_BASE to override API location

[klauern]

Problem

When using the OpenAI models, you can't override where the API points. This is useful for corporate proxies of OpenAI to be able to scope an enterprise's use of API keys more centrally, as OpenAI's interface doesn't give you great tooling to support issuing time-limited API keys, scoped keys, etc.

Proposed Solution

I mentioned this in #245 but if this plugin could use the openai env vars out of the box ($OPENAI_API_KEY and $OPENAI_API_BASE), I wouldn't have to do anything to have this work, as our proxy is a direct mirror.

Additional context

[welcome]

Thank you for opening your first issue in this project! Engagement like this is essential for open source projects! 🤗

If you haven't done so already, check out Jupyter's Code of Conduct. Also, please try to follow the issue template as it helps other other community members to contribute more effectively.

You can meet the other Jovyans by joining our Discourse forum. There is also an intro thread there where you can stop by and say Hi! 👋

Welcome to the Jupyter community! 🎉

[dlqqq]

@klauern I've added support for this in #322, which should add a field allowing you to specify the API base URL. This is visible in the UI right underneath where you select the model. Could you see if you're able to verify the feature in #322? I've included replication steps as a comment on the PR.

[sqlreport]

Can we also add feature to configure REQUESTS_CA_BUNDLE when using chat UI so we can configure with https certificate?

[JasonWeill]

@sqlreport Could you please open a new feature request for REQUESTS_CA_BUNDLE? Thanks!