Ted Sanders

Closing this issue as I still don't know what you're running or what's terminating. Happy to help if you can explain in more detail.

Currently it's left as an exercise to the reader. I'll try to add something next week.

I'm going to close this because I don't think we're going to get to it, unfortunately. Best wishes.

I unfortunately don't have time to help you debug, but I can offer a few pointers. The error about the truth value of a series being ambiguous makes it sound...

I will take a look at this. Thanks for flagging. I believe it worked for me (also Python 3.9), but I will do a rewrite for gpt-3.5 and verify the...

The rewrite was completed in April. Will close this issue.

Yes, I've written an example script and will share it later today (or Monday at the latest).

Here's an example parallel processing script that will automatically throttle to stay under rate limits: https://github.com/openai/openai-cookbook/blob/main/examples/api_request_parallel_processor.py

I used Python 3.9. Apologies for the lack of versioning - I know that type hints especially can break 3.7 and earlier.

>Should we renorm the embedding vector after doing the weighted average? 🤔 Good idea - I'll do that now. I also committed some changes above to polish the text. I...