Ted Sanders

I think this is now fixed (#66). The code runs for me. Let me know if it's still throwing an error for you. If so, I'd guess it's from using...

Will try to fix today. Thanks!

Fixed in #66 . Now the data is updated, and lives in the data folder of the repo.

Moved the data from CDN to repo, so URL is no longer needed. Will close.

There's no perfect solution. What speed are you getting and what speed do you want? One option is to fine-tune a weaker model like ada. Weaker models tend to be...

In general, it will be nearly impossible to guarantee ~100 ms or less with an API call, unfortunately.

I highly recommend following the ideas in this notebook: https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb The fine-tuned Q&A example isn't great and relies on some out of date APIs. Sorry you ran into issues.

Will fix. Thanks!

Sorry, hasn't been at the top of my priority list, even though I'm aware it's a deficiency. If any of you want to fix, I'm happy to accept a PR.

Couple more suggestions: - Add installation instructions for pinecone, weaviate, and qdrant_client, as most people won't have them. I think it's especially valuable here since the package names and import...