Ted Sanders

No plans for a local model. (That would be more complicated to get working than an API call.) What are the pain points you'd like to see fixed?

I'm sorry, that's annoying. How frequently are you hitting it? Can you do exponential backoff and resume? Will escalate to eng team.

Here's a script I wrote for mass processing embeddings in case it's helpful: https://github.com/openai/openai-cookbook/blob/main/examples/api_request_parallel_processor.py

> BTW I'd love to talk to someone at OpenAI about deploying the movie recommendation app I've made with this 😉 Any chance you can put me in contact with...

If no one else gets to this, I'll commit to take a look next week. Apologies for the delays and thanks for your patience. We really do appreciate your contribution.

Now that GPT-4 has launched, I now have time to get to this. Thanks for your patience over the past few weeks. :) I tried running the example, but hit...

Awesome, it works now.

Looks great and I'm happy to merge. Can I ask for one small change before merging: - Change name to `Visualizing_embeddings_with_Atlas.ipynb` The benefit of this name is that this way...

Sweet. Merging now. Thanks for your patience with us (me).

Option 1: Use a newer version of Python (3.9+). Option 2: Delete the type hints in the function definitions. The error is coming from the type hints; e.g., "-> List[int]".