Delayed completion for embeddings

[Avs-safety]

Hi,

Is it possible to have example code to add a delayed completion for producing embeddings please?

I've read 'How to handle rate limits', however due to a lack of knowledge on my part I'm struggling to add a delayed completion function to the code below.

import openai
from openai.embeddings_utils import get_embedding

size = 'babbage'

df['embeddings'] = df['Narrative Description'].apply(lambda x: get_embedding(x, engine=f'text-search-{size}-doc-001'))

df.head()

Thank you in advance!

[ted-at-openai]

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

[Avs-safety]

That would be great, thank you!

[ted-at-openai]

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

[Datamore]

which python works for example? many error message happened when i was running the codes.

[ted-at-openai]

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