[headers] Allow user provided headers in completion (openai#116) (ope…

…nai#71)

ted-at-openai/update-embedding-examples (openai#67)

* updates embeddings examples

* updates README with new example notebook using embeddings for recommendation

Add an option to use Azure endpoints for the /completions & /search o…

…perations. (openai#45)

* Add an option to use Azure endpoints for the /completions operation.

* Add the azure endpoints option for the /search operation + small fixes.

* errata

* Adressed CR comments

Version 11.6 diff (openai#66)

* Hallacy/pickleable exceptions (openai#109)

* Exceptions in python are hard to pickle.  Make Exceptions pickleable

* Remove debug

* Added tests

* nit

* Change embeddings call to openai.Embedding.create (openai#110)

* Change embeddings call to openai.Embedding.create

* And update model names

* Untweak notebook

* Support encoded embeddings response (openai#111)

* Support encoded embeddings response

* Removed imports

* Add a couple of comments

* Typo

* Remove CA bundle (openai#112)

* Remove CA bundle

* Removed some references

Remove packing and default batch size from FT cli (openai#60)

Hallacy/11 4 release (openai#54)

* Make embeddings_utils be importable (openai#104)

* Make embeddings_utils be importable

* Small tweaks to dicts for typing

* Remove default api_prefix and move v1 prefix to default api_base (openai#95)

* make construct_from key argument optional (openai#92)

* Split search.prepare_data into answers/classifications/search versions (openai#93)

* Break out prepare_data into answers, classifications, and search

* And cleaned up CLI

* Validate search files (openai#69)

* Add validators for search files

* Clean up fields

Co-authored-by: kennyhsu5 <[email protected]>
Co-authored-by: Madeleine Thompson <[email protected]>

Add necessary import (openai#51)

* Add necessary import

* version

[fine-tuning] accept file URLs as train & validation files (openai#50)

also a few fixes: setting the correct filename for file uploads using files.create, reinstating the progress meter for uploading files in conjunction with the fine-tuning endpoint, standardizing punctuation on FT help strings

Boris/embedding examples (openai#49)

* add Olympics Q&A fine-tuning tutorial notebooks

* fix batch calculation for very small datasets

* Add embeddings tutorial notebooks

Add embeddings endpoint (openai#85) (openai#36)