v0.11.5

• remove packing flags from fine_tunes.create
• remove recommended batch sizes from data prep tool (default batch sizes now set server-side)

v0.11.4

• Answers and Classification endpoints now have their own prepare_data functions, similar to search
• Moved the utils file used in the embeddings examples to embeddings_utils. This will allow the code to be imported
• Changed the default api_prefix to be "" and instead moved that logic into init.py. You might need to update any local OPENAI_API_BASE that you've set.

v0.11.3

• Hotfix to deal with missing import

v0.11.2

• Accept URLs as train/validation files in the fine-tuning CLI command
• Minor fixes to files.create and fine_tunes.create CLI commands

v0.11.1

• add examples/embeddings for embedding tutorial notebooks
• add examples/finetuning Olympics Q&A fine-tuning tutorial notebooks
• Fix batch size estimation for small dataset sizes

v0.10.5

Adds endpoint support for /embeddings endpoint which is being tested in a closed alpha.

v0.10.4

Adds endpoint support for /search_indices endpoints which are being tested in a closed alpha.
Adds versioning to existing engine search endpoint to use improved search v2 functionality. Also being tested in closed alpha.

v0.10.3

add backtranslation codex example
add rudimentary answers implementation with a custom fine-tuned model
add batch_size suggestion within fine_tunes.prepare_data

v0.10.2

• Improvements to the CLI data_preparation tool

v0.10.1

• Removing unused arguments