Aung/fix text tokens and image tokens not documented or typed#2775
Open
NikkiAung wants to merge 1 commit intoopenai:mainfrom
Open
Aung/fix text tokens and image tokens not documented or typed#2775NikkiAung wants to merge 1 commit intoopenai:mainfrom
NikkiAung wants to merge 1 commit intoopenai:mainfrom
Conversation
NikkiAung
force-pushed
the
aung/fix-text_tokens-and-image_tokens-not-documented-or-typed
branch
from
d6baa87 to
a4edc95
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changes being requested
In your IDE without definition:
details = response.usage.prompt_tokens_details
details.text_ # ← No autocomplete!
details.text_tokens # ← Type checker error!
In your IDE with definition:
details = response.usage.prompt_tokens_details
details.text_ # ← IDE autocompletes to "text_tokens"! ✅
details.text_tokens # ← Type checker OK! ✅
Additional context & links
Since below code is allowing extra fields, we can still access the image_tokens and text_tokens, but it's not good practice knowing that '
text_tokens' and 'image_tokens' is obviously available inside 'prompt_tokens_details'To test this, need to use gpt-4o-audio model (gpt-4o-audio-preview) with kaggle audio dataset to make mini audio_to_text.py to be able to output 'text_tokens' and 'image_tokens' inside 'prompt_tokens_details'
Next Step
Updating in one of the example documentations here to include
text_tokensandimage_tokeninsideusage>prompt_tokens_detailsFixed #2554