[BREAKING_CHANGES] convert EmbeddingModel to string type #629
Conversation
This file contains 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
This gives the user the ability to pass in models for embeddings that are not already defined in the library. Also more closely matches how the completions API works.
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #629 +/- ##
==========================================
- Coverage 98.44% 98.43% -0.02%
==========================================
Files 24 24
Lines 1354 1342 -12
==========================================
- Hits 1333 1321 -12
Misses 15 15
Partials 6 6 ☔ View full report in Codecov by Sentry. |
|
@jaffee thank you so much for the PR! (and sorry for taking so long to review) |
sashabaranov
approved these changes
Jan 15, 2024
|
thanks @sashabaranov 🙏 . Lovely library, appreciate you. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This gives the user the ability to pass in models for embeddings that are not already defined in the library. Also more closely matches how the completions API works.
Describe the change
Addresses the issue described in #602 essentially that forcing embedding model to be represented as an int is awkward.
Provide OpenAI documentation link
The integer representation is never used by openai, only the string https://platform.openai.com/docs/api-reference/embeddings
Describe your solution
Gets rid of the extra layer of indirection and uses the string value directly.
Tests
This mostly ended up deleting code, and so deleted the associated test as well.
Additional context
Add any other context or screenshots or logs about your pull request here. If the pull request relates to an open issue, please link to it.
Issue: #602