fix(gemini): resolve embedding dimensions dynamically instead of hardcoding#1513
Open
McTr0 wants to merge 1 commit into0xPlaygrounds:mainfrom
Open
fix(gemini): resolve embedding dimensions dynamically instead of hardcoding#1513McTr0 wants to merge 1 commit into0xPlaygrounds:mainfrom
McTr0 wants to merge 1 commit into0xPlaygrounds:mainfrom
Conversation
…coding Previously ndims() was hardcoded to return 768 regardless of the actual model or user configuration. This caused dimension mismatches when using gemini-embedding-001 (native default: 3072) with downstream vector stores. Changes: - Add model_default_ndims() lookup (EMBEDDING_001=3072, EMBEDDING_004=768) - Change ndims field from Option<usize> to usize - Resolve dimensions in make(): user-specified > model default > 768 - ndims() now returns self.ndims directly (matching OpenAI pattern) BREAKING CHANGE: EmbeddingModel::new() and with_model() now take usize instead of Option<usize> for the ndims parameter. Closes 0xPlaygrounds#452
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously ndims() was hardcoded to return 768 regardless of the actual model or user configuration. This caused dimension mismatches when using gemini-embedding-001 (native default: 3072) with downstream vector stores.
Changes:
Add model_default_ndims() lookup (EMBEDDING_001=3072, EMBEDDING_004=768)
Change ndims field from Option to usize
Resolve dimensions in make(): user-specified > model default > 768
ndims() now returns self.ndims directly (matching OpenAI pattern)
BREAKING CHANGE: EmbeddingModel::new() and with_model() now take usize instead of Option for the ndims parameter.
Relates to #452