Consider vectorizer the owner of dtype #267
Merged
Conversation
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
Instead of using `dtype`, pass a vectorizer instance to the constructor to specify the vectorizer's dtype.
|
@abrookins looks like we'd still need to do a similar treatment to the |
Ah, yes! Thank you, I'll get on that. |
tylerhutcherson
approved these changes
Jan 31, 2025
tylerhutcherson
approved these changes
Jan 31, 2025
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Outdated suggestions cannot be applied.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.
The
dtypeargument toSemanticCache,SemanticRouter, andSemanticSessionManageris intended to specify the vectorizer's data type. However, the constructors for these classes allow passing in both a vectorizer instance (with dtype already set) anddtype, in which case, the vectorizer may have a differentdtypethan thedtypeused in the index schema.This PR works on eliminating this possibility by adding validation and treating the vectorizer as the true "owner" of
dtype. We also begin the deprecation process for standalonedtypearguments, guiding users to pass in vectorizer instances instead if they require customizing the vectorizer's dtype. Finally, we make vectorizer validation consistent across these classes.