Embedding Normalization Options #8145
Open
+140
−44
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
Branch: LegacyEmbeddingsNormalization Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
…Handler The default normalization behavior remains the same (true for embed, false for embeddings), but this allows users to specify the behavior they want. Branch: LegacyEmbeddingsNormalization Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Also include notes about the discrepency between embed and embeddings with default behavior. Branch: LegacyEmbeddingsNormalization Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Branch: LegacyEmbeddingsNormalization Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
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Outdated suggestions cannot be applied.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.
Description
This PR introduces the new API parameter
normalizefor the/api/embedand/api/embeddingsendpoints that allow the user to explicitly enable/disable normalization. The default behavior of both endpoints is preserved (normalization forembed, no normalization forembeddings), but this allows them to produce equivalent output to avoid future confusion.Issues
Discussion
The
/api/embeddingsendpoint is deprecated according to the docs. An argument could be made that we should not add this functionality to this endpoint and simply document around the discrepancy. I'd be totally open to this!Testing
I updated the
embed_test.goto include the various combinations againstembedandembedding. I ran them as follows: