Add CohereVectorizer for Embed 3 #410
Merged
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
|
LGTM |
okhat
reviewed
Feb 21, 2024
|
Hey @aidangomez , thanks so much for this PR! Looks great. I just moved import cohere inside the constructor to avoid breaking when it's not installed |
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Outdated suggestions cannot be applied.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.
Adds a new vectorizer for Cohere's Embed models analogous to OpenAIVectorizer. Details on the performance of the Embed 3 model can be found here
Of note, the Vectorizer interface doesn't specify whether a query versus a document is being embedded, but Cohere's embedding models produce different embeddings depending on the content you want to embed. The different options are in the docs, but taking this into account can product a fairly dramatic boost to performance.