feat: Postgres pgvector backed index #315
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
jamescalam
changed the title
|
@itsfrankjames thanks for the PR, we'll review — I also agree with you on the |
…feat-index-postgres-pgvector
…es/semantic-router into feat-index-postgres-pgvector
|
@itsfrankjames sorry for the delay, I'm merging into a local PR for testing, will update you again soon |
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Outdated suggestions cannot be applied.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
Implementation of #314 - Postgres pgvector Index.
This implementation reflects the capabilities in the BaseIndex.
I've added a single optional dependency: psycopg3
A judicious review would be appreciated as I haven't written any production Python in a long time.
Random thoughts
I don't love that the Indexes other than Local require 'dimensions' to be set when instantiated, but the object is passed to RouteLayer as a sibling of the Encoder class.
This requires that the user know the dimensions of their embeddings despite that being an implementation detail of the encoder. Might open a seperate issue.