Unify settings for vector and nodestore connections to PostgreSQL#1730
Merged
imartinez merged 3 commits intozylon-ai:mainfrom Mar 15, 2024
Merged
Unify settings for vector and nodestore connections to PostgreSQL#1730imartinez merged 3 commits intozylon-ai:mainfrom
imartinez merged 3 commits intozylon-ai:mainfrom
Conversation
Contributor
|
Published docs preview URL: https://privategpt-preview-80dc3d79-21be-4d6e-953d-904f8fd78592.docs.buildwithfern.com |
imartinez
approved these changes
Mar 15, 2024
Collaborator
imartinez
left a comment
There was a problem hiding this comment.
Makes total sense. Thanks for bringing this improvement. Makes things cleaner and more scalable.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 duel configuration of the postgres connection settings for the nodestore and the vector store has a smell about it. This PR unifies the connection to a postgres database by changing the database mode string from pgvector to postgres.
It has an opinionated configuration for the name of the embedding table, and removes it from the configuration. As the vector table needs to know the embedding model dimension to correctly setup the table, this has been moved into the
embedding:section.It was easier to create a PR than trying to explain all this in a discussion forum.