Conversation
CodeByKarthik
requested changes
Jan 7, 2026
Collaborator
CodeByKarthik
left a comment
CodeByKarthik
left a comment
There was a problem hiding this comment.
Hi James, thanks for your commit. The PR doesn't have any issues and I have left few comments. Let me know your thoughts on this.
I'm thinking this might not be the best way to do it - move the batch/all concepts logic to a method of a generic EmbeddingPipeline?
CodeByKarthik
approved these changes
Mar 3, 2026
Collaborator
CodeByKarthik
left a comment
CodeByKarthik
left a comment
There was a problem hiding this comment.
Looks good to me, thanks James.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Description
Previously, if you don't have a parquet file for embeddings and want to have some in OMOP with PGVector, there wasn't anything to be done about it. This code provides the ability to read from Athena vocabulary CSVs or postgres, create embeddings from some string representation of concepts, then either load them into the db, or write to a parquet file.
I've meant to do this for a while, getting it done was prompted by someone wanting to run lettuce and getting stuck because they couldn't make embeddings
Related Issues or other material
Related #179
Closes #179
Screenshots, example outputs/behaviour etc.
✅ Added/updated tests?