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Outdated suggestions cannot be applied.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.
This moves from the custom solution for vector searching on Postgres, instead using the SK memory feature to do it. Added some new SK dependencies for the memory (and PG memory store), then removed the Embedding column from the current data model, as there is a new table with all that in it.
Refactored the seed logic to load the memory store using the previously generated embeddings.
Changed the CatalogAPI route to use the ISemanticTextMemory search feature to search memory, rather than the custom SQL query. This does mean we don't get distance surfaced, also, pagination is currently lost and SK memory doesn't support that (we could roll that ourselves if we want).
Included a fix so that AOAI can be deployed (issue #280), and pgadmin for easier debugging of the data in the database.
Fixes #282