feat: add Vector Search indexers and retrievers to Vertex AI plugin #519
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
ab71154
to
c33639e
Compare
45b48da
to
8e3b0aa
Compare
8e3b0aa
to
be7cc48
Compare
Ehesp
reviewed
Jul 4, 2024
ssbushi
reviewed
Jul 4, 2024
ssbushi
reviewed
Jul 4, 2024
ssbushi
reviewed
Jul 4, 2024
ssbushi
reviewed
Jul 4, 2024
ssbushi
reviewed
Jul 4, 2024
pavelgj
reviewed
Jul 9, 2024
pavelgj
reviewed
Jul 9, 2024
f7a43ea
to
372313b
Compare
4d489b2
to
51c0c8f
Compare
51c0c8f
to
f7ed986
Compare
ssbushi
reviewed
Jul 16, 2024
| let retrievers: RetrieverAction<z.ZodTypeAny>[] = []; | ||
|
|
||
| if (options?.vectorSearchIndexOptions) { | ||
| const defaultEmbedder = embedders[0]; |
There was a problem hiding this comment.
Should we also let the user specify an embedder (rather than always using a default one)?
There was a problem hiding this comment.
We should be, though i could have made this more obvious -
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
ssbushi
reviewed
Jul 16, 2024
| options?: Options | ||
| ) => Promise<string[]>; | ||
|
|
||
| export interface VectorSearchIndexOption< |
There was a problem hiding this comment.
Optional: Have you considered naming this VectorSearchOptions? The inclusion of Index might suggest that this is only relevant for indexing and not retrieving. Although Index here means a DB index I suppose (rather than the act of indexing).
WDYT?
cc: @pavelgj
ssbushi
reviewed
Jul 16, 2024
js/plugins/vertexai/tests/vector-search/query_public_endpoint_test.ts
Outdated
Show resolved
Hide resolved
ssbushi
reviewed
Jul 16, 2024
js/plugins/vertexai/tests/vector-search/query_public_endpoint_test.ts
Outdated
Show resolved
Hide resolved
ssbushi
reviewed
Jul 16, 2024
js/plugins/vertexai/tests/vector-search/upsert_datapoints_test.ts
Outdated
Show resolved
Hide resolved
ssbushi
reviewed
Jul 16, 2024
|
Thanks @cabljac for adding out-of-the-box indexers/retrievers and test coverage :) I left a few comments on you latest updates. |
664b595
to
3023575
Compare
3023575
to
362673e
Compare
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.
This PR adds Vertex AI Vector Store to the Vertex AI plugin. There are some design decisions still to be made, as VVS works differently to other vector databases (in that it doesn't store metadata, only ids and the feature vectors)
I have included a samples for BigQuery, Firestore, and a Custom local document store (just in a JSON file)