Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(amazonaurora): merge amazon aurora vector stores #723

Closed
wants to merge 1 commit into from

Conversation

maxtybar
Copy link
Contributor

@maxtybar maxtybar commented Oct 1, 2024

Fixes #373, #695

Features of this PR:

  1. AmazonAuroraDefaultVector is removed to simplify the construct consumption.
  2. fromExistingAuroraVectorStore() method is added inside AmazonAuroraVectorStore to allow usage of existing Amazon Aurora database.
  3. Fixed pgvector issue from @cdklabs/generative-ai-cdk-constructs: Unable to use Aurora Postgres pgVector for a knowledge base as described in the documentation #695 by substituting pgvector Python module for pg8000 (necessary for Python PostgreSQL connection implementation)
  4. Created additional foundationmodel and moved models.ts outside of bedrock construct to remove potential circular dependencies. This has given a few issues in the past and would be beneficial to have a standalone module for future additions to Knowledge Base sources.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.

@maxtybar
Copy link
Contributor Author

maxtybar commented Oct 1, 2024

Closed due to yarn.lock issues. Updated in PR #724

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

(amazonaurora): merge amazon aurora vector stores
2 participants