Skip to content

Conversation

JM-Lab
Copy link
Contributor

@JM-Lab JM-Lab commented Jul 26, 2024

These changes enable support for both Exact k-NN and Approximate k-NN searches in OpenSearch. The code was updated and refactored to include this new functionality, as it previously only supported Exact k-NN. This work is based on the squashed changes from Enhance OpenSearchVectorStore #987.

  • Enhanced OpenSearchVectorStore to support both exact and approximate k-NN search methods.
  • Updated integration tests to cover common similarity metrics (cosinesimil, l2, innerproduct) for both exact and approximate k-NN.
  • Made necessary updates to the auto-configuration to accommodate the new support for approximate k-NN.
  • Updated the OpenSearch Vectorstore documentation to reflect these changes.
JM-Lab added 7 commits July 26, 2024 09:41
…archVectorStoreOptions. Signed-off-by: Jemin Huh <hjm1980@gmail.com>
… both exact and approximate k-NN. Signed-off-by: Jemin Huh <hjm1980@gmail.com>
Signed-off-by: Jemin Huh <hjm1980@gmail.com>
Signed-off-by: Jemin Huh <hjm1980@gmail.com>
…archVectorStoreOptions. Signed-off-by: Jemin Huh <hjm1980@gmail.com>
… both exact and approximate k-NN. Signed-off-by: Jemin Huh <hjm1980@gmail.com>
Signed-off-by: Jemin Huh <hjm1980@gmail.com>
@JM-Lab
Copy link
Contributor Author

JM-Lab commented Nov 4, 2024

@tzolov @markpollack
Hello, I was wondering if there's been any progress on reviewing?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment