Skip to content

Conversation

@fen-qin
Copy link

@fen-qin fen-qin commented Nov 14, 2025

Description

This PR is to add sagemaker remonte connector blueprint for asymmetric embedding models.

Related Issues

Check List

  • New functionality includes testing.
  • New functionality has been documented.
  • API changes companion pull request created.
  • Commits are signed per the DCO using --signoff.
  • Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

Signed-off-by: Fen Qin <mfenqin@amazon.com>
@fen-qin fen-qin had a problem deploying to ml-commons-cicd-env-require-approval November 14, 2025 17:40 — with GitHub Actions Error
@fen-qin fen-qin had a problem deploying to ml-commons-cicd-env-require-approval November 14, 2025 17:40 — with GitHub Actions Failure
@fen-qin fen-qin temporarily deployed to ml-commons-cicd-env-require-approval November 14, 2025 17:40 — with GitHub Actions Inactive
@fen-qin fen-qin temporarily deployed to ml-commons-cicd-env-require-approval November 14, 2025 17:40 — with GitHub Actions Inactive
@@ -0,0 +1,224 @@
# AWS SageMaker Asymmetric Embedding Model Standard Blueprint

This blueprint demonstrates how to deploy an asymmetric embedding model (multilingual-e5-small) using AWS SageMaker and integrate it with OpenSearch for semantic search. The asymmetric model uses different prefixes for queries and passages to optimize search performance.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This blueprint demonstrates how to deploy an asymmetric embedding model (multilingual-e5-small) using AWS SageMaker

Seems this doc doesn't have how to deploy the model to AWS SageMaker. Can you add it ?

- **passage_prefix**: "passage: " (prefix added to document passages)
- **space_type**: "l2" (distance metric for similarity calculation)

## References
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add how to use asymmetric embedding model in neural search ? Or link the document

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants