Automatically add the configured model_id to neural searches#353
Merged
mbklein merged 1 commit intodeploy/stagingfrom Mar 19, 2026
Merged
Automatically add the configured model_id to neural searches#353mbklein merged 1 commit intodeploy/stagingfrom
mbklein merged 1 commit intodeploy/stagingfrom
Conversation
…oesn't specify one
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Automatically add the configured model_id (from AWS Secrets Manager) to any neural query that doesn't already have one. This will eliminate the need for the DC front end or the API's MCP server or any other client to know the correct model ID for the API it's calling.
Theoretically, this could be implemented as a
request_processoron the index's default search pipeline. Unfortunately, opensearch-project/neural-search#813 made it so the neural query enricher only worked on top-level neural queries (not queries nested in aboolorhybrid), and even though it was supposedly fixed in OpenSearch 2.12, I still couldn't get it to work in my dev index.While this will allow any public API user to consume Bedrock resources, the cost compared to existing AI search, DC-based hybrid search, and embedding during indexing is negligible.