Support query_template optional field for ML search request processor
#270
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
…ieldlist Signed-off-by: Tyler Ohlsen <[email protected]>
Signed-off-by: Tyler Ohlsen <[email protected]>
ohltyler
requested review from
dbwiddis,
owaiskazi19,
joshpalis,
amitgalitz,
jackiehanyang and
minalsha
as code owners
joshpalis
approved these changes
Aug 7, 2024
opensearch-trigger-bot bot
pushed a commit
that referenced
this pull request
Aug 7, 2024
…or (#270) Signed-off-by: Tyler Ohlsen <[email protected]> (cherry picked from commit 211434e)
ohltyler
added a commit
that referenced
this pull request
Aug 7, 2024
…or (#270) (#271) Signed-off-by: Tyler Ohlsen <[email protected]> (cherry picked from commit 211434e) Co-authored-by: Tyler Ohlsen <[email protected]>
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Outdated suggestions cannot be applied.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.
Description
Adds support for the
query_templateparameter for the ML inference processor in the context of search request. This param is used to rewrite a query, commonly used for creating some knn query based on vectors returned from an embedding model.Also cleans up the
ConfigFieldListto supportjsonfields andjsonStringfields to fully support all optional field types. The latterjsonStringdoes not have the JSON validation, as it could be invalid JSON with variable placeholders in the context of a JSON template. Currently, only the addedquery_templatefield uses this field type.And lastly, finishes processing of ML processor optional inputs and ensure they are included in the final generated template configuration.
Demo video, showing a semantic search use case. Indexes some sample text data with an ML processor to vectorize it. Next, on the search side, take some input query, vectorize the text input, use
query_templateto create someknnquery, using the ML embedding response as the vector to search on. knn results are then returned.screen-capture.22.webm
Issues Resolved
Makes progresson #23
Check List
--signoffBy 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.