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

Improve RAG preset experience #617

Merged
merged 3 commits into from
Feb 13, 2025

Conversation

ohltyler
Copy link
Member

@ohltyler ohltyler commented Feb 12, 2025

Description

This improves the RAG preset experience in a few ways:

  1. Changes the default behavior of ML response processors (when configured for many-to-one), to store the outputs under ext.ml_inference by default. This way, a single ML response is returned in the overall response by default for these scenarios. Existing functionality for ML response processors in other contexts, and/or when one-to-one is configured, remains unchanged.
  2. Auto-navigate to the 'ML outputs' tab if there is values found
  3. Re-ordering and minor renaming of the tabs under 'Results'
  4. Minor reformatting the 'ML outputs' tab content

Demo video, showing the end-to-end RAG preset experience and propagation of the LLM response:

screen-capture.24.webm

Check List

  • Commits are signed per the DCO using --signoff

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: Tyler Ohlsen <ohltyler@amazon.com>
@ohltyler
Copy link
Member Author

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>
Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>
@ohltyler ohltyler marked this pull request as ready for review February 12, 2025 19:33
@saimedhi saimedhi merged commit 2d1d174 into opensearch-project:2.x Feb 13, 2025
5 of 6 checks passed
opensearch-trigger-bot bot pushed a commit that referenced this pull request Feb 13, 2025
* Default ML response processors to append outputs to ext in response

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>

* Auto-navigate to ml outputs tab if found; minor reformatting

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>

* Update presets to omit ext.ml_inference

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>

---------

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>
(cherry picked from commit 2d1d174)
Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
@ohltyler ohltyler deleted the ext-updates-2 branch February 13, 2025 17:58
ohltyler pushed a commit that referenced this pull request Feb 13, 2025
* Default ML response processors to append outputs to ext in response



* Auto-navigate to ml outputs tab if found; minor reformatting



* Update presets to omit ext.ml_inference



---------


(cherry picked from commit 2d1d174)

Signed-off-by: Tyler Ohlsen <ohltyler@amazon.com>
Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backport main enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants