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.

Sign up for GitHub

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

Jump to bottom

[DOCS] Documents trained model auto-scaling #2795

Merged
merged 34 commits into from
Oct 14, 2024
Merged

[DOCS] Documents trained model auto-scaling #2795

merged 34 commits into from
Oct 14, 2024

Conversation

szabosteve
Copy link
Contributor

@szabosteve szabosteve commented Sep 12, 2024 •
edited
Loading

Overview

This PR:

  • creates a new page about model autoscaling,
  • provides tables for the autoscaling behavior in Cloud, (the content for Serverless will be part of another PR)
  • gives instructions on how to optimize a model for search/ingest by using the API,
  • adds link to ELSER, E5, and Deploy trained model pages that points to the autoscaling page,
  • removes the corresponding ELSER limitation,
  • reviews the text on Deploy the model in your cluster page,
  • updates the screenshot on the Deploy the model in your cluster page.

Preview

Remarks

elastic/elasticsearch#114038 removed a link to adaptive allocations docs from the Semantic text tutorial to avoid failing docs builds. The link needs to be updated and put back in the tutorial after this PR is merged.

@szabosteve szabosteve requested a review from a team as a code owner September 12, 2024 14:48
@szabosteve szabosteve marked this pull request as draft September 12, 2024 14:48
@github-actions GitHub Actions
Copy link

A documentation preview will be available soon.

Request a new doc build by commenting
  • Rebuild this PR: run docs-build
  • Rebuild this PR and all Elastic docs: run docs-build rebuild

run docs-build is much faster than run docs-build rebuild. A rebuild should only be needed in rare situations.

If your PR continues to fail for an unknown reason, the doc build pipeline may be broken. Elastic employees can check the pipeline status here.

@mergify mergify bot added the backport-skip Skip automated backport with mergify label Sep 12, 2024
@elastic elastic deleted a comment from mergify bot Sep 19, 2024
@szabosteve szabosteve added backport-8.16 Automated backport with mergify and removed backport-skip Skip automated backport with mergify labels Sep 25, 2024
@szabosteve szabosteve changed the title [DOCS] Documents ELSER auto-scale [DOCS] Documents ELSER / NLP model deployment auto-scale Sep 25, 2024
@szabosteve szabosteve requested a review from arisonl September 30, 2024 14:46
@szabosteve szabosteve marked this pull request as ready for review September 30, 2024 14:46
@arisonl
Copy link

arisonl commented Oct 1, 2024 •
edited
Loading

This looks great @szabosteve, thanks for tagging me. A couple of questions and notes:

  • Agreed on a separate page for model scaling.
  • Should we mention somewhere how to configure a deployment for search vs ingest via the API (1 thread for ingest, >=1 thread(s) for search)?
  • Should we include a link to the pricing calculator (https://cloud.elastic.co/pricing) from the references you are making concerning managing cost?
  • We need the equivalent documentation for serverless.
  • I am going to share with you a document with additional details that we may want to consider.

@szabosteve
Copy link
Contributor Author

@elasticmachine update branch

@szabosteve szabosteve changed the title [DOCS] Documents ELSER / NLP model deployment auto-scale [DOCS] Documents trained model auto-scaling Oct 7, 2024
jan-elastic
jan-elastic previously approved these changes Oct 10, 2024
View reviewed changes
Copy link

@jan-elastic jan-elastic left a comment

Choose a reason for hiding this comment

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

lgtm

szabosteve and others added 2 commits October 11, 2024 14:44
@szabosteve
Changes section title.
7e60639
@szabosteve @darnautov
Apply suggestions from code review
f489618 
Co-authored-by: Dima Arnautov <arnautov.dima@gmail.com>
@szabosteve szabosteve requested a review from darnautov October 11, 2024 12:52
@szabosteve @darnautov
Apply suggestions from code review
486ad39 
Co-authored-by: Dima Arnautov <arnautov.dima@gmail.com>
darnautov
darnautov approved these changes Oct 14, 2024
View reviewed changes
Copy link
Contributor

@darnautov darnautov left a comment

Choose a reason for hiding this comment

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

LGTM

@szabosteve szabosteve merged commit 5496fe0 into elastic:main Oct 14, 2024
3 checks passed
@szabosteve szabosteve deleted the elser-auto-scale branch October 14, 2024 13:20
mergify bot pushed a commit that referenced this pull request Oct 14, 2024
@szabosteve @mergify
[DOCS] Documents trained model auto-scaling (#2795)
6ef6951 
Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
Co-authored-by: Dima Arnautov <arnautov.dima@gmail.com>
(cherry picked from commit 5496fe0)
@mergify mergify bot mentioned this pull request Oct 14, 2024
Merged
szabosteve added a commit that referenced this pull request Oct 14, 2024
@mergify @elasticmachine
@darnautov @szabosteve
[DOCS] Documents trained model auto-scaling (#2795) (#2852)
3546447 
Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
Co-authored-by: Dima Arnautov <arnautov.dima@gmail.com>
Co-authored-by: István Zoltán Szabó <istvan.szabo@elastic.co>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@darnautov darnautov darnautov approved these changes

@jan-elastic jan-elastic jan-elastic left review comments

@arisonl arisonl Awaiting requested review from arisonl

Assignees
No one assigned
Labels
backport-8.16 Automated backport with mergify ELSER :ml nlp v8.16
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@szabosteve @arisonl @darnautov @jan-elastic @elasticmachine