Skip to content

Conversation

@afoucret
Copy link
Contributor

@afoucret afoucret commented Nov 24, 2025

Closes #136860

This PR add CCS support for ES\QL query that are using an inference command (RERANK and COMPLETION) or an inference function (TEXT_EMBEDDING).

The inference is always executed on the coordinator cluster, meaning that the endpoint need to exists on the coordinator clusters.

@afoucret afoucret requested a review from ioanatia November 24, 2025 17:26
@elasticsearchmachine elasticsearchmachine added the Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch label Nov 24, 2025
@elasticsearchmachine
Copy link
Collaborator

Pinging @elastic/es-search-relevance (Team:Search Relevance)

@elasticsearchmachine
Copy link
Collaborator

Hi @afoucret, I've created a changelog YAML for you.

@tylerperk tylerperk changed the title [ES|QL] Support CCQ for inference commands [ES|QL] Support CCS for inference commands Nov 24, 2025
@github-actions
Copy link
Contributor

ℹ️ Important: Docs version tagging

👋 Thanks for updating the docs! Just a friendly reminder that our docs are now cumulative. This means all 9.x versions are documented on the same page and published off of the main branch, instead of creating separate pages for each minor version.

We use applies_to tags to mark version-specific features and changes.

Expand for a quick overview

When to use applies_to tags:

✅ At the page level to indicate which products/deployments the content applies to (mandatory)
✅ When features change state (e.g. preview, ga) in a specific version
✅ When availability differs across deployments and environments

What NOT to do:

❌ Don't remove or replace information that applies to an older version
❌ Don't add new information that applies to a specific version without an applies_to tag
❌ Don't forget that applies_to tags can be used at the page, section, and inline level

🤔 Need help?

Copy link
Contributor

@ioanatia ioanatia left a comment

Choose a reason for hiding this comment

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

code changes look alright, but IMO it would be easier if we get the usage limits changes first.
this way we know there's always a LIMIT before the inference plans.

@@ -0,0 +1,12 @@
{
Copy link
Contributor

Choose a reason for hiding this comment

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

no need to add a new dataset, just use the existing dense_vector one.

r.rerankFields(),
r.scoreAttribute()
);
case Completion c -> new CompletionExec(c.source(), mappedChild, c.inferenceId(), c.prompt(), c.targetField());
Copy link
Contributor

Choose a reason for hiding this comment

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

Have we checked that there's no way to get to a place where we have an unexecutable plan?
IMO we should verify that there is a pipeline breaker before any of the inference plans.

@afoucret afoucret force-pushed the esql-inference-ccq-support branch from 92a6fe5 to 22f5c22 Compare November 26, 2025 07:58
@afoucret afoucret requested a review from a team as a code owner November 26, 2025 07:58
@github-actions
Copy link
Contributor

github-actions bot commented Nov 26, 2025

@afoucret afoucret force-pushed the esql-inference-ccq-support branch from ec2c0df to b119cf6 Compare November 26, 2025 14:40
@afoucret
Copy link
Contributor Author

afoucret commented Dec 9, 2025

Replaced by #139244

@afoucret afoucret closed this Dec 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

>enhancement :Search Relevance/ES|QL Search functionality in ES|QL Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch v9.3.0

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[ES|QL][Inference] Add Cross-Cluster Search (CCS) support for all inference commands

3 participants