Adding common rerank options to Perform Inference API #125239
Merged
Conversation
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
ymao1 changed the title 
| run elasticsearch-ci/8.19.0/bwc-snapshots |
| run elasticsearch-ci/bwc-snapshots |
ymao1 added >enhancement :ml 
| Hi @ymao1, I've created a changelog YAML for you. |
| Pinging @elastic/ml-core (Team:ML) |
jonathan-buttner approved these changes Mar 21, 2025
| import java.util.List; | ||
| import java.util.Objects; | ||
| | ||
| public record GoogleVertexAiRerankRequestEntity(String query, List<String> inputs, @Nullable String model, @Nullable Integer topN) |
There was a problem hiding this comment.
How about we move the logic to determine which topN to use in the GoogleVertexAiRerankRequest. That way this class does need both variables.
| run elasticsearch-ci/rest-compatibility |
💚 All backports created successfully
Questions ?Please refer to the Backport tool documentation |
ymao1 added a commit to ymao1/elasticsearch that referenced this pull request Mar 25, 2025
* wip * Adding rerank common options * Linting * Linting * [CI] Auto commit changes from spotless * Update docs/changelog/125239.yaml * PR feedback --------- Co-authored-by: elasticsearchmachine <infra-root+elasticsearchmachine@elastic.co> (cherry picked from commit a6f685c) # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java # x-pack/plugin/core/src/test/java/org/elasticsearch/xpack/core/inference/action/InferenceActionRequestTests.java
elasticsearchmachine pushed a commit that referenced this pull request Mar 25, 2025
) * wip * Adding rerank common options * Linting * Linting * [CI] Auto commit changes from spotless * Update docs/changelog/125239.yaml * PR feedback --------- Co-authored-by: elasticsearchmachine <infra-root+elasticsearchmachine@elastic.co> (cherry picked from commit a6f685c) # Conflicts: # server/src/main/java/org/elasticsearch/TransportVersions.java # x-pack/plugin/core/src/test/java/org/elasticsearch/xpack/core/inference/action/InferenceActionRequestTests.java
omricohenn pushed a commit to omricohenn/elasticsearch that referenced this pull request Mar 28, 2025
* wip * Adding rerank common options * Linting * Linting * [CI] Auto commit changes from spotless * Update docs/changelog/125239.yaml * PR feedback --------- Co-authored-by: elasticsearchmachine <infra-root+elasticsearchmachine@elastic.co>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
3 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.
Resolves #111273
Summary
Exposes the
return_documentsandtop_nparameters as root level fields in the Perform Inference API forreranktask types. Previously, this setting was available for certain services as a task setting. The root option, if specified, will now take precedence over the task settings option.Services that support rerank
AlibabaCloud AI Search - docs
Does not accept
return_documentsortop_nparameters so throws validation exception if either is specifiedCohere - docs
Elasticearch
Updated to respect the
top_noption if definedGoogle Vertex AI - docs
Jina AI - docs
Voyage AI - docs