This pull request introduces the aggregationMethod parameter to the DocumentSimilarityRanker annotator. The new parameter allows users to specify the method used to aggregate multiple sentence embeddings into a single vector representation.
Motivation and Context
Allows users to tailor the aggregation method to their specific use case, whether they need a general overview (AVERAGE), focus on the initial context (FIRST), or emphasize the strongest signals (MAX).
This change solves the following issues:
Issue #14368
Issue #14195
How Has This Been Tested?
Screenshots (if appropriate):
Local Tests
Google Colab notebook
Types of changes
[x] Bug fix (non-breaking change which fixes an issue)
[x] Code improvements with no or little impact
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
Checklist:
[x] My code follows the code style of this project.
[x] My change requires a change to the documentation.
Description
This pull request introduces the
aggregationMethodparameter to theDocumentSimilarityRankerannotator. The new parameter allows users to specify the method used to aggregate multiple sentence embeddings into a single vector representation.Motivation and Context
Allows users to tailor the aggregation method to their specific use case, whether they need a general overview (AVERAGE), focus on the initial context (FIRST), or emphasize the strongest signals (MAX).
This change solves the following issues:
How Has This Been Tested?
Screenshots (if appropriate):
Types of changes
Checklist: