Addition chunk metadata to ChunkEmbeddings output #14462
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Outdated suggestions cannot be applied.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.
Addition chunk metadata to ChunkEmbeddings output
Description
Previously, ChunkEmbeddings would lose the data in the chunk's original metadata in the output. This PR will continue to keep that metadata in the result.
Motivation and Context
When chunks are found by NERs, we get the entity information like {"entity": "NAME"}. Losing this information makes the result of ChunkEmbeddings unusable. I am thinking of writing a new annotator that takes the result of ChunkEmbeddings as input.
How Has This Been Tested?
I wrote a solid unit test and added a helper unit test class named AnnotationUtils.
Screenshots (if appropriate):
Types of changes
Checklist: