Use Dictionary lookup for supplied IDs to Embedding Operator #148
Conversation
This file contains 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
karlhigley
approved these changes
May 12, 2023
The op now adds the embedding tag automatically, and the input schema cannot have both a CATEGORICAL and EMBEDDING tag
# for free
to join this conversation on GitHub.
Already have an account?
# to comment
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Outdated suggestions cannot be applied.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.
unknown_valueoption enable unknown IDs to set a default the value for the embedding returned for ids that are not found in the set of pre-trained embeddingsmmapparameter to make it optional when passing a file. Currently if passing a file without mmap=True, we get an unrelated error.Example
Using 10 million IDs. The operator transform runs in roughly 500-600 milliseonds. This scales proportionaly with the number of IDs.
After this change the operator transform runs in 50-60 microseconds with 10 million IDs.