add a "quiet" flag to the HTTP API #1984
Open
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
When "quiet" is enabled, prediction responses do not include the original input. This change also keeps the typehints consistent by making `input` optional in `PredictionResponse` (but still required in `PredictionRequest`). Signed-off-by: Daniel Keyes <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in 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Outdated suggestions cannot be applied.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.
For some context, I was working on a use-case where the size of the inputs to my predictor were very large, but the size of the outputs are relatively small. I noticed that since both
PredictionResponseandPredictionRequestare subclasses ofPredictionBaseModel(which definesinput), this meant that the inputs were transmitted in both the response and the request, which used up a lot of network bandwidth.This PR adds an optional "quiet" flag to the http API, which just makes it so the
PredictionResponsedoes not repeat the input.Let me know if this looks good, or if you would like me to change anything.