AI.INFO command #259
Merged
AI.INFO command #259
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
Closed
|
@lantiga @K-Jo @gkorland OSS look and feel. I think that @itamarhaber can be of extreme help here |
filipecosta90
requested changes
Jan 11, 2020
|
Added tests and docs, the PR is ready to land, except for the histograms. |
filipecosta90
requested changes
Jan 29, 2020
| ### AI.INFO Example | ||
|
|
||
| ```sql | ||
| AI.INFO amodel |
There was a problem hiding this comment.
@lantiga can we include the example output here?
filipecosta90
approved these changes
Feb 2, 2020
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Outdated suggestions cannot be applied.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.
This PR adds a new AI.INFO command to RedisAI.
Stats on each model/script key being run are accumulated and reported periodically.
TODO items:
modelkeyas a mandatory argument (details below in the UPDATE)ERRORS, evaluatingHISTOGRAM)AI.INFO modelkey RESET) to clean up all stat keys and start freshUPDATE (credit @K-Jo): avoid getting stats from all models with a single command (response potentially unbounded, it looks like a scan), but have users call
AI.INFOwith amodelkeyas the argument. This way a) the stats will have the same lifetime as the respective models (we can collocate stats directly in the model struct and get rid of the module-level dictUPDATE: we will still keep the stats in the dict to avoid accessing keyspace in the callback); b) responses will be bounded and specific for each model. Users will also be in charge of callingRESETSTATon the model stats.