-
Notifications
You must be signed in to change notification settings - Fork 138
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add remote inference tutorial #1158
Conversation
Signed-off-by: Yaliang Wu <[email protected]>
Signed-off-by: Yaliang Wu <[email protected]>
Codecov Report
@@ Coverage Diff @@
## 2.x #1158 +/- ##
============================================
- Coverage 78.99% 78.94% -0.06%
+ Complexity 2121 2118 -3
============================================
Files 167 167
Lines 8633 8633
Branches 869 869
============================================
- Hits 6820 6815 -5
- Misses 1419 1425 +6
+ Partials 394 393 -1
Flags with carried forward coverage won't be shown. Click here to find out more. |
In 2.9, we released [ML model access control](https://opensearch.org/docs/latest/ml-commons-plugin/model-access-control/) which supports model level access control. | ||
User can enable the feature by | ||
``` | ||
PUT /_cluster/settings |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should we add some explain for the case when model_access_control is disabled? Since we support default model group, so this setting is not required to be true anymore. We should let user know that the feature still works without the access control but it would introduce risks, etc.
PUT /_cluster/settings | ||
{ | ||
"persistent" : { | ||
"plugins.ml_commons.connector_access_control_enabled" : true |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The same to the model access control, we can add a little bit description that the setting can be false and the feature will still work without access control.
"parameters": { | ||
"model": "gpt-3.5-turbo" | ||
}, | ||
"credential": { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We should state that this credential provided to Ml-commons will not be shown to the customer through any APIs, so it's customers' responsibility to store the credential safely.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, will address the comments in a new PR soon.
* add remote inference tutorial Signed-off-by: Yaliang Wu <[email protected]> * change model group id to keep consistent Signed-off-by: Yaliang Wu <[email protected]> --------- Signed-off-by: Yaliang Wu <[email protected]>
* add remote inference tutorial Signed-off-by: Yaliang Wu <[email protected]> * change model group id to keep consistent Signed-off-by: Yaliang Wu <[email protected]> --------- Signed-off-by: Yaliang Wu <[email protected]>
Description
[Describe what this change achieves]
Issues Resolved
[List any issues this PR will resolve]
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.