You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Apr 5, 2024. It is now read-only.
It would be nice if I can just pass the connector-id to a remote search processor and have it grab the JSON definition from the ml-plugin index. Basically, I want to be able to share it across the Sycamore stack.
Can you get what you need by using the search connectors API? I'd prefer for RPS to be as close to a black box to opensearch as I can - so the processor plugin has minimal app logic
I guess you can't get the credentials out of opensearch. (I think). But then you shouldn't be able to pass that out of opensearch either, right? Or do you want to route all your openai requests through ml-commons?
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
It would be nice if I can just pass the connector-id to a remote search processor and have it grab the JSON definition from the ml-plugin index. Basically, I want to be able to share it across the Sycamore stack.
Ref: https://opensearch.org/docs/latest/ml-commons-plugin/remote-models/connectors/
The text was updated successfully, but these errors were encountered: