-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
feat(vertexai): explicit caching #10310
Conversation
b3718aa
to
77025ce
Compare
OK TO SUBMIT. Feature is now available. |
Implement explicit caching. - The CachedContent type. - Client methods to create, update, list and delete CachedContents. The update method follows the same pattern in some other cloud clients, where a separate type carries the fields to be updated. - Two ways to set the CachedContent in a model: 1. The GenerativeModel.CachedContentName field, which corresponds to the actual proto. 2. The GenerativeModelFromCachedContent method, which requires a properly initialized CachedContent but guarantees that the model names of the CachedContent and GenerativeModel are the same.
@codyoss Do you see the problem with kokoro? |
|
@codyoss could you describe the path of mouse clicks taking you to this information from the kokoro "Details" page? |
I guess this builds locally because of go.work. |
Merged in #10363, which was released in v0.11.0 |
Pull request was closed
Implement explicit caching.
The CachedContent type.
Methods to create, update, list and delete CachedContents.
The update method follows the same pattern in some other cloud clients,
where a separate type carries the fields to be updated.
Two ways to set the CachedContent in a model:
to the actual proto.
a properly initialized CachedContent but guarantees that
the model names of the CachedContent and GenerativeModel are
the same.