-
Notifications
You must be signed in to change notification settings - Fork 10.3k
[AIG]Guardrails docs #20098
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
[AIG]Guardrails docs #20098
Conversation
|
Howdy and thanks for contributing to our repo. We review internal PRs with 1 week. If it's something urgent or has been sitting without a comment, start a thread in the Developer Docs space internally. |
Overview Page How Guardrails works Page |
|
Legal team request to add the following onto dev docs page: |
|
were you planning on having changelog be a separate PR? (the normal short one that is within AI Gateway docs) or should it be part of this PR? |
updated wording
deleted extra sentence
|
|
||
| Llama Guard is provided as-is without any representations, warranties, or guarantees. Any rules or examples contained in blogs, developer docs, or other reference materials are provided for informational purposes only. You acknowledge and understand that you are responsible for the results and outcomes of your use of AI Gateway. | ||
|
|
||
| ## ::: |
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.
I think from here until the end is just a duplication of the existing content?
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.
You can avoid this by previewing your build locally || looking at the preview links once you push it up.
| order: 3 | ||
| --- | ||
|
|
||
| AI Gateway inspects all interactions in real time by evaluating content against predefined safety parameters. Below a breakdown of the process: |
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 delete this entire page and instead move the different sub-groups of information to other pages (noting below)
|
|
||
| Llama Guard is provided as-is without any representations, warranties, or guarantees. Any rules or examples contained in blogs, developer docs, or other reference materials are provided for informational purposes only. You acknowledge and understand that you are responsible for the results and outcomes of your use of AI Gateway. | ||
|
|
||
| ## ::: |
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.
You can avoid this by previewing your build locally || looking at the preview links once you push it up.
updated wording in supported model types section
Separate PR depending on when it goes live |
Co-authored-by: Kody Jackson <[email protected]>
3 changes 1) moved configuration first, before supported model types 2) moved note about llamaguard to llamaguard section 3) added link to workers ai dashboard
|
should we rename the second page, since the "how guardrails works" section is in the overview page now? --> Set up Guardrails? |
Removed heading
Removed heading
added info on what happens if Workers AI is down
changed tab
Co-authored-by: Maddy <[email protected]>

Summary
Screenshots (optional)
Documentation checklist