Skip to content
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

Adds EP-10494: AI APIs enhancement proposal #10495

Open
wants to merge 18 commits into
base: main
Choose a base branch
from

Conversation

npolshakova
Copy link
Contributor

Description

Adds Enhancement Proposal 10494 that proposes adding AI Gateway APIs support.

Supports #10494

Initial APIs can be found in this draft PR: #10493

Copy link
Contributor

@EItanya EItanya left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This proposal LGTM

@npolshakova npolshakova requested a review from linsun January 28, 2025 21:57
@npolshakova
Copy link
Contributor Author

@linsun / @yuval-k can I get another review?

@npolshakova npolshakova requested a review from lgadban January 31, 2025 16:29
docs/content/enhancements/10494.md Outdated Show resolved Hide resolved
docs/content/enhancements/10494.md Outdated Show resolved Hide resolved
docs/content/enhancements/10494.md Outdated Show resolved Hide resolved
docs/content/enhancements/10494.md Outdated Show resolved Hide resolved
@npolshakova npolshakova mentioned this pull request Feb 6, 2025
4 tasks
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Outdated Show resolved Hide resolved
spec:
ai:
vertexAi:
model: gemini-1.5-flash-001
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we mention what would happen if the URL or the request body contains the model value that's not the same as the model value in the Upstream?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yep, I'll add a sentence about if the model is not provided as well. We use the Upstream in the case of a mismatch, right?

@npolshakova npolshakova force-pushed the add-ai-api-enhancement-proposal branch from 3ab7979 to b1fe48b Compare February 12, 2025 20:46
design/10494.md Outdated Show resolved Hide resolved
design/10494.md Show resolved Hide resolved
@npolshakova npolshakova mentioned this pull request Feb 14, 2025
4 tasks
name: openai-secret
```

Notice that this Upstream does not specify a model, so kgateway will use the model value in the request to determine
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

kgateway will use the model value in the request

What does this mean? Might be worth elaborating here.

Comment on lines +168 to +173
filters:
- type: ExtensionRef
extensionRef:
group: gateway.kgateway.dev/v1alpha1
kind: RoutePolicy
name: open-ai-opt
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Prefer using targetRef attachment on the RoutePolicy rather than ExtensionRef?

The `pool` entries can either define a list of backends or a single backend.

```yaml
multi:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does this live on the Upstream? More context would be help IMO

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants