-
Notifications
You must be signed in to change notification settings - Fork 31
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 AI LLM endpoint #2319
Add AI LLM endpoint #2319
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
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.
LGTM
it("should call the AI Gateway for generate API /llm", async () => { | ||
const res = await client.fetch("/beta/generate/llm", { | ||
method: "POST", | ||
body: buildForm({ prompt: "foo" }), |
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.
lol so the LLM API is a multipart form even tho there's no files in the payload? or is it multi-modal and could receive files? if it could, I'd say we test with a dummy file here as well just in case
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.
yeah.... it did strike me as odd too but wasn't sure. there aren't any file fields in the spec 😬 Maybe we're futureproofing..?
What does this pull request do? Explain your changes. (required)
Adding a new AI endpoint for LLM.
Specific updates (required)
How did you test each of these updates (required)
Testing in staging and unit testing.
Does this pull request close any open issues?
Screenshots (optional)
Checklist