When you're prototyping an app, you can query our QuickStart Templates without creating an endpoint in your account. These endpoints are rate limited, and intended for testing and experimentation only in public beta. You can click the "Clone" button as described in the QuickStart Templates guide to make a copy of the template on your account to no longer experience rate limitations.
The SDK also allows for running inferences against other endpoints as well, such as using it for local testing of a container or your own custom endpoints such as those created using our CLI Authoring Tool.
When you're prototyping an app, you can query our QuickStart templates without creating an endpoint in your account. You can check the TypeScript SDK Reference for more information about the Client class.
Before getting started, ensure you have a set
OCTOAI_TOKEN either as an environment variable or passed to the client. See TypeScript SDK Installation & Setup for more information.
To run an inference, you need to know 2 pieces of data.
- The endpoint that can accept inferences
- The data the endpoint takes in to produce an output.
To find this for QuickStart templates, visit octoai.cloud, click on "QuickStart Templates" and select which one you'd like to use. Let's check this using a Stable Diffusion controlling model called Canny.
If you scroll down below the GUI to run inferences, you will see "Endpoint URL" as well as a description on how to run an inference using cURL. In the future, examples using the Python SDK will also be available to run more easily.
For health checks, most end with the URL
Updated 12 days ago