Run machine learning models in the cloud.
Cancel a specific prediction identified by Id. See the documentation
Run any Bash in a Pipedream step within your workflow. Refer to the Pipedream Bash docs to learn more.
Get a specific prediction identified by Id. See the documentation
The Replicate API allows you to access a wide array of machine learning models for tasks such as image generation, text-to-image, and more. Using Pipedream, you can orchestrate these models to automate content creation, analyze media, or enhance data with AI-generated insights. Pipedream's serverless platform empowers you to create workflows that react to events, schedule tasks, and integrate with numerous other services, all harnessing the power of Replicate's AI models.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
replicate: {
type: "app",
app: "replicate",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.replicate.com/v1/predictions`,
headers: {
"Authorization": `Token ${this.replicate.$auth.api_key}`,
},
})
},
})
# $PIPEDREAM_STEPS file contains data from previous steps
cat $PIPEDREAM_STEPS | jq .trigger.context.id
# Write data to $PIPEDREAM_EXPORTS to return it from the step
# Exports must be written as key=value
echo foo=bar >> $PIPEDREAM_EXPORTS