with Scale AI and Anthropic (Claude)?
Create a document transcription task. See the documentation
Create an image annotation task. See the documentation
Create a text annotation task. See the documentation
Scale AI offers an API to automate and streamline data labeling for machine learning applications, providing access to a global workforce and sophisticated tools. With Scale AI's API on Pipedream, you can integrate scalable data annotation workflows directly into your apps. Trigger tasks, manage datasets, and receive annotated data, all within Pipedream's serverless platform. This enables seamless automation of labeling tasks, integration with machine learning pipelines, and real-time updates on annotations.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
scale_ai: {
type: "app",
app: "scale_ai",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.scale.com/v1/teams`,
headers: {
"Accept": `application/json`,
},
auth: {
username: `${this.scale_ai.$auth.api_key}`,
password: ``,
},
})
},
})
The Anthropic (Claude) API offers a conversational AI that can be leveraged for a variety of applications, ranging from answering questions to generating content or providing customer support. In Pipedream, you can create powerful workflows that utilize the capabilities of Claude to automate responses, analyze text, or enhance data with AI-generated insights. Pipedream's serverless platform simplifies integrating Claude into your processes with other apps and services for seamless automation.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
anthropic: {
type: "app",
app: "anthropic",
}
},
async run({steps, $}) {
const data = {
"model": "claude-3-haiku-20240307",
"max_tokens": 300,
"messages": [
{"role": "user", "content": "Write me a haiku about Pipedream workflows."}
]
}
return await axios($, {
method: "post",
url: `https://api.anthropic.com/v1/messages`,
headers: {
"x-api-key": `${this.anthropic.$auth.api_key}`,
"anthropic-version": `2023-06-01`,
},
data,
})
},
})