API and SDK that enables AI Agents to contact humans for feedback, input, and approvals.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
humanlayer: {
type: "app",
app: "humanlayer",
}
},
async run({steps, $}) {
const data = {
"run_id": "run_120", //adjust your run and call ids
"call_id": "call_640",
"spec": {
"msg": "Can someone approve this small typo fix PR? Just stumbled upon those while testing other stuff?",
"subject": "Small PR fix",
"channel": {
"email": {
"address": "superman@pd.com",
"subject": "Small PR fix",
"in_reply_to": "msg_790"
}
}
}
}
return await axios($, {
method: "post",
url: `https://api.humanlayer.dev/humanlayer/v1/human_contacts`,
headers: {
Authorization: `Bearer ${this.humanlayer.$auth.api_key}`,
"content-type": `application/json`,
},
data,
})
},
})
Develop, run and deploy your Python code in Pipedream workflows. Integrate seamlessly between no-code steps, with connected accounts, or integrate Data Stores and manipulate files within a workflow.
This includes installing PyPI packages, within your code without having to manage a requirements.txt
file or running pip
.
Below is an example of using Python to access data from the trigger of the workflow, and sharing it with subsequent workflow steps:
def handler(pd: "pipedream"):
# Reference data from previous steps
print(pd.steps["trigger"]["context"]["id"])
# Return data for use in future steps
return {"foo": {"test":True}}