AI is the new platform. We help you build impactful applications on top of large language models and align these systems with human feedback.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
The HumanLoop API provides a robust platform for incorporating AI and machine learning model feedback loops into applications, enabling continuous improvement of models based on human input. With Pipedream's capabilities, you can trigger workflows upon receiving data, process and analyze that data, and send it to HumanLoop to further train your AI models. This integration allows you to automate the data annotation process, handle user feedback, and improve your machine learning models over time.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
humanloop: {
type: "app",
app: "humanloop",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.humanloop.com/v3/projects`,
headers: {
"X-API-KEY": `${this.humanloop.$auth.api_key}`,
"accept": `application/json`,
},
})
},
})
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}}