with CustomGPT and Python?
Emit new event when a new conversation is created. See the documentation
Emit new event when a new message is created in a conversation. See the documentation
Create a new conversation for an agent (formerly known as project) identified by its unique projectId. See the documentation
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Create a new agent by importing data either from a sitemap or an uploaded file. The system will process the provided data and generate a new agent based on the imported or uploaded information. See the documentation
Sends a message to an existing conversation within a project. See the documentation
CustomGPT API harnesses the power of generative AI to create custom chatbots tailored to specific needs or data sets. With Pipedream's serverless platform, you can integrate CustomGPT into complex workflows, triggering custom AI responses based on events from over 3,000+ apps. Automate tasks like customer support, personalized content creation, or data analysis by tapping into the rich capabilities of CustomGPT and Pipedream's seamless orchestration.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
customgpt: {
type: "app",
app: "customgpt",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://app.customgpt.ai/api/v1/projects`,
headers: {
Authorization: `Bearer ${this.customgpt.$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}}