Access 200+ AI Models with a Single AI API
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: {
ai_ml_api: {
type: "app",
app: "ai_ml_api",
}
},
async run({steps, $}) {
const data = {
"model": "mistralai/Mistral-7B-v0.1",
"messages": [
{
"role": "system",
"content": "You are an AI assistant who knows everything.",
},
{
"role": "user",
"content": "Tell me, why is the sky blue?"
},
]
}
return await axios($, {
method: "POST",
url: `https://api.aimlapi.com/chat/completions`,
headers: {
Authorization: `Bearer ${this.ai_ml_api.$auth.api_key}`,
},
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}}