Langfuse
Open source LLM engineering platform. Traces, evals, prompt management and metrics to debug and improve your LLM application.
Integrate the Langfuse API with the Python API
Setup the Langfuse API trigger to run a workflow which integrates with the Python API. Pipedream's integration platform allows you to integrate Langfuse and Python remarkably fast. Free for developers.
Trusted by 1,000,000+ developers from startups to Fortune 500 companies
Popular Langfuse and Python Triggers#
Emit new event when user feedback (score) is submitted on a trace in Langfuse. See the documentation.
Emit new event when a new trace is recorded in Langfuse. See the documentation.
Popular Langfuse and Python Actions#
Attach user feedback to an existing trace in Langfuse. See the documentation.
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
Connect Langfuse#
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
langfuse: {
type: "app",
app: "langfuse",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://${this.langfuse.$auth.region}.langfuse.com/api/public/observations`,
auth: {
username: `${this.langfuse.$auth.public_key}`,
password: `${this.langfuse.$auth.secret_key}`,
},
})
},
})
Overview of Python#
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:
Connect Python#
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}}Trusted by 1,000,000+ developers from startups to Fortune 500 companies