Monitor your LobeHub application with Langfuse

What is Langfuse?

Langfuse an open-source LLM Observability platform. By enabling the Langfuse integration, you can trace your application data to develop, monitor, and improve the use of LobeHub, including:

Application traces
Usage patterns
Cost data by user and model
Evaluations

Get Started

<Steps> ### Set up Langfuse

Get your Langfuse API key by signing up for Langfuse Cloud or self-hosting Langfuse.

Set up LobeHub

There are multiple ways to self-host LobeHub. For this example, we will use the Docker Desktop deployment.

<Tabs items={["Environment Variables", "Example in Docker Desktop"]}> <Tab> Before deploying LobeHub, set the following four environment variables with the Langfuse API keys you created in the previous step.

  ```sh
  ENABLE_LANGFUSE = '1'
  LANGFUSE_SECRET_KEY = 'sk-lf...'
  LANGFUSE_PUBLIC_KEY = 'pk-lf...'
  LANGFUSE_HOST = 'https://cloud.langfuse.com'
  ```
</Tab>

<Tab>
  Before running the Docker container, set the environment variables in the Docker Desktop with the Langfuse API keys you created in the previous step.

  <Image alt={'Environment Variables in Docker Desktop'} src={'https://langfuse.com/images/docs/LobeHub-docker-desktop-env.png'} />
</Tab>

</Tabs>

Activate Analytics in Settings

Once you have LobeHub running, navigate to the About tab in the Settings and activate analytics. This is necessary for traces to be sent to Langfuse.

See Chat Traces in Langfuse

After setting your LLM model key, you can start interacting with your LobeHub application.

All conversations in the chat are automatically traced and sent to Langfuse. You can view the traces in the Traces section in the Langfuse UI.

Example trace in the Langfuse UI </Steps>

Feedback

If you have any feedback or requests, please create a GitHub Issue or share your work with the Langfuse community on Discord.

Observability and Tracing for LobeHub