Yes, you can trace a self-hosted LangFlow with a self-hosted Phoenix instance. The recommended approach is to set up Phoenix as a Docker container (exposing port 6006), configure LangFlow to send traces to Phoenix by setting the `PHOENIX_API_KEY` and `PHOENIX_COLLECTOR_ENDPOINT` environment variables in LangFlow鈥檚 `.env` file, and then run both services. This enables Phoenix to collect and visualize traces from LangFlow workflows. For step-by-step instructions, see the <https://github.com/Arize-ai/phoenix/blob/main/docs/tracing/integrations-tracing/langflow.md|LangFlow integration guide>.
Would you like more detail on the Docker setup or environment variable configuration?
Sources:
- <https://github.com/Arize-ai/phoenix/blob/main/docs/tracing/integrations-tracing/langflow.md|LangFlow integration guide>