How to Improve the Performance of RAGFlow

[zyoung1212]

I want to improve its concurrency and found a warning during startup: WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
How can I switch to a WSGI server? Could you provide a detailed tutorial? Thank you!

[dosubot[bot]]

I found several similar threads discussing production deployment and WSGI server usage for RAGFlow, but none of them provided a solution in the comments ^[1][2][3][4].

Regarding your question, while I couldn't find specific instructions for switching RAGFlow to a WSGI server, I can provide some general guidance. RAGFlow uses Flask, which is compatible with WSGI servers. Here are some steps you can follow:

1. Choose a WSGI Server: Popular options include Gunicorn and uWSGI. These servers are well-suited for production environments.

2. Install the WSGI Server: You can install Gunicorn using pip:

   pip install gunicorn

3. Run RAGFlow with Gunicorn: Assuming your Flask app is named app.py and the Flask application instance is named app, you can start Gunicorn with:

   gunicorn -w 4 -b 0.0.0.0:8000 app:app

   • -w 4 specifies the number of worker processes for handling requests. Adjust this based on your server's CPU cores.
   • -b 0.0.0.0:8000 binds the server to all IP addresses on port 8000.

4. Configure for Production: Ensure your server environment is configured for production, including setting environment variables and optimizing server settings.

5. Dependencies: Make sure all dependencies listed in the pyproject.toml file are installed and compatible with your server environment ^[5][6].

For detailed configuration and optimization, you might need to refer to the documentation of the specific WSGI server you choose.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}