frontend-server

Serve a FastAPI frontend by rendering Jinja2 templates and exposing them via an endpoint. This Skill provides a lightweight UI server that renders the index page, serves static assets, and connects to a backend API through a configurable API_BASE.

Connect a FastAPI UI server to your RAG backend by configuring the API_BASE environment variable. You can set API_BASE to your backend URL, such as http://localhost:8090, allowing the frontend to seamlessly communicate with the RAG or LLM backend.

Yes, you need uvicorn to run the FastAPI frontend server. The Skill requires standard Python dependencies including FastAPI, Jinja2, and uvicorn, which are listed in the requirements.txt file, and the server starts using the uvicorn command.

Yes, you can customize the page title on the voice assistant web UI. The frontend server supports configuration through environment variables, allowing you to set both the API_BASE for the backend and the TITLE for the rendered page.

Host static assets for a voice assistant web interface by using a lightweight FastAPI server. This Skill serves static assets from a designated static directory to power the web UI, enabling seamless user interaction via a browser.

Jinja2 template rendering requires standard Python dependencies to be installed correctly. Ensure you install dependencies from requirements.txt and start the server properly with uvicorn, then open localhost port 8000 to view the rendered index page.