Markdown server

Local helper to serve markdown files from this repo.

Setup

• Create a venv and install deps: bash python3 -m venv .venv . .venv/bin/activate pip install -r requirements.txt
• The server defaults to docs/ for content. Override with MD_BASE_DIR.

Run

• Start the server: bash . .venv/bin/activate python md_server.py
• View a rendered file: http://localhost:8080/view/markdown-server.md
• Fetch raw markdown: http://localhost:8080/raw/markdown-server.md
• Translate text (English <-> Chinese): http://localhost:8080/translate
• Pick one or more models at the top to compare results in parallel.

Translate settings

• Create a .env from .env.example and set FIREWORKS_API_KEY.
• Default model is Fireworks deepseek-v3p2 (select others in the UI).
• Base URL override: FIREWORKS_BASE_URL (default: https://api.fireworks.ai/inference/v1)
• History storage: set REDIS_URL, or use REDIS_HOST + REDIS_PASSWORD.
• To enable OpenAI models in the picker, set OPENAI_API_KEY.