mirror of
https://github.com/OpenSquawk/OpenSquawk
synced 2026-07-02 00:15:50 +08:00
d11633adde
chore: Optimize the input data sent to the OpenAI API to reduce token usage and improve decision quality. Add quick responses for common pilot utterances like radio checks and emergencies to avoid unnecessary LLM calls. The key changes are: - Use a smaller LLM model (`gpt-5-nano`) to reduce token usage - Optimize the input data by only sending relevant candidate and context information - Implement quick responses for common pilot utterances like radio checks and emergencies - Ensure ATC responses are only included when necessary to reduce token usage
Nuxt Minimal Starter
Look at the Nuxt documentation to learn more.
Setup
Make sure to install dependencies:
# npm
npm install
# pnpm
pnpm install
# yarn
yarn install
# bun
bun install
Development Server
Start the development server on http://localhost:3000:
# npm
npm run dev
# pnpm
pnpm dev
# yarn
yarn dev
# bun
bun run dev
Production
Build the application for production:
# npm
npm run build
# pnpm
pnpm build
# yarn
yarn build
# bun
bun run build
Locally preview production build:
# npm
npm run preview
# pnpm
pnpm preview
# yarn
yarn preview
# bun
bun run preview
Check out the deployment documentation for more information.
Piper TTS local
if you want to use local tts, install and run pip install "piper-tts[http]" on port 5001, then set USE_PIPER=true in .env
Whisper Tiny local
if you want to use local whisper tiny implement it #TODO