Telegram bot powered by OpenAI

Usage

Chat with gpt-4o	Analyze image	Generate with dall-e-3

Roadmap

• [x] Integrate with Assistants API
• [x] Use GPT-4o for conversation
• [x] Use DALL-E 3 for image generation
• [x] Use whisper-1 for speech to text transcription
• [x] Use tts-1 for text to speech synthesis
• [x] Add support for memory recall
• [ ] Allow bot to search for old messages, and maybe continue previous conversation
• [ ] Add support for reminders
• [ ] Add support for Google Mail

Development

# this project uses PNPM instead of NPM
npm install --global pnpm

# install dependencies
pnpm install

# set secrets for the local stage, use `--stage prod` for production
# see the full list of secrets below
pnpm sst secrets set KEY VALUE

# this project use SST to deploy to AWS
# use its dev command for https://docs.sst.dev/live-lambda-development
pnpm dev

Secrets

• OpenAI assistant doesn't need to be fully configured, the instruction and tools will be set per run
• Only admin can initiate chat with the bot
• Admin can invite the bot to a group chat, it will reply to everyone

Deployment

# set secrets for the production stage
pnpm sst secrets set --stage prod KEY VALUE

# go production!
pnpm run deploy --stage prod

This project has been setup to be deployed automatically with GitHub Actions. A few manual steps are required:

• Setup OpenID Connect to authenticate with AWS https://docs.sst.dev/going-to-production#manual-setup
• Update .github/workflows/sst.yml to use the correct role-to-assume and aws-region