✨✨ Create your own GPT4 Assistant with ease and use it from the command line. ✨✨

• Runs an OpenAI GPT-4V assistant from the command line
• Execute tools from the command line as required
• Generates the JSON schema for your tools from TS interfaces
• Access it globally from the ai command in your terminal

git clone [email protected]:pAIrprogio/gpt-assistant-cli-playground.git
pnpm install

• Add your OpenAI API key to a .env file using OPENAI_API_KEY=your-key
• Edit the ai.config.yml file as needed
  • This file is loaded from where you run the ai command so it can be different for each project.
  • Autocomplete is available for this file in VSCode using ./schemas/ai.config.schema.json

To install your assistant globally and access it with the ai command, run pnpm link -g or npm link in the project's folder.

Any change made to the project will be reflected in the global command without extra build step.

Follow the steps in docs/add-new-tool.md

The entire project is setup to be debugged in VSCode. Just run the Run index.ts task and it will start the app in debug mode in your terminal