Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jhsu/tldraw-llm
https://github.com/jhsu/tldraw-llm
Last synced: 21 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/jhsu/tldraw-llm
- Owner: jhsu
- License: gpl-3.0
- Created: 2024-06-30T18:56:26.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-07-07T22:49:12.000Z (6 months ago)
- Last Synced: 2024-12-20T21:13:13.753Z (21 days ago)
- Language: TypeScript
- Size: 241 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
This repository collects demos that show how you might use [tldraw](https://github.com/tldraw/tldraw) together with an LLM like GPT-4. It is very much a work in progress, please use it as inspiration and experimentation.
PRs welcome for new demos, prompts, strategies and models.
# Installation
Run `npm install` to install dependencies.
# Usage
1. Create an OpenAI API key on the [platform.openai.com](platform.openai.com) website.
2. Create an Assistant on the [platform.openai.com](platform.openai.com) website.
3. Create a second Assistant on the [platform.openai.com](platform.openai.com) website.
4. Create `.env` file at the root of this repo with both the key and the assistant's id.
```
OPENAI_API_KEY="sk-sk-etcetcetc"
OPENAI_ASSISTANT_ID="asst_etcetcetc"
OPENAI_FUNCTIONS_ASSISTANT_ID="asst_etcetcetc"
```
Run `npm run dev` to start the server.
See notes below on the different demos.
# Collaborate
multiple cursors using automerge-tldraw