Github/screenshot-to-code
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Abi Raja 2023-11-14 17:49:17 -05:00
parent 8be1b42fb4
commit e2dc80f47d
1 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
README.md
View File

@ -1,26 +1,30 @@
[Video Demo]
# screenshot-to-html
### Instructions
This is a simple app that converts a screenshot to HTML (uses Tailwind CSS). It uses GPT-4 Vision to generate the code.
Run the backend
[Video GIF]
## Getting Started
The app has a React/Vite front-end and a FastAPI backend. You will need an OpenAI API key with access to the GPT-4 Vision API.
In the root directory,
```bash
cd backend
echo "OPENAI_API_KEY=sk-your-key" > .env
poetry install
poetry run uvicorn main:app --reload --port 7000
```
Run the frontend,
```bash
cd ..
cd frontend
yarn
yarn dev
```
Open http://localhost:5173 to use the app.
If you prefer to run the backend on a different port, just modify VITE_WS_BACKEND_URL=ws://127.0.0.1:7000 in .env.local.
## Hosted Version
Hosted version coming soon at https://picoapps.xyz
### Environment Variables
.env.local contains
VITE_WS_BACKEND_URL=ws://127.0.0.1:7000