deepsite / README.md
tommytracx's picture
Update README.md
04e9b34 verified
|
raw
history blame
2.02 kB
---
title: DeepSite
emoji: 🐳
colorFrom: blue
colorTo: blue
sdk: docker
pinned: true
app_port: 5173
license: mit
short_description: Generate any application with DeepSeek
models:
- deepseek-ai/DeepSeek-V3-0324
- deepseek-ai/DeepSeek-R1-0528
# ── OAuth settings ────────────────────────────────────────────────
hf_oauth: true
hf_oauth_expiration_minutes: 480
hf_oauth_scopes:
- write-repos
---
# DeepSite 🐳
DeepSite is a coding platform powered by DeepSeek AI, designed to make coding smarter and more efficient. Tailored for developers, data scientists, and AI engineers, it integrates generative AI into your coding projects to enhance creativity and productivity.
---
## Sign-in with Hugging Face
> The first time you open the Space you’ll see a β€œSign-in with HF” button.
> Accept the permissions prompt and you’ll be redirected back to DeepSite authenticated.
**Redirect URL**
```
https://tommytracx-deepsite.hf.space/auth/login
```
Add this URL to:
1. **Space variables**
`REDIRECT_URI=https://tommytracx-deepsite.hf.space/auth/login`
2. **OAuth app β†’ Authorization callback URLs**
Required secrets (Settings β†’ Secrets):
| Name | Value |
|------|-------|
| `OAUTH_CLIENT_ID` | client ID from your OAuth app |
| `OAUTH_CLIENT_SECRET` | client secret from your OAuth app |
| `DEFAULT_HF_TOKEN` | personal access token (scope: read) |
---
## Running locally
Clone the repo and provide the same variables in a local `.env` file:
```bash
APP_PORT=5173
OAUTH_CLIENT_ID=…
OAUTH_CLIENT_SECRET=…
DEFAULT_HF_TOKEN=…
REDIRECT_URI=http://localhost:5173/auth/login
```
Then build and run the Docker image:
```bash
docker build -t deepsite .
docker run -p 5173:5173 --env-file .env deepsite
```
The app will be available at <http://localhost:5173> and the OAuth flow will work against Hugging Face just like in the hosted Space.