1
0
mirror of https://github.com/coalaura/whiskr.git synced 2025-09-08 17:06:42 +00:00
Files
whiskr/README.md

133 lines
4.7 KiB
Markdown
Raw Normal View History

2025-08-10 00:51:58 +02:00
# whiskr
2025-08-05 04:03:21 +02:00
2025-08-10 01:20:03 +02:00
![screenshot](.github/chat.png)
2025-08-10 01:17:13 +02:00
whiskr is a private, self-hosted web chat interface for interacting with AI models via [OpenRouter](https://openrouter.ai/).
2025-08-05 04:03:21 +02:00
## Features
2025-08-10 01:19:23 +02:00
- Private and self-hosted (data stored in localStorage)
2025-08-10 01:17:13 +02:00
- Supports any model available on your OpenRouter account
- Real-time streaming responses
- Edit, delete, or copy any message
- Persistent settings for model, temperature, and other parameters
- Full conversation control including clearing and modifying messages
2025-08-25 22:45:03 +02:00
- Title generation (and refresh)
2025-08-10 18:23:01 +02:00
- Smooth UI updates with [morphdom](https://github.com/patrick-steele-idem/morphdom), selections, images, and other state are preserved during updates
- Easy model selection:
- Tags indicate if a model supports **tools**, **vision**, or **reasoning**
- Search field with fuzzy matching to quickly find models
- Models are listed newest -> oldest
2025-08-25 18:37:30 +02:00
- Web search tools (set the `tokens.exa` to enable):
2025-08-14 17:15:33 +02:00
- `search_web`: search via Exa in auto mode; returns up to 10 results with short summaries
- `fetch_contents`: fetch page contents for one or more URLs via Exa /contents
2025-08-25 18:38:37 +02:00
- `github_repository`: get a quick overview of a GitHub repository (repo info, up to 20 branches, top-level files/dirs, and the README) without cloning (optionally set `tokens.github` for higher rate limits and private repos)
2025-08-18 03:47:37 +02:00
- Images attachments for vision models using simple markdown image tags
- Text/Code file attachments
- Reasoning effort control
2025-08-11 00:15:58 +02:00
- Structured JSON output
2025-08-23 17:44:36 +02:00
- Statistics for messages (provider, ttft, tps, token count and cost)
2025-08-16 14:54:41 +02:00
- Import and export of chats as JSON files
2025-08-16 17:18:48 +02:00
- Authentication (optional)
2025-08-10 01:17:13 +02:00
2025-08-18 04:46:17 +02:00
## TODO
2025-08-26 02:29:21 +02:00
- improved custom prompts
- collapse messages
2025-08-26 03:04:54 +02:00
- user defined timezone
2025-08-23 14:01:30 +02:00
- settings
- auto-retry on edit
- ctrl+enter vs enter for sending
2025-08-18 04:46:17 +02:00
- multiple chats
2025-08-10 01:17:13 +02:00
## Built With
**Frontend**
- Vanilla JavaScript and CSS
2025-08-10 18:23:01 +02:00
- [morphdom](https://github.com/patrick-steele-idem/morphdom) for DOM diffing without losing state
2025-08-10 01:17:13 +02:00
- [marked](https://github.com/markedjs/marked) for Markdown rendering
- [highlight.js](https://highlightjs.org/) for syntax highlighting
2025-08-16 17:23:08 +02:00
- Fonts: [Inter](https://rsms.me/inter/) (UI), [Comic Code](https://tosche.net/fonts/comic-code) (code)
- Icons: [SVGRepo](https://www.svgrepo.com/)
- Color palette: [Catppuccin Macchiato](https://catppuccin.com/)
**Backend**
- Go
2025-08-24 00:32:40 +02:00
- [chi/v5](https://go-chi.io/) for the http routing/server
2025-08-16 17:23:08 +02:00
- [OpenRouter](https://openrouter.ai/) for model list and completions
- [Exa](https://exa.ai/) for web search and content retrieval (`/search`, `/contents`)
## Getting Started
1. Copy `example.config.yml` to `config.yml` and set `tokens.openrouter`:
```bash
cp example.config.yml config.yml
```
2. Build and run:
```bash
go build -o whiskr
./whiskr
```
3. Open `http://localhost:3443` in your browser.
## Authentication (optional)
2025-08-16 17:23:55 +02:00
whiskr supports simple, stateless authentication. If enabled, users must log in with a username and password before accessing the chat. Passwords are hashed using bcrypt (12 rounds). If `authentication.enabled` is set to `false`, whiskr will not prompt for authentication at all.
2025-08-16 17:23:08 +02:00
```yaml
authentication:
enabled: true
users:
- username: laura
password: "$2a$12$cIvFwVDqzn18wyk37l4b2OA0UyjLYP1GdRIMYbNqvm1uPlQjC/j6e"
- username: admin
password: "$2a$12$mhImN70h05wnqPxWTci8I.RzomQt9vyLrjWN9ilaV1.GIghcGq.Iy"
```
After a successful login, whiskr issues a signed (HMAC-SHA256) token, using the server secret (`tokens.secret` in `config.yml`). This is stored as a cookie and re-used for future authentications.
2025-08-19 16:42:30 +02:00
## Nginx (optional)
When running behind a reverse proxy like nginx, you can have the proxy serve static files.
```ngnix
server {
listen 443 ssl;
server_name chat.example.com;
http2 on;
root /path/to/whiskr/static;
location / {
index index.html index.htm;
etag on;
add_header Cache-Control "public, max-age=2592000, must-revalidate";
expires 30d;
}
location ~ ^/- {
proxy_pass http://127.0.0.1:3443;
proxy_set_header X-Forwarded-For $remote_addr;
proxy_set_header Host $host;
}
ssl_certificate /path/to/cert.pem;
ssl_certificate_key /path/to/key.pem;
}
```
2025-08-05 04:03:21 +02:00
## Usage
2025-08-10 01:17:13 +02:00
- Send a message with `Ctrl+Enter` or the send button
2025-08-10 16:02:48 +02:00
- Just add a message with the add button
2025-08-10 01:17:13 +02:00
- Hover over a message to edit, delete, or copy it
- Adjust model, temperature, prompt, or message role from the controls in the bottom-left
2025-08-10 18:23:01 +02:00
- Use the model search field to quickly find models (supports fuzzy matching)
- Look for tags in the model list to see if a model supports tools, vision, or reasoning
2025-08-15 03:38:24 +02:00
- Use `![alt](url)` in your message to display an image inline. If the model supports vision, the same image URL is passed to the model for multimodal input.
2025-08-10 01:17:13 +02:00
## License
GPL-3.0 see [LICENSE](LICENSE) for details.