# Lede — page summarizer & chat (WIP)

A browser extension for Chrome and Firefox that lets you ask questions and summarize any webpage using AI (using Ollama or any OpenAI-compatible API). Works best with the GPT-OSS-20b model.

In **Beta**. Not yet in the Chrome Web Store or Firefox Addons.

## Features

- 📄 **One-Click Summaries** - Summarize page content efficiently
- 🤖 **Follow Up Questions** - Ask questions about the current webpage and summary
- 🔌 **OpenAI-Compatible** - Works with Ollama, OpenAI, Groq, and LM Studio
- ⚙️ **Configurable** - Choose your own model and API endpoint
- 🔒 **Privacy-first** - Keep summaries local with Ollama, or use a cloud provider when you choose one.
- ⌨️ **Quick access** - Keyboard shortcut of `Ctrl/Cmd+Shift+U`, use the right click menu, or click the extension icon.

## About
Made to solve a very simple problem I had as a user of the Helium web browser.

## Installation (in dev mode)

### Chrome

1. Open Chrome and navigate to `chrome://extensions/`
2. Enable **Developer mode** (toggle in top right)
3. Click **Load unpacked**
4. Select the `webai-summarizer` folder
5. The extension icon should appear in your toolbar
6. Optionally set up the keyboard shortcut at `chrome://extensions/shortcuts`

### Firefox

1. Open Firefox and navigate to `about:debugging#/runtime/this-firefox`
2. Click **Load Temporary Add-on**
3. Select the `manifest.json` file in the `webai-summarizer` folder
4. The extension icon should appear in your toolbar

**Note:** Firefox requires you to manually enable the keyboard shortcut:
1. Type `about:addons` in the address bar
2. Click the gear icon (⚙️) → **Manage Extension Shortcuts**

## TODO

- [x] Better branding / icon / logo
- [ ] Similar to "branding" -- Rename extension to something more unique and not placeholder-y
- [ ] Publish to Chrome Web Store
- [ ] Publish to Firefox Add-ons

### Build for Specific Browser

If needed, you can build for a specific browser:

```bash
# For Chrome
./build.sh chrome

# For Firefox
./build.sh firefox
```

## Usage

1. **Navigate to any webpage**
2. **Click the extension icon** in your toolbar, **or press `Ctrl/Cmd+Shift+U`**
3. **Click "Summarize Page"** for an instant summary, **or**
4. **Type a question** about the page content and press Enter


## API Mode Explained

### Ollama Native Mode
- Uses Ollama's native `/api/generate` endpoint
- Works out of the box if Ollama is installed
- Recommended for local Ollama installations
- Base URL should NOT include `/v1`

### OpenAI-Compatible Mode
- Uses the `/v1/chat/completions` endpoint
- Required for OpenAI, Groq, and other cloud providers
- Can work with Ollama if you set the `OPENAI_API_BASE` environment variable
- Base URL MUST include `/v1` for Ollama compatibility mode

## Privacy Notes

- In **Ollama Native** mode, your content stays on your machine (local model/server).
- In **OpenAI-compatible** mode, page content is sent to the provider endpoint you configure.
- The extension now extracts page text on-demand when you trigger summarize/chat, rather than running a persistent content script on all pages.

## Troubleshooting

### "Cannot connect to localhost:11434"
1. Make sure Ollama is running: `ollama serve`
2. Check that you pulled the model: `ollama list`
3. If using Ollama, make sure your URL doesn't have `/v1` in Native mode
4. Check browser console for detailed error messages

### "HTTP 403" or "HTTP 405"
This means the API endpoint is wrong. Try:
1. Switch API Mode from settings
2. For Ollama Native: use `http://localhost:11434` (no /v1)
3. For OpenAI mode: use `http://localhost:11434/v1` (with /v1)

## File Structure

```
webai-summarizer/
├── manifest.json            # Extension configuration (active)
├── manifest-chrome.json    # Chrome-specific manifest
├── manifest-firefox.json    # Firefox-specific manifest
├── build.sh                # Build script for browser switching
├── BROWSER_SUPPORT.md      # Browser compatibility documentation
├── popup/
│   ├── popup.html         # Chat interface
│   ├── popup.css          # Styling
│   ├── popup.js           # Popup logic
│   └── marked.min.js      # Markdown parser
├── scripts/
│   ├── content.js         # Webpage text extraction
│   └── background.js      # API communication
├── options/
│   ├── options.html       # Settings page
│   ├── options.css
│   └── options.js
└── icons/
    ├── icon16.png
    ├── icon32.png
    ├── icon48.png
    └── icon128.png
```