Website for the Lede browser extension.
delete folders used when generating website
-129
-1
info on the extension/info.md
-1
info on the extension/info.md
···
1
-
- Open source on Tangled -- https://tangled.org/ellioth.co/summarizer-extension
-128
info on the extension/project-readme.md
-128
info on the extension/project-readme.md
···
1
-
# Lede — page summarizer & chat (WIP)
2
-
3
-
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.
4
-
5
-
In **Beta**. Not yet in the Chrome Web Store or Firefox Addons.
6
-
7
-
## Features
8
-
9
-
- 📄 **One-Click Summaries** - Summarize page content efficiently
10
-
- 🤖 **Follow Up Questions** - Ask questions about the current webpage and summary
11
-
- 🔌 **OpenAI-Compatible** - Works with Ollama, OpenAI, Groq, and LM Studio
12
-
- ⚙️ **Configurable** - Choose your own model and API endpoint
13
-
- 🔒 **Privacy-first** - Keep summaries local with Ollama, or use a cloud provider when you choose one.
14
-
- ⌨️ **Quick access** - Keyboard shortcut of `Ctrl/Cmd+Shift+U`, use the right click menu, or click the extension icon.
15
-
16
-
## About
17
-
Made to solve a very simple problem I had as a user of the Helium web browser.
18
-
19
-
## Installation (in dev mode)
20
-
21
-
### Chrome
22
-
23
-
1. Open Chrome and navigate to `chrome://extensions/`
24
-
2. Enable **Developer mode** (toggle in top right)
25
-
3. Click **Load unpacked**
26
-
4. Select the `webai-summarizer` folder
27
-
5. The extension icon should appear in your toolbar
28
-
6. Optionally set up the keyboard shortcut at `chrome://extensions/shortcuts`
29
-
30
-
### Firefox
31
-
32
-
1. Open Firefox and navigate to `about:debugging#/runtime/this-firefox`
33
-
2. Click **Load Temporary Add-on**
34
-
3. Select the `manifest.json` file in the `webai-summarizer` folder
35
-
4. The extension icon should appear in your toolbar
36
-
37
-
**Note:** Firefox requires you to manually enable the keyboard shortcut:
38
-
1. Type `about:addons` in the address bar
39
-
2. Click the gear icon (⚙️) → **Manage Extension Shortcuts**
40
-
41
-
## TODO
42
-
43
-
- [x] Better branding / icon / logo
44
-
- [ ] Similar to "branding" -- Rename extension to something more unique and not placeholder-y
45
-
- [ ] Publish to Chrome Web Store
46
-
- [ ] Publish to Firefox Add-ons
47
-
48
-
### Build for Specific Browser
49
-
50
-
If needed, you can build for a specific browser:
51
-
52
-
```bash
53
-
# For Chrome
54
-
./build.sh chrome
55
-
56
-
# For Firefox
57
-
./build.sh firefox
58
-
```
59
-
60
-
## Usage
61
-
62
-
1. **Navigate to any webpage**
63
-
2. **Click the extension icon** in your toolbar, **or press `Ctrl/Cmd+Shift+U`**
64
-
3. **Click "Summarize Page"** for an instant summary, **or**
65
-
4. **Type a question** about the page content and press Enter
66
-
67
-
68
-
## API Mode Explained
69
-
70
-
### Ollama Native Mode
71
-
- Uses Ollama's native `/api/generate` endpoint
72
-
- Works out of the box if Ollama is installed
73
-
- Recommended for local Ollama installations
74
-
- Base URL should NOT include `/v1`
75
-
76
-
### OpenAI-Compatible Mode
77
-
- Uses the `/v1/chat/completions` endpoint
78
-
- Required for OpenAI, Groq, and other cloud providers
79
-
- Can work with Ollama if you set the `OPENAI_API_BASE` environment variable
80
-
- Base URL MUST include `/v1` for Ollama compatibility mode
81
-
82
-
## Privacy Notes
83
-
84
-
- In **Ollama Native** mode, your content stays on your machine (local model/server).
85
-
- In **OpenAI-compatible** mode, page content is sent to the provider endpoint you configure.
86
-
- The extension now extracts page text on-demand when you trigger summarize/chat, rather than running a persistent content script on all pages.
87
-
88
-
## Troubleshooting
89
-
90
-
### "Cannot connect to localhost:11434"
91
-
1. Make sure Ollama is running: `ollama serve`
92
-
2. Check that you pulled the model: `ollama list`
93
-
3. If using Ollama, make sure your URL doesn't have `/v1` in Native mode
94
-
4. Check browser console for detailed error messages
95
-
96
-
### "HTTP 403" or "HTTP 405"
97
-
This means the API endpoint is wrong. Try:
98
-
1. Switch API Mode from settings
99
-
2. For Ollama Native: use `http://localhost:11434` (no /v1)
100
-
3. For OpenAI mode: use `http://localhost:11434/v1` (with /v1)
101
-
102
-
## File Structure
103
-
104
-
```
105
-
webai-summarizer/
106
-
├── manifest.json # Extension configuration (active)
107
-
├── manifest-chrome.json # Chrome-specific manifest
108
-
├── manifest-firefox.json # Firefox-specific manifest
109
-
├── build.sh # Build script for browser switching
110
-
├── BROWSER_SUPPORT.md # Browser compatibility documentation
111
-
├── popup/
112
-
│ ├── popup.html # Chat interface
113
-
│ ├── popup.css # Styling
114
-
│ ├── popup.js # Popup logic
115
-
│ └── marked.min.js # Markdown parser
116
-
├── scripts/
117
-
│ ├── content.js # Webpage text extraction
118
-
│ └── background.js # API communication
119
-
├── options/
120
-
│ ├── options.html # Settings page
121
-
│ ├── options.css
122
-
│ └── options.js
123
-
└── icons/
124
-
├── icon16.png
125
-
├── icon32.png
126
-
├── icon48.png
127
-
└── icon128.png
128
-
```