open-webui/Fu-Jie_openwebui-extensions
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: standardize plugin READMEs and documentation rules

Browse Source
This commit is contained in:
fujie
2026-01-17 16:26:43 +08:00
parent 87e47fd4b2
commit 71bef146c8
23 changed files with 239 additions and 872 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
plugins/README.md
View File

@@ -124,10 +124,6 @@ Each plugin should include:
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## License
MIT License
---
> **Note**: For detailed information about each plugin type, see the respective README files in each plugin type directory.

4
plugins/README_CN.md
View File

@@ -124,10 +124,6 @@ plugins/
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 许可证
MIT License
---
> **注意**：有关每种插件类型的详细信息，请参阅每个插件类型目录中的相应 README 文件。

4
plugins/actions/README.md
View File

@@ -230,7 +230,3 @@ except Exception as e:
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## License
MIT License

4
plugins/actions/README_CN.md
View File

@@ -229,7 +229,3 @@ except Exception as e:
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 许可证
MIT License

9
plugins/actions/deep-dive/README.md
View File

@@ -1,6 +1,6 @@
# 🌊 Deep Dive
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.0.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.0.0 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
A comprehensive thinking lens that dives deep into any content - from context to logic, insights, and action paths.
@@ -81,3 +81,10 @@ The plugin generates a structured thinking timeline:
- `deep_dive.py` - English version
- `deep_dive_cn.py` - Chinese version (精读)
## Troubleshooting ❓
- **Plugin not working?**: Check if the filter/action is enabled in the model settings.
- **Debug Logs**: Enable `SHOW_STATUS` in Valves to see progress updates.
- **Error Messages**: If you see an error, please copy the full error message and report it.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

9
plugins/actions/deep-dive/README_CN.md
View File

@@ -1,6 +1,6 @@
# 📖 精读
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.0.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.0.0 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
全方位的思维透镜 —— 从背景全景到逻辑脉络，从深度洞察到行动路径。
@@ -81,3 +81,10 @@
- `deep_dive.py` - 英文版 (Deep Dive)
- `deep_dive_cn.py` - 中文版 (精读)
## 故障排除 (Troubleshooting) ❓
- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
- **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

9
plugins/actions/export_to_docx/README.md
View File

@@ -1,6 +1,6 @@
# 📝 Export to Word (Enhanced)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
Export conversation to Word (.docx) with **syntax highlighting**, **native math equations**, **Mermaid diagrams**, **citations**, and **enhanced table formatting**.
@@ -86,3 +86,10 @@ Export conversation to Word (.docx) with **syntax highlighting**, **native math
- **Font & Style Configuration**: Customizable fonts and table colors.
- **Mermaid Enhancements**: Hybrid SVG+PNG rendering, background color config.
- **Performance**: Real-time progress updates for large exports.
## Troubleshooting ❓
- **Plugin not working?**: Check if the filter/action is enabled in the model settings.
- **Debug Logs**: Check the browser console (F12) for detailed logs if available.
- **Error Messages**: If you see an error, please copy the full error message and report it.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

9
plugins/actions/export_to_docx/README_CN.md
View File

@@ -1,6 +1,6 @@
# 📝 导出为 Word (增强版)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.4.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
将对话导出为 Word (.docx)，支持**代码语法高亮**、**原生数学公式**、**Mermaid 图表**、**引用参考**和**增强表格格式**。
@@ -86,3 +86,10 @@
- **字体与样式配置**: 支持自定义中英文字体、代码字体以及表格颜色。
- **Mermaid 增强**: 混合 SVG+PNG 渲染，支持背景色配置。
- **性能优化**: 导出大型文档时提供实时进度反馈。
## 故障排除 (Troubleshooting) ❓
- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
- **调试日志**: 请查看浏览器控制台 (F12) 获取详细日志（如果可用）。
- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

55
plugins/actions/flash-card/README.md
View File

@@ -2,9 +2,18 @@
Generate polished learning flashcards from any text—title, summary, key points, tags, and category—ready for review and sharing.
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.2.4 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
## Preview 📸
![Flash Card Example](flash_card.png)
## Highlights
## What's New
### v0.2.4
- **Clean Output**: Removed debug messages from output.
## Key Features 🔑
- **One-click generation**: Drop in text, get a structured card.
- **Concise extraction**: 3–5 key points and 2–4 tags automatically surfaced.
@@ -12,7 +21,14 @@ Generate polished learning flashcards from any text—title, summary, key points
- **Progressive merge**: Multiple runs append cards into the same HTML container; enable clearing to reset.
- **Status updates**: Live notifications for generating/done/error.
## Parameters
## How to Use 🛠️
1. **Install**: Add the plugin to your OpenWebUI instance.
2. **Configure**: Adjust settings in the Valves menu (optional).
3. **Trigger**: Send text to the chat.
4. **Result**: Watch status updates; the card HTML is embedded into the latest message.
## Configuration (Valves) ⚙️
| Param | Description | Default |
| ------------------- | ------------------------------------------------------------ | ------- |
@@ -23,34 +39,9 @@ Generate polished learning flashcards from any text—title, summary, key points
| CLEAR_PREVIOUS_HTML | Whether to clear previous card HTML (otherwise append/merge) | false |
| MESSAGE_COUNT | Use the latest N messages to build the card | 1 |
## How to Use
## Troubleshooting ❓
1. Install and enable “Flash Card”.
2. Send the text to the chat (multi-turn supported; governed by MESSAGE_COUNT).
3. Watch status updates; the card HTML is embedded into the latest message.
4. To regenerate from scratch, toggle CLEAR_PREVIOUS_HTML or resend text.
## Output Format
- JSON fields: `title`, `summary`, `key_points` (3–5), `tags` (2–4), `category`.
- UI: gradient-styled card with tags, key-point list; supports stacking multiple cards.
## Tips
- Very short text triggers a prompt to add more; consider summarizing first.
- Long text is accepted; for deep analysis, pre-condense with other tools before card creation.
## Author
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## License
MIT License
## Changelog
### v0.2.4
- Removed debug messages from output
- **Plugin not working?**: Check if the filter/action is enabled in the model settings.
- **Debug Logs**: Enable `SHOW_STATUS` in Valves to see progress updates.
- **Error Messages**: If you see an error, please copy the full error message and report it.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

55
plugins/actions/flash-card/README_CN.md
View File

@@ -2,9 +2,18 @@
快速将文本提炼为精美的学习记忆卡片，自动抽取标题、摘要、关键要点、标签和分类，适合复习与分享。
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.2.4 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
## 预览 📸
![闪记卡示例](flash_card_cn.png)
## 功能亮点
## 更新日志
### v0.2.4
- **输出优化**: 移除输出中的调试信息。
## 核心特性 🔑
- **一键生成**：输入任意文本，直接产出结构化卡片。
- **要点聚合**：自动提取 3-5 个记忆要点与 2-4 个标签。
@@ -12,7 +21,14 @@
- **渐进合并**：多次调用会将新卡片合并到同一 HTML 容器中；如需重置可启用清空选项。
- **状态提示**：实时推送“生成中/完成/错误”等状态与通知。
## 参数说明
## 使用方法 🛠️
1. **安装**: 在插件市场安装并启用“闪记卡”。
2. **配置**: 根据需要调整 Valves 设置（可选）。
3. **触发**: 将待整理的文本发送到聊天框。
4. **结果**: 等待状态提示，卡片将以 HTML 形式嵌入到最新消息中。
## 配置参数 (Valves) ⚙️
| 参数 | 说明 | 默认值 |
| ------------------- | ------------------------------------- | ------ |
@@ -23,34 +39,9 @@
| CLEAR_PREVIOUS_HTML | 是否清空旧的卡片 HTML（否则合并追加） | false |
| MESSAGE_COUNT | 取最近 N 条消息生成卡片 | 1 |
## 使用步骤
## 故障排除 (Troubleshooting) ❓
1. 在插件市场安装并启用“闪记卡”。
2. 将待整理的文本发送到聊天框（可多轮对话，受 MESSAGE_COUNT 控制）。
3. 等待状态提示，卡片将以 HTML 形式嵌入到最新消息中。
4. 若需重新生成，开启 CLEAR_PREVIOUS_HTML 或直接重发文本。
## 输出格式
- JSON 字段：`title`、`summary`、`key_points`（3-5 条）、`tags`（2-4 条）、`category`。
- 前端呈现：单卡片带渐变主题、标签胶囊、要点列表，可连续追加多张卡片。
## 使用建议
- 文本过短会提醒补充，可先汇总再生成卡片。
- 长文本无需截断，直接生成；如需深度分析可先用其他工具精炼后再制作卡片。
## 作者
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 许可证
MIT License
## 更新日志
### v0.2.4
- 移除输出中的调试信息
- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
- **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

10
plugins/actions/infographic/README.md
View File

@@ -1,6 +1,6 @@
# 📊 Smart Infographic (AntV)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.4.9 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.4.9 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
An Open WebUI plugin powered by the AntV Infographic engine. It transforms long text into professional, beautiful infographics with a single click.
@@ -56,6 +56,14 @@ You can adjust the following parameters in the plugin settings to optimize the g
| **Hierarchy** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | Org Charts, Structures |
| **Charts** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | Trends, Distributions, Metrics |
## Troubleshooting ❓
- **Plugin not working?**: Check if the filter/action is enabled in the model settings.
- **Debug Logs**: Enable `SHOW_STATUS` in Valves to see progress updates.
- **Error Messages**: If you see an error, please copy the full error message and report it.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
## 📝 Syntax Example (For Advanced Users)
You can also input this syntax directly for AI to render:

10
plugins/actions/infographic/README_CN.md
View File

@@ -1,6 +1,6 @@
# 📊 智能信息图 (AntV Infographic)
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.4.9 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui)
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.4.9 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
基于 AntV Infographic 引擎的 Open WebUI 插件，能够将长文本内容一键转换为专业、美观的信息图表。
@@ -56,6 +56,14 @@
| **层级与结构** | `hierarchy-tree-tech-style-capsule-item`, `hierarchy-structure` | 组织架构、层级关系 |
| **图表与数据** | `chart-column-simple`, `chart-bar-plain-text`, `chart-line-plain-text`, `chart-wordcloud` | 数据趋势、比例分布、数值对比 |
## 故障排除 (Troubleshooting) ❓
- **插件不工作？**: 请检查是否在模型设置中启用了该过滤器/动作。
- **调试日志**: 在 Valves 中启用 `SHOW_STATUS` 以查看进度更新。
- **错误信息**: 如果看到错误，请复制完整的错误信息并报告。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
## 📝 语法示例 (高级用户)
你也可以直接输入以下语法让 AI 渲染：

65
plugins/actions/infographic/README_EN.md
View File

@@ -1,65 +0,0 @@
# 📊 Smart Infographic (AntV)
An Open WebUI plugin powered by the AntV Infographic engine. It transforms long text into professional, beautiful infographics with a single click.
## ✨ Key Features
- 🚀 **AI-Powered Transformation**: Automatically analyzes text logic, extracts key points, and generates structured charts.
- 🎨 **Professional Templates**: Includes various AntV official templates: Lists, Trees, Mindmaps, Comparison Tables, Flowcharts, and Statistical Charts.
- 🔍 **Auto-Icon Matching**: Built-in logic to search and match the most relevant Material Design Icons based on content.
- 📥 **Multi-Format Export**: Download your infographics as **SVG**, **PNG**, or a **Standalone HTML** file.
- 🌈 **Highly Customizable**: Supports Dark/Light modes, auto-adapts theme colors, with bold titles and refined card layouts.
- 📱 **Responsive Design**: Generated charts look great on both desktop and mobile devices.
## 🛠️ Supported Template Types
| Category | Template Name | Use Case |
| :--- | :--- | :--- |
| **Lists & Hierarchy** | `list-grid`, `tree-vertical`, `mindmap` | Features, Org Charts, Brainstorming |
| **Sequence & Relation** | `sequence-roadmap`, `relation-circle` | Roadmaps, Circular Flows, Steps |
| **Comparison & Analysis** | `compare-binary`, `compare-swot`, `quadrant-quarter` | Pros/Cons, SWOT, Quadrants |
| **Charts & Data** | `chart-bar`, `chart-line`, `chart-pie` | Trends, Distributions, Metrics |
## 🚀 How to Use
1. **Install**: Search for "Smart Infographic" in the Open WebUI Community and install.
2. **Trigger**: Enter your text in the chat, then click the **Action Button** (📊 icon) next to the input box.
3. **AI Processing**: The AI analyzes the text and generates the infographic syntax.
4. **Preview & Download**: Preview the result and use the download buttons below to save your infographic.
## ⚙️ Configuration (Valves)
You can adjust the following parameters in the plugin settings to optimize the generation:
| Parameter | Default | Description |
| :--- | :--- | :--- |
| **Show Status (SHOW_STATUS)** | `True` | Whether to show real-time AI analysis and generation status in the chat. |
| **Model ID (MODEL_ID)** | `Empty` | Specify the LLM model for text analysis. If empty, the current chat model is used. |
| **Min Text Length (MIN_TEXT_LENGTH)** | `100` | Minimum characters required to trigger analysis, preventing accidental triggers on short text. |
| **Clear Previous (CLEAR_PREVIOUS_HTML)** | `False` | Whether to clear previous charts. If `False`, new charts will be appended below. |
| **Message Count (MESSAGE_COUNT)** | `1` | Number of recent messages to use for analysis. Increase this for more context. |
## 📝 Syntax Example (For Advanced Users)
You can also input this syntax directly for AI to render:
```infographic
infographic list-grid
data
title 🚀 Plugin Benefits
desc Why use the Smart Infographic plugin
items
- label Fast Generation
desc Convert text to charts in seconds
- label Beautiful Design
desc Uses AntV professional design standards
```
## 👨‍💻 Author
**jeff**
- GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 📄 License
MIT License

381
plugins/actions/smart-mind-map/README.md
View File

@@ -1,14 +1,10 @@
# Smart Mind Map - Mind Mapping Generation Plugin
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.9.1 | **License:** MIT
> **Important**: To ensure the maintainability and usability of all plugins, each plugin should be accompanied by clear and comprehensive documentation to ensure its functionality, configuration, and usage are well explained.
Smart Mind Map is a powerful OpenWebUI action plugin that intelligently analyzes long-form text content and automatically generates interactive mind maps, helping users structure and visualize knowledge.
---
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 0.9.1 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
## 🔥 What's New in v0.9.1
## What's New in v0.9.1
**New Feature: Image Output Mode**
@@ -18,362 +14,51 @@ Smart Mind Map is a powerful OpenWebUI action plugin that intelligently analyzes
- **Efficient Storage**: Image mode uploads SVG to `/api/v1/files`, avoiding huge base64 strings in chat history.
- **Smart Features**: Auto-responsive width and automatic theme detection (light/dark) for generated images.
| Feature | HTML Mode (Default) | Image Mode |
| :--- | :--- | :--- |
| **Output Format** | Interactive HTML Block | Static Markdown Image |
| **Interactivity** | Zoom, Pan, Expand/Collapse | None (Static Image) |
| **Chat History** | Contains HTML Code | Clean (Image URL only) |
| **Storage** | Browser Rendering | `/api/v1/files` Upload |
## Key Features 🔑
---
- ✅ **Intelligent Text Analysis**: Automatically identifies core themes, key concepts, and hierarchical structures.
- ✅ **Interactive Visualization**: Generates beautiful interactive mind maps based on Markmap.js.
- ✅ **High-Resolution PNG Export**: Export mind maps as high-quality PNG images (9x scale).
- ✅ **Complete Control Panel**: Zoom controls, expand level selection, and fullscreen mode.
- ✅ **Theme Switching**: Manual theme toggle button with automatic theme detection.
- ✅ **Image Output Mode**: Generate static SVG images embedded directly in Markdown for cleaner history.
## Core Features
## How to Use 🛠️
- ✅ **Intelligent Text Analysis**: Automatically identifies core themes, key concepts, and hierarchical structures
- ✅ **Interactive Visualization**: Generates beautiful interactive mind maps based on Markmap.js
- ✅ **High-Resolution PNG Export**: Export mind maps as high-quality PNG images (9x scale, ~1-2MB file size)
- ✅ **Complete Control Panel**: Zoom controls (+/-/reset), expand level selection (All/2/3 levels), and fullscreen mode
- ✅ **Theme Switching**: Manual theme toggle button (light/dark) with automatic theme detection
- ✅ **Dark Mode Support**: Full dark mode support with automatic detection and manual override
- ✅ **Multi-language Support**: Automatically adjusts output based on user language
- ✅ **Real-time Rendering**: Renders mind maps directly in the chat interface without navigation
- ✅ **Export Capabilities**: Supports PNG, SVG code, and Markdown source export
- ✅ **Customizable Configuration**: Configurable LLM model, minimum text length, and other parameters
- ✅ **Image Output Mode**: Generate static SVG images embedded directly in Markdown (**No HTML code output**, cleaner chat history)
1. **Install**: Upload the `smart_mind_map.py` file in OpenWebUI Admin Settings -> Plugins -> Actions.
2. **Configure**: Ensure you have an LLM model configured (e.g., `gemini-2.5-flash`).
3. **Trigger**: Enable the "Smart Mind Map" action in chat settings and send text (at least 100 characters).
4. **Result**: The mind map will be rendered directly in the chat interface.
---
## How It Works
1. **Text Extraction**: Extracts text content from user messages (automatically filters HTML code blocks)
2. **Intelligent Analysis**: Analyzes text structure using the configured LLM model
3. **Markdown Generation**: Converts analysis results to Markmap-compatible Markdown format
4. **Visual Rendering**: Renders the mind map using Markmap.js in an HTML template with optimized font hierarchy (H1: 22px bold, H2: 18px bold)
5. **Interactive Display**: Presents the mind map to users in an interactive format with complete control panel
6. **Theme Detection**: Automatically detects and applies the current OpenWebUI theme (light/dark mode)
7. **Export Options**: Provides PNG (high-resolution), SVG, and Markdown export functionality
---
## Installation and Configuration
### 1. Plugin Installation
1. Download the `smart_mind_map_cn.py` file to your local computer
2. In OpenWebUI Admin Settings, find the "Plugins" section
3. Select "Actions" type
4. Upload the downloaded file
5. Refresh the page, and the plugin will be available
### 2. Model Configuration
The plugin requires access to an LLM model for text analysis. Please ensure:
- Your OpenWebUI instance has at least one available LLM model configured
- Recommended to use fast, economical models (e.g., `gemini-2.5-flash`) for the best experience
- Configure the `LLM_MODEL_ID` parameter in the plugin settings
### 3. Plugin Activation
Select the "Smart Mind Map" action plugin in chat settings to enable it.
### 4. Theme Color Consistency (Optional)
To keep the mind map visually consistent with the OpenWebUI theme colors, enable same-origin access for artifacts in OpenWebUI:
- **Configuration Location**: In OpenWebUI User Settings: **Interface** → **Artifacts** → **iframe Sandbox Allow Same Origin**
- **Enable Option**: Check the "Allow same-origin access for artifacts" / "iframe sandbox allow-same-origin" option
- **Sandbox Attributes**: Ensure the iframe's sandbox attribute includes both `allow-same-origin` and `allow-scripts`
Once enabled, the mind map will automatically detect and apply the current OpenWebUI theme (light/dark) without any manual configuration.
---
## Configuration Parameters
You can adjust the following parameters in the plugin's settings (Valves):
## Configuration (Valves) ⚙️
| Parameter | Default | Description |
| :--- | :--- | :--- |
| `show_status` | `true` | Whether to display operation status updates in the chat interface (e.g., "Analyzing..."). |
| `LLM_MODEL_ID` | `gemini-2.5-flash` | LLM model ID for text analysis. Recommended to use fast and economical models. |
| `MIN_TEXT_LENGTH` | `100` | Minimum text length (in characters) required for mind map analysis. Text that's too short cannot generate valid mind maps. |
| `CLEAR_PREVIOUS_HTML` | `false` | Whether to clear previous plugin-generated HTML content when generating a new mind map. |
| `MESSAGE_COUNT` | `1` | Number of recent messages to use for mind map generation (1-5). |
| `OUTPUT_MODE` | `html` | Output mode: `html` for interactive HTML (default), or `image` to embed as static Markdown image. |
| `show_status` | `true` | Whether to display operation status updates. |
| `LLM_MODEL_ID` | `gemini-2.5-flash` | LLM model ID for text analysis. |
| `MIN_TEXT_LENGTH` | `100` | Minimum text length required for analysis. |
| `CLEAR_PREVIOUS_HTML` | `false` | Whether to clear previous plugin-generated HTML content. |
| `MESSAGE_COUNT` | `1` | Number of recent messages to use for generation (1-5). |
| `OUTPUT_MODE` | `html` | Output mode: `html` (interactive) or `image` (static). |
---
## Troubleshooting ❓
## Usage
### Basic Usage
1. Enable the "Smart Mind Map" action in chat settings
2. Input or paste long-form text content (at least 100 characters) in the conversation
3. After sending the message, the plugin will automatically analyze and generate a mind map
4. The mind map will be rendered directly in the chat interface
### Usage Example
**Input Text:**
```
Artificial Intelligence (AI) is a branch of computer science dedicated to creating systems capable of performing tasks that typically require human intelligence.
Main application areas include:
1. Machine Learning - Enables computers to learn from data
2. Natural Language Processing - Understanding and generating human language
3. Computer Vision - Recognizing and processing images
4. Robotics - Creating intelligent systems that can interact with the physical world
```
**Generated Result:**
The plugin will generate an interactive mind map centered on "Artificial Intelligence", including major application areas and their sub-concepts.
### Export Features
Generated mind maps support three export methods:
1. **Download PNG**: Click the "📥 Download PNG" button to export the mind map as a high-resolution PNG image (9x scale, ~1-2MB file size)
2. **Copy SVG Code**: Click the "Copy SVG Code" button to copy the mind map in SVG format to the clipboard
3. **Copy Markdown**: Click the "Copy Markdown" button to copy the raw Markdown format to the clipboard
### Control Panel
The interactive mind map includes a comprehensive control panel:
- **Zoom Controls**: `+` (zoom in), `-` (zoom out), `↻` (reset view)
- **Expand Level**: Switch between "All", "2 Levels", "3 Levels" to control node expansion depth
- **Fullscreen**: Enter fullscreen mode for better viewing experience
- **Theme Toggle**: Manually switch between light and dark themes
- **Plugin not working?**: Check if the action is enabled in the chat settings.
- **Text too short**: Ensure input text contains at least 100 characters.
- **Rendering failed**: Check browser console for errors related to Markmap.js or D3.js.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
---
## Technical Architecture
### Frontend Rendering
- **Markmap.js**: Open-source mind mapping rendering engine
- **D3.js**: Data visualization foundation library
- **Responsive Design**: Adapts to different screen sizes
- **Font Hierarchy**: Optimized typography with H1 (22px bold) and H2 (18px bold) for better readability
### PNG Export Technology
- **SVG to Canvas Conversion**: Converts mind map SVG to canvas for PNG export
- **ForeignObject Handling**: Properly processes HTML content within SVG elements
- **High Resolution**: 9x scale factor for print-quality output (~1-2MB file size)
- **Theme Preservation**: Maintains current theme (light/dark) in exported PNG
### Theme Detection Mechanism
Automatically detects and applies themes with a 4-level priority:
1. **Explicit Toggle**: User manually clicks theme toggle button (highest priority)
2. **Meta Tag**: Reads `<meta name="theme-color">` from parent document
3. **Class/Data-Theme**: Checks `class` or `data-theme` attributes on parent HTML/body
4. **System Preference**: Falls back to `prefers-color-scheme` media query
### Backend Processing
- **LLM Integration**: Calls configured models via `generate_chat_completion`
- **Text Preprocessing**: Automatically filters HTML code blocks, extracts plain text content
- **Format Conversion**: Converts LLM output to Markmap-compatible Markdown format
### Security Enhancements
- **XSS Protection**: Automatically escapes `</script>` tags to prevent script injection
- **Input Validation**: Checks text length to avoid invalid requests
- **Non-Bubbling Events**: Button clicks use `stopPropagation()` to prevent navigation interception
---
## Troubleshooting
### Issue: Plugin Won't Start
**Solution:**
- Check OpenWebUI logs for error messages
- Confirm the plugin is correctly uploaded and enabled
- Verify OpenWebUI version supports action plugins
### Issue: Text Content Too Short
**Symptom:** Prompt shows "Text content is too short for effective analysis"
**Solution:**
- Ensure input text contains at least 100 characters (default configuration)
- Lower the `MIN_TEXT_LENGTH` parameter value in plugin settings
- Provide more detailed, structured text content
### Issue: Mind Map Not Generated
**Solution:**
- Check if `LLM_MODEL_ID` is configured correctly
- Confirm the configured model is available in OpenWebUI
- Review backend logs for LLM call failures
- Verify user has sufficient permissions to access the configured model
### Issue: Mind Map Display Error
**Symptom:** Shows "⚠️ Mind map rendering failed"
**Solution:**
- Check browser console for error messages
- Confirm Markmap.js and D3.js libraries are loading correctly
- Verify generated Markdown format conforms to Markmap specifications
- Try refreshing the page to re-render
### Issue: PNG Export Not Working
**Symptom:** PNG download button doesn't work or produces blank/corrupted images
**Solution:**
- Ensure browser supports HTML5 Canvas API (all modern browsers do)
- Check browser console for errors related to `toDataURL()` or canvas rendering
- Verify the mind map is fully rendered before clicking export
- Try refreshing the page and re-generating the mind map
- Use Chrome or Firefox for best PNG export compatibility
### Issue: Theme Not Auto-Detected
**Symptom:** Mind map doesn't match OpenWebUI theme colors
**Solution:**
- Enable "iframe Sandbox Allow Same Origin" in OpenWebUI Settings → Interface → Artifacts
- Verify the iframe's sandbox attribute includes both `allow-same-origin` and `allow-scripts`
- Ensure parent document has `<meta name="theme-color">` tag or theme class/attribute
- Use the manual theme toggle button to override automatic detection
- Check browser console for cross-origin errors
### Issue: Export Function Not Working
**Solution:**
- Confirm browser supports Clipboard API
- Check if browser is blocking clipboard access permissions
- Use modern browsers (Chrome, Firefox, Edge, etc.)
---
- **Markmap.js**: Open-source mind mapping rendering engine.
- **PNG Export**: 9x scale factor for print-quality output (~1-2MB file size).
- **Theme Detection**: 4-level priority detection (Manual > Meta > Class > System).
- **Security**: XSS protection and input validation.
## Best Practices
1. **Text Preparation**
- Provide text content with clear structure and distinct hierarchies
- Use paragraphs, lists, and other formatting to help LLM understand text structure
- Avoid excessively lengthy or unstructured text
2. **Model Selection**
- For daily use, recommend fast models like `gemini-2.5-flash`
- For complex text analysis, use more powerful models (e.g., GPT-4)
- Balance speed and analysis quality based on needs
3. **Performance Optimization**
- Set `MIN_TEXT_LENGTH` appropriately to avoid processing text that's too short
- For particularly long texts, consider summarizing before generating mind maps
- Disable `show_status` in production environments to reduce interface updates
4. **Export Quality**
- **PNG Export**: Best for presentations, documents, and sharing (9x resolution suitable for printing)
- **SVG Export**: Best for further editing in vector graphics tools (infinite scalability)
- **Markdown Export**: Best for version control, collaboration, and regeneration
5. **Theme Consistency**
- Enable same-origin access for automatic theme detection
- Use manual theme toggle if automatic detection fails
- Export PNG after switching to desired theme for consistent visuals
---
## Requirements
This plugin uses only OpenWebUI's built-in dependencies. **No additional packages need to be installed.**
---
## Changelog
### v0.9.1
**New Feature: Image Output Mode**
- Added `OUTPUT_MODE` configuration parameter with two options:
- `html` (default): Interactive HTML mind map with full control panel
- `image`: Static SVG image embedded directly in Markdown (uploaded to `/api/v1/files`)
- Image mode features:
- Auto-responsive width (adapts to chat container)
- Automatic theme detection (light/dark)
- Persistent storage via Chat API (survives page refresh)
- Efficient file storage (no huge base64 strings in chat history)
**Improvements:**
- Implemented robust Chat API update mechanism with retry logic
- Fixed message persistence using both `messages[]` and `history.messages`
- Added Event API for immediate frontend updates
- Removed unnecessary `SVG_WIDTH` and `SVG_HEIGHT` parameters (now auto-calculated)
**Technical Details:**
- Image mode uses `__event_call__` to execute JavaScript in the browser
- SVG is rendered offline, converted to Blob, and uploaded to OpenWebUI Files API
- Updates chat message with `/api/v1/files/{id}/content` URL via OpenWebUI Backend-Controlled API flow
### v0.8.2
- Removed debug messages from output
### v0.8.0 (Previous Version)
**Major Features:**
- Added high-resolution PNG export (9x scale, ~1-2MB file size)
- Implemented complete control panel with zoom controls (+/-/reset)
- Added expand level selection (All/2/3 levels)
- Integrated fullscreen mode with auto-fit
- Added manual theme toggle button (light/dark)
- Implemented automatic theme detection with 4-level priority
**Improvements:**
- Optimized font hierarchy (H1: 22px bold, H2: 18px bold)
- Enhanced dark mode with full theme support
- Improved PNG export technology (SVG to Canvas with foreignObject handling)
- Added theme preservation in exported PNG images
- Enhanced security with non-bubbling button events
**Bug Fixes:**
- Fixed theme detection in cross-origin iframes
- Resolved PNG export issues with HTML content in SVG
- Improved compatibility with OpenWebUI theme system
### v0.7.2
- Optimized text extraction logic, automatically filters HTML code blocks
- Improved error handling and user feedback
- Enhanced export functionality compatibility
- Optimized UI styling and interactive experience
---
## License
This plugin is released under the MIT License.
## Contributing
Welcome to submit issue reports and improvement suggestions! Please visit the project repository: [awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
---
## Related Resources
- [Markmap Official Website](https://markmap.js.org/)
- [OpenWebUI Documentation](https://docs.openwebui.com/)
- [D3.js Official Website](https://d3js.org/)
1. **Text Preparation**: Provide text with clear structure and distinct hierarchies.
2. **Model Selection**: Use fast models like `gemini-2.5-flash` for daily use.
3. **Export Quality**: Use PNG for presentations and SVG for further editing.

379
plugins/actions/smart-mind-map/README_CN.md
View File

@@ -1,14 +1,10 @@
# 思维导图 - 思维导图生成插件
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.9.1 | **许可证:** MIT
> **重要提示**：为了确保所有插件的可维护性和易用性，每个插件都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。
思维导图是一个强大的 OpenWebUI 动作插件，能够智能分析长篇文本内容，自动生成交互式思维导图，帮助用户结构化和可视化知识。
---
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 0.9.1 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
## 🔥 v0.9.1 更新亮点
## v0.9.1 更新亮点
**新功能：图片输出模式**
@@ -18,362 +14,51 @@
- **高效存储**：图片模式将 SVG 上传至 `/api/v1/files`，避免聊天记录中出现超长 Base64 字符串。
- **智能特性**：生成的图片支持自动响应式宽度和自动主题检测（亮色/暗色）。
| 特性 | HTML 模式 (默认) | 图片模式 |
| :--- | :--- | :--- |
| **输出格式** | 交互式 HTML 代码块 | 静态 Markdown 图片 |
| **交互性** | 缩放、拖拽、展开/折叠 | 无 (静态图片) |
| **聊天记录** | 包含 HTML 代码 | 简洁 (仅图片链接) |
| **存储方式** | 浏览器实时渲染 | `/api/v1/files` 上传 |
## 核心特性 🔑
---
- ✅ **智能文本分析**：自动识别文本的核心主题、关键概念和层次结构。
- ✅ **交互式可视化**：基于 Markmap.js 生成美观的交互式思维导图。
- ✅ **高分辨率 PNG 导出**：导出高质量的 PNG 图片（9 倍分辨率）。
- ✅ **完整控制面板**：缩放控制、展开层级选择、全屏模式。
- ✅ **主题切换**：手动主题切换按钮与自动主题检测。
- ✅ **图片输出模式**：生成静态 SVG 图片直接嵌入 Markdown，聊天记录更简洁。
## 核心特性
## 使用方法 🛠️
- ✅ **智能文本分析**：自动识别文本的核心主题、关键概念和层次结构
- ✅ **交互式可视化**：基于 Markmap.js 生成美观的交互式思维导图
- ✅ **高分辨率 PNG 导出**：导出高质量的 PNG 图片（9 倍分辨率，约 1-2MB 文件大小）
- ✅ **完整控制面板**：缩放控制（+/-/重置）、展开层级选择（全部/2级/3级）、全屏模式
- ✅ **主题切换**：手动主题切换按钮（亮色/暗色）与自动主题检测
- ✅ **深色模式支持**：完整的深色模式支持，自动检测与手动覆盖
- ✅ **多语言支持**：根据用户语言自动调整输出
- ✅ **实时渲染**：在聊天界面中直接渲染思维导图，无需跳转
- ✅ **导出功能**：支持 PNG、SVG 代码和 Markdown 源码导出
- ✅ **自定义配置**：可配置 LLM 模型、最小文本长度等参数
- ✅ **图片输出模式**：生成静态 SVG 图片直接嵌入 Markdown（**不输出 HTML 代码**，聊天记录更简洁）
1. **安装**: 在 OpenWebUI 管理员设置 -> 插件 -> 动作中上传 `smart_mind_map_cn.py`。
2. **配置**: 确保配置了 LLM 模型（如 `gemini-2.5-flash`）。
3. **触发**: 在聊天设置中启用“思维导图”动作，并发送文本（至少 100 字符）。
4. **结果**: 思维导图将在聊天界面中直接渲染显示。
---
## 工作原理
1. **文本提取**：从用户消息中提取文本内容（自动过滤 HTML 代码块）
2. **智能分析**：使用配置的 LLM 模型分析文本结构
3. **Markdown 生成**：将分析结果转换为 Markmap 兼容的 Markdown 格式
4. **可视化渲染**：在 HTML 模板中使用 Markmap.js 渲染思维导图，并优化字体层级（H1：22px 粗体，H2：18px 粗体）
5. **交互展示**：以可交互的形式展示给用户，并提供完整的控制面板
6. **主题检测**：自动检测并应用当前 OpenWebUI 的主题（亮色/暗色模式）
7. **导出选项**：提供 PNG（高分辨率）、SVG 和 Markdown 导出功能
---
## 安装与配置
### 1. 插件安装
1. 下载 `smart_mind_map_cn.py` 文件到本地
2. 在 OpenWebUI 管理员设置中找到"插件"（Plugins）部分
3. 选择"动作"（Actions）类型
4. 上传下载的文件
5. 刷新页面，插件即可使用
### 2. 模型配置
插件需要访问 LLM 模型来分析文本。请确保：
- 您的 OpenWebUI 实例中配置了至少一个可用的 LLM 模型
- 推荐使用快速、经济的模型（如 `gemini-2.5-flash`）来获得最佳体验
- 在插件设置中配置 `LLM_MODEL_ID` 参数
### 3. 插件启用
在聊天设置中选择"思维导图"动作插件即可启用。
### 4. 主题颜色风格一致性（可选）
为了使思维导图与 OpenWebUI 主题颜色风格保持一致，需要在 OpenWebUI 中启用 artifact 的同源访问：
- **配置位置**：在 OpenWebUI 用户设置中找到"界面"→"产物"部分（Settings → Interface → Products/Artifacts）
- **启用选项**：勾选 "iframe 沙盒允许同源访问"（Allow same-origin access for artifacts / iframe sandbox allow-same-origin）
- **沙箱属性**：确保 iframe 的 sandbox 属性包含 `allow-same-origin` 和 `allow-scripts`
启用后，思维导图会自动检测并应用 OpenWebUI 的当前主题（亮色/暗色），无需手动配置。
---
## 配置参数
您可以在插件的设置（Valves）中调整以下参数：
## 配置参数 (Valves) ⚙️
| 参数 | 默认值 | 描述 |
| :--- | :--- | :--- |
| `show_status` | `true` | 是否在聊天界面显示操作状态更新（如"正在分析..."）。 |
| `LLM_MODEL_ID` | `gemini-2.5-flash` | 用于文本分析的 LLM 模型 ID。推荐使用快速且经济的模型。 |
| `MIN_TEXT_LENGTH` | `100` | 进行思维导图分析所需的最小文本长度（字符数）。文本过短将无法生成有效的导图。 |
| `CLEAR_PREVIOUS_HTML` | `false` | 在生成新的思维导图时，是否清除之前由插件生成的 HTML 内容。 |
| `show_status` | `true` | 是否在聊天界面显示操作状态更新。 |
| `LLM_MODEL_ID` | `gemini-2.5-flash` | 用于文本分析的 LLM 模型 ID。 |
| `MIN_TEXT_LENGTH` | `100` | 进行思维导图分析所需的最小文本长度。 |
| `CLEAR_PREVIOUS_HTML` | `false` | 在生成新的思维导图时，是否清除之前的 HTML 内容。 |
| `MESSAGE_COUNT` | `1` | 用于生成思维导图的最近消息数量（1-5）。 |
| `OUTPUT_MODE` | `html` | 输出模式：`html` 为交互式 HTML（默认），`image` 为嵌入静态 Markdown 图片。 |
| `OUTPUT_MODE` | `html` | 输出模式：`html`（交互式）或 `image`（静态图片）。 |
---
## 故障排除 (Troubleshooting) ❓
## 使用方法
### 基本使用
1. 在聊天设置中启用"思维导图"动作
2. 在对话中输入或粘贴长篇文本内容（至少 100 字符）
3. 发送消息后，插件会自动分析并生成思维导图
4. 思维导图将在聊天界面中直接渲染显示
### 使用示例
**输入文本：**
```
人工智能（AI）是计算机科学的一个分支，致力于创建能够执行通常需要人类智能的任务的系统。
主要应用领域包括：
1. 机器学习 - 使计算机能够从数据中学习
2. 自然语言处理 - 理解和生成人类语言
3. 计算机视觉 - 识别和处理图像
4. 机器人技术 - 创建能够与物理世界交互的智能系统
```
**生成结果：**
插件会生成一个以"人工智能"为中心主题的交互式思维导图，包含主要应用领域及其子概念。
### 导出功能
生成的思维导图支持三种导出方式：
1. **下载 PNG**：点击“📥 下载 PNG”按钮，可将思维导图导出为高分辨率 PNG 图片（9 倍分辨率，约 1-2MB 文件大小）
2. **复制 SVG 代码**：点击“复制 SVG 代码”按钮，可将思维导图的 SVG 格式复制到剪贴板
3. **复制 Markdown**：点击“复制 Markdown”按钮，可将原始 Markdown 格式复制到剪贴板
### 控制面板
交互式思维导图包含完整的控制面板：
- **缩放控制**：`+`（放大）、`-`（缩小）、`↻`（重置视图）
- **展开层级**：在“全部”、“2 级”、“3 级”之间切换，控制节点展开深度
- **全屏模式**：进入全屏模式，获得更好的查看体验
- **主题切换**：手动在亮色和暗色主题之间切换
- **插件无法启动**：检查 OpenWebUI 日志，确认插件已正确上传并启用。
- **文本内容过短**：确保输入的文本至少包含 100 个字符。
- **渲染失败**：检查浏览器控制台，确认 Markmap.js 和 D3.js 库是否正确加载。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)
---
## 技术架构
### 前端渲染
- **Markmap.js**：开源的思维导图渲染引擎
- **D3.js**：数据可视化基础库
- **响应式设计**：适配不同屏幕尺寸
- **字体层级**：优化的字体排版，H1（22px 粗体）和 H2（18px 粗体），提供更好的可读性
### PNG 导出技术
- **SVG 转 Canvas**：将思维导图 SVG 转换为 Canvas 以导出 PNG
- **ForeignObject 处理**：正确处理 SVG 元素中的 HTML 内容
- **高分辨率**：9 倍缩放因子，输出打印级质量（约 1-2MB 文件大小）
- **主题保持**：在导出的 PNG 中保持当前主题（亮色/暗色）
### 主题检测机制
自动检测并应用主题，具有 4 级优先级：
1. **显式切换**：用户手动点击主题切换按钮（最高优先级）
2. **Meta 标签**：从父文档读取 `<meta name="theme-color">`
3. **Class/Data-Theme**：检查父文档 HTML/body 的 `class` 或 `data-theme` 属性
4. **系统偏好**：回退到 `prefers-color-scheme` 媒体查询
### 后端处理
- **LLM 集成**：通过 `generate_chat_completion` 调用配置的模型
- **文本预处理**：自动过滤 HTML 代码块，提取纯文本内容
- **格式转换**：将 LLM 输出转换为 Markmap 兼容的 Markdown 格式
### 安全性增强
- **XSS 防护**：自动转义 `</script>` 标签，防止脚本注入
- **输入验证**：检查文本长度，避免无效请求
- **非冒泡事件**：按钮点击使用 `stopPropagation()` 防止导航拦截
---
## 故障排除
### 问题：插件无法启动
**解决方案：**
- 检查 OpenWebUI 日志，查看是否有错误信息
- 确认插件已正确上传并启用
- 验证 OpenWebUI 版本是否支持动作插件
### 问题：文本内容过短
**现象：** 提示"文本内容过短，无法进行有效分析"
**解决方案：**
- 确保输入的文本至少包含 100 个字符（默认配置）
- 可以在插件设置中降低 `MIN_TEXT_LENGTH` 参数值
- 提供更详细、结构化的文本内容
### 问题：思维导图未生成
**解决方案：**
- 检查 `LLM_MODEL_ID` 是否配置正确
- 确认配置的模型在 OpenWebUI 中可用
- 查看后端日志，检查是否有 LLM 调用失败的错误
- 验证用户是否有足够的权限访问配置的模型
### 问题：思维导图显示错误
**现象：** 显示"⚠️ 思维导图渲染失败"
**解决方案：**
- 检查浏览器控制台的错误信息
- 确认 Markmap.js 和 D3.js 库是否正确加载
- 验证生成的 Markdown 格式是否符合 Markmap 规范
- 尝试刷新页面重新渲染
### 问题：PNG 导出不工作
**现象：**PNG 下载按钮不工作或生成空白/损坏的图片
**解决方案：**
- 确保浏览器支持 HTML5 Canvas API（所有现代浏览器都支持）
- 检查浏览器控制台是否有与 `toDataURL()` 或 Canvas 渲染相关的错误
- 确保思维导图在点击导出前已完全渲染
- 尝试刷新页面并重新生成思维导图
- 使用 Chrome 或 Firefox，获得最佳 PNG 导出兼容性
### 问题：主题未自动检测
**现象：**思维导图不匹配 OpenWebUI 主题颜色
**解决方案：**
- 在 OpenWebUI 设置 → 界面 → 产物中，启用“iframe 沙盒允许同源访问”
- 验证 iframe 的 sandbox 属性包含 `allow-same-origin` 和 `allow-scripts`
- 确保父文档有 `<meta name="theme-color">` 标签或主题 class/属性
- 使用手动主题切换按钮覆盖自动检测
- 检查浏览器控制台是否有跨域错误
### 问题：导出功能不工作
**解决方案：**
- 确认浏览器支持剪贴板 API
- 检查浏览器是否阻止了剪贴板访问权限
- 使用现代浏览器（Chrome、Firefox、Edge 等）
---
- **Markmap.js**：开源的思维导图渲染引擎。
- **PNG 导出技术**：9 倍缩放因子，输出打印级质量。
- **主题检测机制**：4 级优先级检测（手动 > Meta > Class > 系统）。
- **安全性增强**：XSS 防护与输入验证。
## 最佳实践
1. **文本准备**
- 提供结构清晰、层次分明的文本内容
- 使用段落、列表等格式帮助 LLM 理解文本结构
- 避免过于冗长或无结构的文本
2. **模型选择**
- 对于日常使用，推荐 `gemini-2.5-flash` 等快速模型
- 对于复杂文本分析，可以使用更强大的模型（如 GPT-4）
- 根据需求平衡速度和分析质量
3. **性能优化**
- 合理设置 `MIN_TEXT_LENGTH`，避免处理过短的文本
- 对于特别长的文本，考虑先进行摘要再生成思维导图
- 在生产环境中关闭 `show_status` 以减少界面更新
4. **导出质量**
- **PNG 导出**：最适合演示、文档和分享（9 倍分辨率适合打印）
- **SVG 导出**：最适合在矢量图形工具中进一步编辑（无限缩放）
- **Markdown 导出**：最适合版本控制、协作和重新生成
5. **主题一致性**
- 启用同源访问以实现自动主题检测
- 如果自动检测失败，使用手动主题切换
- 在切换到所需主题后导出 PNG，以保持视觉一致性
---
## 依赖要求
本插件仅使用 OpenWebUI 的内置依赖，**无需安装额外的软件包。**
---
## 更新日志
### v0.9.1
**新功能：图片输出模式**
- 新增 `OUTPUT_MODE` 配置参数，支持两种模式：
- `html`（默认）：交互式 HTML 思维导图，带完整控制面板
- `image`：静态 SVG 图片直接嵌入 Markdown（上传至 `/api/v1/files`）
- 图片模式特性：
- 自动响应式宽度（适应聊天容器）
- 自动主题检测（亮色/暗色）
- 通过 Chat API 持久化存储（刷新页面后保留）
- 高效文件存储（聊天记录中无超长 Base64 字符串）
**改进项：**
- 实现健壮的 Chat API 更新机制，带重试逻辑
- 修复消息持久化，同时更新 `messages[]` 和 `history.messages`
- 添加 Event API 实现即时前端更新
- 移除不必要的 `SVG_WIDTH` 和 `SVG_HEIGHT` 参数（现已自动计算）
**技术细节：**
- 图片模式使用 `__event_call__` 在浏览器中执行 JavaScript
- SVG 离屏渲染，转换为 Blob，并上传至 OpenWebUI Files API
- 通过 OpenWebUI Backend-Controlled API 流程更新聊天消息为 `/api/v1/files/{id}/content` URL
### v0.8.2
- 移除输出中的调试信息
### v0.8.0 (Previous Version)
**主要功能：**
- 添加高分辨率 PNG 导出（9 倍分辨率，约 1-2MB 文件大小）
- 实现完整的控制面板，包含缩放控制（+/-/重置）
- 添加展开层级选择（全部/2级/3级）
- 集成全屏模式，自动适应
- 添加手动主题切换按钮（亮色/暗色）
- 实现 4 级优先级的自动主题检测
**改进项：**
- 优化字体层级（H1：22px 粗体，H2：18px 粗体）
- 增强深色模式，完整的主题支持
- 改进 PNG 导出技术（SVG 转 Canvas，处理 foreignObject）
- 在导出的 PNG 图片中保持主题
- 增强安全性，按钮事件使用非冒泡机制
**Bug 修复：**
- 修复跨域 iframe 中的主题检测问题
- 解决 SVG 中 HTML 内容的 PNG 导出问题
- 改进与 OpenWebUI 主题系统的兼容性
### v0.7.2
- 优化文本提取逻辑，自动过滤 HTML 代码块
- 改进错误处理和用户反馈
- 增强导出功能的兼容性
- 优化 UI 样式和交互体验
---
## 许可证
本插件采用 MIT 许可证发布。
## 贡献
欢迎提交问题报告和改进建议！请访问项目仓库：[awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
---
## 相关资源
- [Markmap 官方网站](https://markmap.js.org/)
- [OpenWebUI 文档](https://docs.openwebui.com/)
- [D3.js 官方网站](https://d3js.org/)
1. **文本准备**：提供结构清晰、层次分明的文本内容。
2. **模型选择**：日常使用推荐 `gemini-2.5-flash` 等快速模型。
3. **导出质量**：PNG 适合演示分享，SVG 适合进一步矢量编辑。

4
plugins/filters/README.md
View File

@@ -48,7 +48,3 @@ When adding a new filter, please follow these steps:
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## License
MIT License

4
plugins/filters/README_CN.md
View File

@@ -70,7 +70,3 @@
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 许可证
MIT License

7
plugins/filters/async-context-compression/README.md
View File

@@ -1,6 +1,6 @@
# Async Context Compression Filter
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.1.3 | **License:** MIT
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.1.3 | **Project:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **License:** MIT
This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.
@@ -69,9 +69,6 @@ It is recommended to keep this filter early in the chain so it runs before filte
---
## Troubleshooting
- **Database table not created**: Ensure Open WebUI is configured with a database and check Open WebUI logs for errors.
- **Summary not generated**: Confirm `compression_threshold_tokens` was hit and `summary_model` is compatible. Review logs for details.
- **Initial system prompt is lost**: Keep `keep_first` greater than 0 to protect the initial message.
- **Compression effect is weak**: Raise `compression_threshold_tokens` or lower `keep_first` / `keep_last` to allow more aggressive compression.
- **Submit an Issue**: If you encounter any problems, please submit an issue on GitHub: [Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

7
plugins/filters/async-context-compression/README_CN.md
View File

@@ -1,6 +1,6 @@
# 异步上下文压缩过滤器
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.1.3 | **许可证:** MIT
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.1.3 | **项目:** [Awesome OpenWebUI](https://github.com/Fu-Jie/awesome-openwebui) | **许可证:** MIT
> **重要提示**：为了确保所有过滤器的可维护性和易用性，每个过滤器都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。
@@ -112,9 +112,6 @@
---
## 故障排除
- **数据库表未创建**：确保 Open WebUI 已配置数据库，并查看日志获取错误信息。
- **摘要未生成**：检查是否达到 `compression_threshold_tokens`，确认 `summary_model` 可用，并查看日志。
- **初始系统提示丢失**：将 `keep_first` 设置为大于 0。
- **压缩效果不明显**：提高 `compression_threshold_tokens`，或降低 `keep_first` / `keep_last` 以增强压缩力度。
- **提交 Issue**: 如果遇到任何问题，请在 GitHub 上提交 Issue：[Awesome OpenWebUI Issues](https://github.com/Fu-Jie/awesome-openwebui/issues)

4
plugins/pipes/README.md
View File

@@ -63,7 +63,3 @@ When adding a new pipe plugin, please follow these steps:
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## License
MIT License

4
plugins/pipes/README_CN.md
View File

@@ -63,7 +63,3 @@
Fu-Jie
GitHub: [Fu-Jie/awesome-openwebui](https://github.com/Fu-Jie/awesome-openwebui)
## 许可证
MIT License