docs: update documentation, add new filters, remove deprecated plugins
This commit is contained in:
fujie
2054
.github/copilot-instructions.md
vendored
2054
.github/copilot-instructions.md
vendored
File diff suppressed because it is too large
Load Diff
@@ -1,9 +1,9 @@
|
||||
# Knowledge Card
|
||||
# Flash Card
|
||||
|
||||
<span class="category-badge action">Action</span>
|
||||
<span class="version-badge">v0.2.2</span>
|
||||
<span class="version-badge">v0.2.4</span>
|
||||
|
||||
Quickly generates beautiful learning memory cards, perfect for studying and quick memorization.
|
||||
Quickly generates beautiful flashcards from text, extracting key points and categories.
|
||||
|
||||
---
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Knowledge Card（知识卡片）
|
||||
|
||||
<span class="category-badge action">Action</span>
|
||||
<span class="version-badge">v0.2.0</span>
|
||||
<span class="version-badge">v0.2.4</span>
|
||||
|
||||
快速生成精美的学习记忆卡片，适合学习和速记。
|
||||
|
||||
@@ -23,7 +23,7 @@ Actions are interactive plugins that:
|
||||
|
||||
Intelligently analyzes text content and generates interactive mind maps with beautiful visualizations.
|
||||
|
||||
**Version:** 0.8.0
|
||||
**Version:** 0.9.1
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](smart-mind-map.md)
|
||||
|
||||
@@ -37,15 +37,15 @@ Actions are interactive plugins that:
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](smart-infographic.md)
|
||||
|
||||
- :material-card-text:{ .lg .middle } **Knowledge Card**
|
||||
- :material-card-text:{ .lg .middle } **Flash Card**
|
||||
|
||||
---
|
||||
|
||||
Quickly generates beautiful learning memory cards, perfect for studying and memorization.
|
||||
Quickly generates beautiful flashcards from text, extracting key points and categories.
|
||||
|
||||
**Version:** 0.2.2
|
||||
**Version:** 0.2.4
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](knowledge-card.md)
|
||||
[:octicons-arrow-right-24: Documentation](flash-card.md)
|
||||
|
||||
- :material-file-excel:{ .lg .middle } **Export to Excel**
|
||||
|
||||
@@ -77,15 +77,7 @@ Actions are interactive plugins that:
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](deep-dive.md)
|
||||
|
||||
- :material-image-text:{ .lg .middle } **Infographic to Markdown**
|
||||
|
||||
---
|
||||
|
||||
AI-powered infographic generator that renders SVG and embeds it as Markdown Data URL image.
|
||||
|
||||
**Version:** 1.0.0
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](infographic-markdown.md)
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Smart Mind Map
|
||||
|
||||
<span class="category-badge action">Action</span>
|
||||
<span class="version-badge">v0.8.0</span>
|
||||
<span class="version-badge">v0.9.1</span>
|
||||
|
||||
Intelligently analyzes text content and generates interactive mind maps for better visualization and understanding.
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Smart Mind Map（智能思维导图）
|
||||
|
||||
<span class="category-badge action">Action</span>
|
||||
<span class="version-badge">v0.8.0</span>
|
||||
<span class="version-badge">v0.9.1</span>
|
||||
|
||||
智能分析文本内容，生成交互式思维导图，帮助你更直观地理解信息结构。
|
||||
|
||||
|
||||
@@ -1,54 +0,0 @@
|
||||
# Gemini Manifold Companion
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.3.2</span>
|
||||
|
||||
Companion filter for the Gemini Manifold pipe plugin, providing enhanced functionality.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
The Gemini Manifold Companion works alongside the [Gemini Manifold Pipe](../pipes/gemini-manifold.md) to provide additional processing and enhancement for Gemini model integrations.
|
||||
|
||||
## Features
|
||||
|
||||
- :material-handshake: **Seamless Integration**: Works with Gemini Manifold pipe
|
||||
- :material-format-text: **Message Formatting**: Optimizes messages for Gemini
|
||||
- :material-shield: **Error Handling**: Graceful handling of API issues
|
||||
- :material-tune: **Fine-tuning**: Additional configuration options
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
1. First, install the [Gemini Manifold Pipe](../pipes/gemini-manifold.md)
|
||||
2. Download the companion filter: [`gemini_manifold_companion.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/gemini_manifold_companion)
|
||||
3. Upload to OpenWebUI: **Admin Panel** → **Settings** → **Functions**
|
||||
4. Enable the filter
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
|
||||
| Option | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `auto_format` | boolean | `true` | Auto-format messages for Gemini |
|
||||
| `handle_errors` | boolean | `true` | Enable error handling |
|
||||
|
||||
---
|
||||
|
||||
## Requirements
|
||||
|
||||
!!! warning "Dependency"
|
||||
This filter requires the **Gemini Manifold Pipe** to be installed and configured.
|
||||
|
||||
!!! note "Prerequisites"
|
||||
- OpenWebUI v0.3.0 or later
|
||||
- Gemini Manifold Pipe installed
|
||||
|
||||
---
|
||||
|
||||
## Source Code
|
||||
|
||||
[:fontawesome-brands-github: View on GitHub](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/gemini_manifold_companion){ .md-button }
|
||||
@@ -1,54 +0,0 @@
|
||||
# Gemini Manifold Companion
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.3.2</span>
|
||||
|
||||
Gemini Manifold Pipe 的伴随过滤器，用于增强 Gemini 集成的处理效果。
|
||||
|
||||
---
|
||||
|
||||
## 概览
|
||||
|
||||
Gemini Manifold Companion 与 [Gemini Manifold Pipe](../pipes/gemini-manifold.md) 搭配使用，为 Gemini 模型集成提供额外的处理与优化。
|
||||
|
||||
## 功能特性
|
||||
|
||||
- :material-handshake: **无缝协同**：与 Gemini Manifold Pipe 配合工作
|
||||
- :material-format-text: **消息格式化**：针对 Gemini 优化消息
|
||||
- :material-shield: **错误处理**：更友好的 API 异常处理
|
||||
- :material-tune: **精细配置**：提供额外调优选项
|
||||
|
||||
---
|
||||
|
||||
## 安装
|
||||
|
||||
1. 先安装 [Gemini Manifold Pipe](../pipes/gemini-manifold.md)
|
||||
2. 下载伴随过滤器：[`gemini_manifold_companion.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/gemini_manifold_companion)
|
||||
3. 上传到 OpenWebUI：**Admin Panel** → **Settings** → **Functions**
|
||||
4. 启用过滤器
|
||||
|
||||
---
|
||||
|
||||
## 配置项
|
||||
|
||||
| 选项 | 类型 | 默认值 | 说明 |
|
||||
|--------|------|---------|-------------|
|
||||
| `auto_format` | boolean | `true` | 为 Gemini 自动格式化消息 |
|
||||
| `handle_errors` | boolean | `true` | 开启错误处理 |
|
||||
|
||||
---
|
||||
|
||||
## 运行要求
|
||||
|
||||
!!! warning "依赖"
|
||||
本过滤器需要先安装并配置 **Gemini Manifold Pipe**。
|
||||
|
||||
!!! note "前置条件"
|
||||
- OpenWebUI v0.3.0 及以上
|
||||
- 已安装 Gemini Manifold Pipe
|
||||
|
||||
---
|
||||
|
||||
## 源码
|
||||
|
||||
[:fontawesome-brands-github: 在 GitHub 查看](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/gemini_manifold_companion){ .md-button }
|
||||
@@ -36,15 +36,7 @@ Filters act as middleware in the message pipeline:
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](context-enhancement.md)
|
||||
|
||||
- :material-google:{ .lg .middle } **Gemini Manifold Companion**
|
||||
|
||||
---
|
||||
|
||||
Companion filter for the Gemini Manifold pipe plugin.
|
||||
|
||||
**Version:** 1.7.0
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](gemini-manifold-companion.md)
|
||||
|
||||
- :material-format-paint:{ .lg .middle } **Markdown Normalizer**
|
||||
|
||||
@@ -52,10 +44,30 @@ Filters act as middleware in the message pipeline:
|
||||
|
||||
Fixes common Markdown formatting issues in LLM outputs, including Mermaid syntax, code blocks, and LaTeX formulas.
|
||||
|
||||
**Version:** 1.0.1
|
||||
**Version:** 1.1.2
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](markdown_normalizer.md)
|
||||
|
||||
- :material-merge:{ .lg .middle } **Multi-Model Context Merger**
|
||||
|
||||
---
|
||||
|
||||
Automatically merges context from multiple model responses in the previous turn, enabling collaborative answers.
|
||||
|
||||
**Version:** 0.1.0
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](multi-model-context-merger.md)
|
||||
|
||||
- :material-file-document-multiple:{ .lg .middle } **Web Gemini Multimodal Filter**
|
||||
|
||||
---
|
||||
|
||||
A powerful filter that provides multimodal capabilities (PDF, Office, Images, Audio, Video) to any model in OpenWebUI.
|
||||
|
||||
**Version:** 0.3.2
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](web-gemini-multimodel.md)
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
35
docs/plugins/filters/multi-model-context-merger.md
Normal file
35
docs/plugins/filters/multi-model-context-merger.md
Normal file
@@ -0,0 +1,35 @@
|
||||
# Multi-Model Context Merger
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.1.0</span>
|
||||
|
||||
Automatically merges context from multiple model responses in the previous turn, enabling collaborative answers.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This filter detects when multiple models have responded in the previous turn (e.g., using "Arena" mode or multiple models selected). It consolidates these responses and injects them as context for the current turn, allowing the next model to see what others have said.
|
||||
|
||||
## Features
|
||||
|
||||
- :material-merge: **Auto-Merge**: Consolidates responses from multiple models into a single context block.
|
||||
- :material-format-list-group: **Structured Injection**: Uses XML-like tags (`<response>`) to separate different model outputs.
|
||||
- :material-robot-confused: **Collaboration**: Enables models to build upon or critique each other's answers.
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
1. Download the plugin file: [`multi_model_context_merger.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters)
|
||||
2. Upload to OpenWebUI: **Admin Panel** → **Settings** → **Functions**
|
||||
3. Enable the filter.
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
1. Select **multiple models** in the chat (or use Arena mode).
|
||||
2. Ask a question. All models will respond.
|
||||
3. Ask a follow-up question.
|
||||
4. The filter will inject the previous responses from ALL models into the context of the current model(s).
|
||||
35
docs/plugins/filters/multi-model-context-merger.zh.md
Normal file
35
docs/plugins/filters/multi-model-context-merger.zh.md
Normal file
@@ -0,0 +1,35 @@
|
||||
# 多模型上下文合并 (Multi-Model Context Merger)
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.1.0</span>
|
||||
|
||||
自动合并上一轮中多个模型的回答上下文，实现协作问答。
|
||||
|
||||
---
|
||||
|
||||
## 概述
|
||||
|
||||
此过滤器检测上一轮是否由多个模型回复（例如使用“竞技场”模式或选择了多个模型）。它将这些回复合并并作为上下文注入到当前轮次，使下一个模型能够看到其他模型之前所说的内容。
|
||||
|
||||
## 功能特性
|
||||
|
||||
- :material-merge: **自动合并**: 将多个模型的回复合并为单个上下文块。
|
||||
- :material-format-list-group: **结构化注入**: 使用类似 XML 的标签 (`<response>`) 分隔不同模型的输出。
|
||||
- :material-robot-confused: **协作**: 允许模型基于彼此的回答进行构建或评论。
|
||||
|
||||
---
|
||||
|
||||
## 安装
|
||||
|
||||
1. 下载插件文件: [`multi_model_context_merger.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters)
|
||||
2. 上传到 OpenWebUI: **管理员面板** → **设置** → **函数**
|
||||
3. 启用过滤器。
|
||||
|
||||
---
|
||||
|
||||
## 使用方法
|
||||
|
||||
1. 在聊天中选择 **多个模型** (或使用竞技场模式)。
|
||||
2. 提问。所有模型都会回答。
|
||||
3. 提出后续问题。
|
||||
4. 过滤器会将所有模型之前的回答注入到当前模型的上下文中。
|
||||
51
docs/plugins/filters/web-gemini-multimodel.md
Normal file
51
docs/plugins/filters/web-gemini-multimodel.md
Normal file
@@ -0,0 +1,51 @@
|
||||
# Web Gemini Multimodal Filter
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.3.2</span>
|
||||
|
||||
A powerful filter that provides multimodal capabilities (PDF, Office, Images, Audio, Video) to any model in OpenWebUI.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This plugin enables multimodal processing for any model by leveraging Gemini as an analyzer. It supports direct file processing for Gemini models and "Analyzer Mode" for other models (like DeepSeek, Llama), where Gemini analyzes the file and injects the result as context.
|
||||
|
||||
## Features
|
||||
|
||||
- :material-file-document-multiple: **Multimodal Support**: Process PDF, Word, Excel, PowerPoint, EPUB, MP3, MP4, and Images.
|
||||
- :material-router-network: **Smart Routing**:
|
||||
- **Direct Mode**: Files are passed directly to Gemini models.
|
||||
- **Analyzer Mode**: Files are analyzed by Gemini, and results are injected into the context for other models.
|
||||
- :material-history: **Persistent Context**: Maintains session history across multiple turns using OpenWebUI Chat ID.
|
||||
- :material-database-check: **Deduplication**: Automatically tracks analyzed file hashes to prevent redundant processing.
|
||||
- :material-subtitles: **Subtitle Enhancement**: Specialized mode for generating high-quality SRT subtitles from video/audio.
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
1. Download the plugin file: [`web_gemini_multimodel.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/web_gemini_multimodel_filter)
|
||||
2. Upload to OpenWebUI: **Admin Panel** → **Settings** → **Functions**
|
||||
3. Configure the Gemini Adapter URL and other settings.
|
||||
4. Enable the filter globally or per chat.
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
|
||||
| Option | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `gemini_adapter_url` | string | `http://...` | URL of the Gemini Adapter service |
|
||||
| `target_model_keyword` | string | `"webgemini"` | Keyword to identify Gemini models |
|
||||
| `mode` | string | `"auto"` | `auto`, `direct`, or `analyzer` |
|
||||
| `analyzer_base_model_id` | string | `"gemini-3.0-pro"` | Model used for document analysis |
|
||||
| `subtitle_keywords` | string | `"字幕,srt"` | Keywords to trigger subtitle flow |
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
1. **Upload a file** (PDF, Image, Video, etc.) in the chat.
|
||||
2. **Ask a question** about the file.
|
||||
3. The plugin will automatically process the file and provide context to your selected model.
|
||||
51
docs/plugins/filters/web-gemini-multimodel.zh.md
Normal file
51
docs/plugins/filters/web-gemini-multimodel.zh.md
Normal file
@@ -0,0 +1,51 @@
|
||||
# Web Gemini 多模态过滤器
|
||||
|
||||
<span class="category-badge filter">Filter</span>
|
||||
<span class="version-badge">v0.3.2</span>
|
||||
|
||||
一个强大的过滤器，为 OpenWebUI 中的任何模型提供多模态能力：PDF、Office、图片、音频、视频等。
|
||||
|
||||
---
|
||||
|
||||
## 概述
|
||||
|
||||
此插件利用 Gemini 作为分析器，为任何模型提供多模态处理能力。它支持 Gemini 模型的直接文件处理，以及其他模型（如 DeepSeek, Llama）的“分析器模式”，即由 Gemini 分析文件并将结果注入上下文。
|
||||
|
||||
## 功能特性
|
||||
|
||||
- :material-file-document-multiple: **多模态支持**: 处理 PDF, Word, Excel, PowerPoint, EPUB, MP3, MP4 和图片。
|
||||
- :material-router-network: **智能路由**:
|
||||
- **直连模式 (Direct Mode)**: 对于 Gemini 模型，文件直接传递（原生多模态）。
|
||||
- **分析器模式 (Analyzer Mode)**: 对于非 Gemini 模型，文件由 Gemini 分析，结果注入为上下文。
|
||||
- :material-history: **持久上下文**: 利用 OpenWebUI 的 Chat ID 跨多轮对话维护会话历史。
|
||||
- :material-database-check: **数据库去重**: 自动记录已分析文件的哈希值，防止重复上传和分析。
|
||||
- :material-subtitles: **字幕增强**: 针对视频/音频上传的专用模式，生成高质量 SRT 字幕。
|
||||
|
||||
---
|
||||
|
||||
## 安装
|
||||
|
||||
1. 下载插件文件: [`web_gemini_multimodel.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/filters/web_gemini_multimodel_filter)
|
||||
2. 上传到 OpenWebUI: **管理员面板** → **设置** → **函数**
|
||||
3. 配置 Gemini Adapter URL 和其他设置。
|
||||
4. 启用过滤器。
|
||||
|
||||
---
|
||||
|
||||
## 配置
|
||||
|
||||
| 选项 | 类型 | 默认值 | 描述 |
|
||||
|------|------|--------|------|
|
||||
| `gemini_adapter_url` | string | `http://...` | Gemini Adapter 服务的 URL |
|
||||
| `target_model_keyword` | string | `"webgemini"` | 识别 Gemini 模型的关键字 |
|
||||
| `mode` | string | `"auto"` | `auto` (自动), `direct` (直连), 或 `analyzer` (分析器) |
|
||||
| `analyzer_base_model_id` | string | `"gemini-3.0-pro"` | 用于文档分析的模型 |
|
||||
| `subtitle_keywords` | string | `"字幕,srt"` | 触发字幕流程的关键字 |
|
||||
|
||||
---
|
||||
|
||||
## 使用方法
|
||||
|
||||
1. 在聊天中 **上传文件** (PDF, 图片, 视频等)。
|
||||
2. 关于文件 **提问**。
|
||||
3. 插件会自动处理文件并为所选模型提供上下文。
|
||||
@@ -1,106 +0,0 @@
|
||||
# Gemini Manifold
|
||||
|
||||
<span class="category-badge pipe">Pipe</span>
|
||||
<span class="version-badge">v1.0.0</span>
|
||||
|
||||
Integration pipeline for Google's Gemini models with full streaming support.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
The Gemini Manifold pipe provides seamless integration with Google's Gemini AI models. It exposes Gemini models as selectable options in OpenWebUI, allowing you to use them just like any other model.
|
||||
|
||||
## Features
|
||||
|
||||
- :material-google: **Full Gemini Support**: Access all Gemini model variants
|
||||
- :material-stream: **Streaming**: Real-time response streaming
|
||||
- :material-image: **Multimodal**: Support for images and text
|
||||
- :material-shield: **Error Handling**: Robust error management
|
||||
- :material-tune: **Configurable**: Customize model parameters
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
1. Download the plugin file: [`gemini_manifold.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/pipes/gemini_mainfold)
|
||||
2. Upload to OpenWebUI: **Admin Panel** → **Settings** → **Functions**
|
||||
3. Configure your Gemini API key
|
||||
4. Select Gemini models from the model dropdown
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
|
||||
| Option | Type | Required | Description |
|
||||
|--------|------|----------|-------------|
|
||||
| `GEMINI_API_KEY` | string | Yes | Your Google AI Studio API key |
|
||||
| `DEFAULT_MODEL` | string | No | Default Gemini model to use |
|
||||
| `TEMPERATURE` | float | No | Response temperature (0-1) |
|
||||
| `MAX_TOKENS` | integer | No | Maximum response tokens |
|
||||
|
||||
---
|
||||
|
||||
## Available Models
|
||||
|
||||
When configured, the following models become available:
|
||||
|
||||
- `gemini-pro` - Text-only model
|
||||
- `gemini-pro-vision` - Multimodal model
|
||||
- `gemini-1.5-pro` - Latest Pro model
|
||||
- `gemini-1.5-flash` - Fast response model
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
1. After installation, go to any chat
|
||||
2. Open the model selector dropdown
|
||||
3. Look for models prefixed with your pipe name
|
||||
4. Select a Gemini model
|
||||
5. Start chatting!
|
||||
|
||||
---
|
||||
|
||||
## Getting an API Key
|
||||
|
||||
1. Visit [Google AI Studio](https://makersuite.google.com/app/apikey)
|
||||
2. Create a new API key
|
||||
3. Copy the key and paste it in the plugin configuration
|
||||
|
||||
!!! warning "API Key Security"
|
||||
Keep your API key secure. Never share it publicly or commit it to version control.
|
||||
|
||||
---
|
||||
|
||||
## Companion Filter
|
||||
|
||||
For enhanced functionality, consider installing the [Gemini Manifold Companion](../filters/gemini-manifold-companion.md) filter.
|
||||
|
||||
---
|
||||
|
||||
## Requirements
|
||||
|
||||
!!! note "Prerequisites"
|
||||
- OpenWebUI v0.3.0 or later
|
||||
- Valid Gemini API key
|
||||
- Internet access to Google AI APIs
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
??? question "Models not appearing?"
|
||||
Ensure your API key is correctly configured and the plugin is enabled.
|
||||
|
||||
??? question "API errors?"
|
||||
Check your API key validity and quota limits in Google AI Studio.
|
||||
|
||||
??? question "Slow responses?"
|
||||
Consider using `gemini-1.5-flash` for faster response times.
|
||||
|
||||
---
|
||||
|
||||
## Source Code
|
||||
|
||||
[:fontawesome-brands-github: View on GitHub](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/pipes/gemini_mainfold){ .md-button }
|
||||
@@ -1,106 +0,0 @@
|
||||
# Gemini Manifold
|
||||
|
||||
<span class="category-badge pipe">Pipe</span>
|
||||
<span class="version-badge">v1.0.0</span>
|
||||
|
||||
面向 Google Gemini 模型的集成流水线，支持完整流式返回。
|
||||
|
||||
---
|
||||
|
||||
## 概览
|
||||
|
||||
Gemini Manifold Pipe 提供与 Google Gemini AI 模型的无缝集成。它会将 Gemini 模型作为可选项暴露在 OpenWebUI 中，你可以像使用其他模型一样使用它们。
|
||||
|
||||
## 功能特性
|
||||
|
||||
- :material-google: **完整 Gemini 支持**：可使用所有 Gemini 模型变体
|
||||
- :material-stream: **流式输出**：实时流式响应
|
||||
- :material-image: **多模态**：支持图像与文本
|
||||
- :material-shield: **错误处理**：健壮的错误管理
|
||||
- :material-tune: **可配置**：可自定义模型参数
|
||||
|
||||
---
|
||||
|
||||
## 安装
|
||||
|
||||
1. 下载插件文件：[`gemini_manifold.py`](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/pipes/gemini_mainfold)
|
||||
2. 上传到 OpenWebUI：**Admin Panel** → **Settings** → **Functions**
|
||||
3. 配置你的 Gemini API Key
|
||||
4. 在模型下拉中选择 Gemini 模型
|
||||
|
||||
---
|
||||
|
||||
## 配置
|
||||
|
||||
| 选项 | 类型 | 是否必填 | 说明 |
|
||||
|--------|------|----------|-------------|
|
||||
| `GEMINI_API_KEY` | string | 是 | 你的 Google AI Studio API Key |
|
||||
| `DEFAULT_MODEL` | string | 否 | 默认使用的 Gemini 模型 |
|
||||
| `TEMPERATURE` | float | 否 | 输出温度（0-1） |
|
||||
| `MAX_TOKENS` | integer | 否 | 最大回复 token 数 |
|
||||
|
||||
---
|
||||
|
||||
## 可用模型
|
||||
|
||||
配置完成后，你可以选择以下模型：
|
||||
|
||||
- `gemini-pro` —— 纯文本模型
|
||||
- `gemini-pro-vision` —— 多模态模型
|
||||
- `gemini-1.5-pro` —— 最新 Pro 模型
|
||||
- `gemini-1.5-flash` —— 快速响应模型
|
||||
|
||||
---
|
||||
|
||||
## 使用方法
|
||||
|
||||
1. 安装后进入任意对话
|
||||
2. 打开模型选择下拉
|
||||
3. 查找以 Pipe 名称前缀的模型
|
||||
4. 选择 Gemini 模型
|
||||
5. 开始聊天！
|
||||
|
||||
---
|
||||
|
||||
## 获取 API Key
|
||||
|
||||
1. 访问 [Google AI Studio](https://makersuite.google.com/app/apikey)
|
||||
2. 创建新的 API Key
|
||||
3. 复制并粘贴到插件配置中
|
||||
|
||||
!!! warning "API Key 安全"
|
||||
请妥善保管你的 API Key，不要公开或提交到版本库。
|
||||
|
||||
---
|
||||
|
||||
## 伴随过滤器
|
||||
|
||||
如需增强功能，可安装 [Gemini Manifold Companion](../filters/gemini-manifold-companion.md) 过滤器。
|
||||
|
||||
---
|
||||
|
||||
## 运行要求
|
||||
|
||||
!!! note "前置条件"
|
||||
- OpenWebUI v0.3.0 及以上
|
||||
- 有效的 Gemini API Key
|
||||
- 可访问 Google AI API 的网络
|
||||
|
||||
---
|
||||
|
||||
## 常见问题
|
||||
|
||||
??? question "模型没有出现？"
|
||||
请确认 API Key 配置正确且插件已启用。
|
||||
|
||||
??? question "出现 API 错误？"
|
||||
检查 Google AI Studio 中的 Key 有效性和额度限制。
|
||||
|
||||
??? question "响应较慢？"
|
||||
可尝试使用 `gemini-1.5-flash` 获得更快速度。
|
||||
|
||||
---
|
||||
|
||||
## 源码
|
||||
|
||||
[:fontawesome-brands-github: 在 GitHub 查看](https://github.com/Fu-Jie/awesome-openwebui/tree/main/plugins/pipes/gemini_mainfold){ .md-button }
|
||||
@@ -15,19 +15,7 @@ Pipes allow you to:
|
||||
|
||||
## Available Pipe Plugins
|
||||
|
||||
<div class="grid cards" markdown>
|
||||
|
||||
- :material-google:{ .lg .middle } **Gemini Manifold**
|
||||
|
||||
---
|
||||
|
||||
Integration pipeline for Google's Gemini models with full streaming support.
|
||||
|
||||
**Version:** 1.0.0
|
||||
|
||||
[:octicons-arrow-right-24: Documentation](gemini-manifold.md)
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,54 +0,0 @@
|
||||
# Example Pipe Plugin
|
||||
|
||||
**Author:** OpenWebUI Community | **Version:** 1.26.0 | **License:** MIT
|
||||
|
||||
This is a template/example for creating Pipe plugins in OpenWebUI.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Pipes are plugins that process and enhance LLM responses after they are generated and before they are displayed to the user.
|
||||
|
||||
## Core Features
|
||||
|
||||
- ✅ **Response Processing**: Modify or enhance LLM output
|
||||
- ✅ **Format Conversion**: Convert responses to different formats
|
||||
- ✅ **Content Filtering**: Filter or sanitize content
|
||||
- ✅ **Integration**: Connect with external services
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
1. Download the `.py` file from this directory
|
||||
2. Open OpenWebUI Admin Settings → Plugins
|
||||
3. Select "Pipes" type
|
||||
4. Upload the file
|
||||
5. Refresh the page
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
|
||||
Configure the pipe parameters in your chat settings as needed.
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
Once enabled, this pipe will automatically process all LLM responses.
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
- Check the logs for any errors during pipe execution
|
||||
- Ensure the pipe is properly configured
|
||||
- Verify the pipe is enabled in chat settings
|
||||
|
||||
---
|
||||
|
||||
## Contributing
|
||||
|
||||
Feel free to create your own pipe plugins! Follow the structure and documentation guidelines in this template.
|
||||
@@ -1,54 +0,0 @@
|
||||
# 示例管道插件
|
||||
|
||||
**作者:** OpenWebUI 社区 | **版本:** 1.0.0 | **许可证:** MIT
|
||||
|
||||
这是在 OpenWebUI 中创建管道插件的模板/示例。
|
||||
|
||||
---
|
||||
|
||||
## 概述
|
||||
|
||||
管道是在 LLM 生成响应后、显示给用户前对响应进行处理和增强的插件。
|
||||
|
||||
## 核心特性
|
||||
|
||||
- ✅ **响应处理**: 修改或增强 LLM 输出
|
||||
- ✅ **格式转换**: 将响应转换为不同格式
|
||||
- ✅ **内容过滤**: 过滤或清理内容
|
||||
- ✅ **集成**: 与外部服务连接
|
||||
|
||||
---
|
||||
|
||||
## 安装
|
||||
|
||||
1. 从此目录下载 `.py` 文件
|
||||
2. 打开 OpenWebUI 管理员设置 → 插件（Plugins）
|
||||
3. 选择"Pipes"类型
|
||||
4. 上传文件
|
||||
5. 刷新页面
|
||||
|
||||
---
|
||||
|
||||
## 配置
|
||||
|
||||
根据需要在聊天设置中配置管道参数。
|
||||
|
||||
---
|
||||
|
||||
## 使用
|
||||
|
||||
启用后，该管道将自动处理所有 LLM 响应。
|
||||
|
||||
---
|
||||
|
||||
## 故障排除
|
||||
|
||||
- 查看日志了解管道执行过程中的任何错误
|
||||
- 确保管道配置正确
|
||||
- 验证管道在聊天设置中已启用
|
||||
|
||||
---
|
||||
|
||||
## 贡献
|
||||
|
||||
欢迎创建您自己的管道插件！请遵循此模板中的结构和文档指南。
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user