Add Flash Card plugin with HTML generation and key point extraction

- Introduced a new Flash Card plugin that generates visually appealing flashcards from text input. - Implemented functionality to extract key points and categories for efficient learning. - Added a new Python file for the plugin logic and a corresponding image asset. - Removed outdated README files for the previous knowledge card plugin.
2025-12-30 11:18:36 +08:00
parent fb4af28539
commit 6a4a578394
8 changed files with 91 additions and 61 deletions
--- a/plugins/actions/flash-card/README.md
+++ b/plugins/actions/flash-card/README.md
@@ -0,0 +1,41 @@
+# Flash Card
+
+Generate polished learning flashcards from any text—title, summary, key points, tags, and category—ready for review and sharing.
+
+![Flash Card Example](flash_card.png)
+
+## Highlights
+
+- **One-click generation**: Drop in text, get a structured card.
+- **Concise extraction**: 3–5 key points and 2–4 tags automatically surfaced.
+- **Multi-language**: Choose target language (default English).
+- **Progressive merge**: Multiple runs append cards into the same HTML container; enable clearing to reset.
+- **Status updates**: Live notifications for generating/done/error.
+
+## Parameters
+
+| Param               | Description                                                  | Default |
+| ------------------- | ------------------------------------------------------------ | ------- |
+| MODEL_ID            | Model to use; empty falls back to current session model      | empty   |
+| MIN_TEXT_LENGTH     | Minimum text length; below this prompts for more text        | 50      |
+| LANGUAGE            | Output language (e.g., en, zh)                               | en      |
+| SHOW_STATUS         | Whether to show status updates                               | true    |
+| 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
+
+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.
--- a/plugins/actions/flash-card/README_CN.md
+++ b/plugins/actions/flash-card/README_CN.md
@@ -0,0 +1,41 @@
+# 闪记卡 (Flash Card)
+
+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。
+
+![闪记卡示例](flash_card_cn.png)
+
+## 功能亮点
+
+- **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。
+- **多语言支持**：可设定目标语言（默认中文）。
+- **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
+
+| 参数                | 说明                                  | 默认值 |
+| ------------------- | ------------------------------------- | ------ |
+| MODEL_ID            | 指定推理模型；为空则使用当前会话模型  | 空     |
+| MIN_TEXT_LENGTH     | 最小文本长度，不足时提示补充          | 50     |
+| LANGUAGE            | 输出语言（如 zh、en）                 | zh     |
+| SHOW_STATUS         | 是否显示状态更新                      | true   |
+| 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
+
+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。
--- a/plugins/actions/flash-card/flash_card.png
+++ b/plugins/actions/flash-card/flash_card.png
--- a/plugins/actions/knowledge-card/knowledge_card.py
+++ b/plugins/actions/knowledge-card/knowledge_card.py
@@ -80,10 +80,6 @@ class Action:
            default=50,
            description="Minimum text length required to generate a flashcard (characters).",
        )
-        MAX_TEXT_LENGTH: int = Field(
-            default=2000,
-            description="Recommended maximum text length. For longer texts, deep analysis tools are recommended.",
-        )
        LANGUAGE: str = Field(
            default="en",
            description="Target language for card content (e.g., 'en', 'zh').",
@@ -153,13 +149,6 @@ class Action:
            )
            return body

-        if text_length > self.valves.MAX_TEXT_LENGTH:
-            await self._emit_notification(
-                __event_emitter__,
-                f"Text quite long ({text_length} chars), consider using 'Deep Reading' for deep analysis.",
-                "info",
-            )
-
        # Notify user that we are generating the card
        await self._emit_notification(
            __event_emitter__, "⚡ Generating Flash Card...", "info"
--- a/plugins/actions/flash-card/flash_card_cn.png
+++ b/plugins/actions/flash-card/flash_card_cn.png
--- a/plugins/actions/knowledge-card/闪记卡.py
+++ b/plugins/actions/knowledge-card/闪记卡.py
@@ -12,6 +12,7 @@ from pydantic import BaseModel, Field
 from typing import Optional, Dict, Any, List
 import json
 import logging
+import re
 from open_webui.utils.chat import generate_chat_completion
 from open_webui.models.users import Users

@@ -78,10 +79,6 @@ class Action:
        MIN_TEXT_LENGTH: int = Field(
            default=50, description="生成闪记卡所需的最小文本长度（字符数）。"
        )
-        MAX_TEXT_LENGTH: int = Field(
-            default=2000,
-            description="建议的最大文本长度。超过此长度建议使用深度分析工具。",
-        )
        LANGUAGE: str = Field(
            default="zh", description="卡片内容的目标语言 (例如 'zh', 'en')。"
        )
@@ -149,13 +146,6 @@ class Action:
            )
            return body

-        if text_length > self.valves.MAX_TEXT_LENGTH:
-            await self._emit_notification(
-                __event_emitter__,
-                f"文本较长（{text_length}字符），建议使用'墨海拾贝'进行深度分析。",
-                "info",
-            )
-
        # Notify user that we are generating the card
        await self._emit_notification(__event_emitter__, "⚡ 正在生成闪记卡...", "info")
        await self._emit_status(__event_emitter__, "⚡ 闪记卡: 开始生成...", done=False)
@@ -177,13 +167,13 @@ class Action:
 你是一个闪记卡生成专家，专注于创建适合学习和记忆的知识卡片。你的任务是将文本提炼成简洁、易记的学习卡片。

 请提取以下字段，并以 JSON 格式返回：
-1. "title": 创建一个简短、精准的标题（6-12 字），突出核心概念
-2. "summary": 用一句话总结核心要义（20-40 字），要通俗易懂、便于记忆
-3. "key_points": 列出 3-5 个关键记忆点（每个 10-20 字）
-   - 每个要点应该是独立的知识点
-   - 使用简洁、口语化的表达
-   - 避免冗长的句子
-4. "tags": 列出 2-4 个分类标签（每个 2-5 字）
+1. "title": 创建一个简短、精准的标题（3-8 个词），突出核心概念
+2. "summary": 用一句话总结核心要义（10-25 个词），要通俗易懂、便于记忆
+3. "key_points": 列出 3-5 个关键记忆点（每个 5-15 个词）
+    - 每个要点应该是独立的知识点
+    - 使用简洁、口语化的表达
+    - 避免冗长的句子
+4. "tags": 列出 2-4 个分类标签（每个 1-3 个词）
 5. "category": 选择一个主分类（如：概念、技能、事实、方法等）

 目标语言: {self.valves.LANGUAGE}
@@ -680,7 +670,7 @@ class Action:
        tags_html = ""
        if "tags" in data and data["tags"]:
            for tag in data["tags"]:
-                tags_html += f'<span class="card-tag">#{tag}</span>'
+                tags_html += f'<div class="card-tag"><span class="card-tag-label">#</span>{tag}</div>'

        # Generate key points HTML
        points_html = ""
@@ -708,7 +698,6 @@ class Action:
                        </ul>
                    </div>
                    <div class="card-footer">
-                        <span class="card-tag-label">标签</span>
                        {tags_html}
                    </div>
                </div>
--- a/plugins/actions/knowledge-card/README.md
+++ b/plugins/actions/knowledge-card/README.md
@@ -1,15 +0,0 @@
-# Flash Card
-
-Quickly generates beautiful flashcards from text, extracting key points and categories for efficient learning.
-
-## Features
-
- **Instant Generation**: Turn any text into a structured flashcard.
- **Key Point Extraction**: Automatically identifies core concepts.
- **Visual Design**: Generates a visually appealing HTML card.
-
-## Usage
-
-1. Install the plugin.
-2. Send text to the chat.
-3. The plugin will analyze the text and generate a flashcard.
--- a/plugins/actions/knowledge-card/README_CN.md
+++ b/plugins/actions/knowledge-card/README_CN.md
@@ -1,15 +0,0 @@
-# 闪记卡 (Flash Card)
-
-快速将文本提炼为精美的学习记忆卡片，支持核心要点提取与分类，助力高效学习。
-
-## 功能特点
-
- **即时生成**：将任何文本转化为结构化的记忆卡片。
- **要点提取**：自动识别核心概念。
- **视觉设计**：生成视觉精美的 HTML 卡片。
-
-## 使用方法
-
-1. 安装插件。
-2. 发送文本到聊天框。
-3. 插件将分析文本并生成一张闪记卡。