panda/bettafish-company
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update readme.

Browse Source
This commit is contained in:
戒酒的李白
2025-09-02 00:39:32 +08:00
parent b5e6b3ac11
commit 1812c47a96
2 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README-EN.md
+12 -9
View File
@@ -56,15 +56,18 @@ Say goodbye to traditional data dashboards. In "WeiYu", everything starts with a
<img src="static/image/framework.png" alt="banner" width="800">
</div>
A complete analysis workflow:
1. User Query → Flask main application receives the query
2. Parallel Launch → Three Agents start working simultaneously
3. Preliminary Analysis → Each Agent uses dedicated tools for overview search
4. Strategy Formulation → Develop segmented research strategies based on preliminary results
5. In-depth Research → Multi-round search and reflection mechanisms calling respective tools
6. Forum Collaboration → ForumEngine accepts key findings from each Agent and facilitates Agent communication
7. Result Integration → Report Agent collects all analysis results and forum content
8. Report Generation → Dynamically select templates and styles, generate final reports through multiple rounds
### Complete Analysis Workflow
| Step | Phase Name | Main Operations | Participating Components |
|------|------------|-----------------|-------------------------|
| 1 | User Query | Flask main application receives the query | Flask Main Application |
| 2 | Parallel Launch | Three Agents start working simultaneously | Query Agent, Media Agent, Insight Agent |
| 3 | Preliminary Analysis | Each Agent uses dedicated tools for overview search | Each Agent + Dedicated Toolsets |
| 4 | Strategy Formulation | Develop segmented research strategies based on preliminary results | Internal Decision Modules of Each Agent |
| 5 | In-depth Research | Multi-round search and reflection mechanisms calling respective tools | Each Agent + Reflection Mechanisms |
| 6 | Forum Collaboration | ForumEngine accepts key findings from each Agent and facilitates Agent communication | ForumEngine + All Agents |
| 7 | Result Integration | Report Agent collects all analysis results and forum content | Report Agent |
| 8 | Report Generation | Dynamically select templates and styles, generate final reports through multiple rounds | Report Agent + Template Engine |
### Project Code Structure Tree
README.md
+12 -9
View File
@@ -56,15 +56,18 @@
<img src="static/image/framework.png" alt="banner" width="800">
</div>
一次完整的分析流程：
1. 用户提问 → Flask主应用接收查询
2. 并行启动 → 三个Agent同时开始工作
3. 初步分析 → 各Agent使用专属工具进行概览搜索
4. 策略制定 → 基于初步结果制定分块研究策略
5. 深度研究 → 多轮搜索与反思机制调用各自工具
6. 论坛协作 → ForumEngine接受各Agent关键发现并促进Agent交流
7. 结果整合 → Report Agent收集所有分析结果和论坛内容
8. 报告生成 → 动态选择模板和样式，多轮生成最终报告
### 完整分析流程
| 步骤 | 阶段名称 | 主要操作 | 参与组件 |
|------|----------|----------|----------|
| 1 | 用户提问 | Flask主应用接收查询 | Flask主应用 |
| 2 | 并行启动 | 三个Agent同时开始工作 | Query Agent、Media Agent、Insight Agent |
| 3 | 初步分析 | 各Agent使用专属工具进行概览搜索 | 各Agent + 专属工具集 |
| 4 | 策略制定 | 基于初步结果制定分块研究策略 | 各Agent内部决策模块 |
| 5 | 深度研究 | 多轮搜索与反思机制调用各自工具 | 各Agent + 反思机制 |
| 6 | 论坛协作 | ForumEngine接受各Agent关键发现并促进Agent交流 | ForumEngine + 所有Agent |
| 7 | 结果整合 | Report Agent收集所有分析结果和论坛内容 | Report Agent |
| 8 | 报告生成 | 动态选择模板和样式，多轮生成最终报告 | Report Agent + 模板引擎 |
### 项目代码结构树