wangtinghu/agentUniverse
1
0
Fork 0
mirror of https://github.com/agentuniverse-ai/agentUniverse.git synced 2026-02-09 01:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: update README & modify index of guidebook

Browse Source
This commit is contained in:
Jerry Z H
2024-07-11 19:48:35 +08:00
parent 772909a171
commit 5a05949c16
9 changed files with 136 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@@ -35,6 +35,7 @@ More patterns are coming soon...
* [User Guide](#User-Guide)
* [API Reference](#API-Reference)
* [Support](#Support)
* [Citation](#Citation)
* [Acknowledgements](#Acknowledgements)
****************************************
## Quick Start
@@ -64,6 +65,11 @@ For more details, please read the [Quick Start](./docs/guidebook/en/1_3_Quick_St
[Financial Event Analysis Based on PEER Multi-Agent Mode](./docs/guidebook/en/6_4_1_Financial_Event_Analysis_Case.md)
[Andrew Ng's Reflexive Workflow Translation Agent Replication](./docs/guidebook/en/7_1_1_Translation_Case.md)
#### 🚩 DataAgent - Data Autonomous Agent
agentUniverse has launched DataAgent (Minimum Viable Product Version). DataAgent aims to empower your agent with the capability of self-assessment and evolution through the use of intelligent agent abilities. For more details, please refer to the documentation. [DataAgent - Data Autonomous Agent](./docs/guidebook/en/8_1_1_data_autonomous_agent.md)
### 🌟 Example Projects
[agentUniverse Example Projects](sample_standard_app)
@@ -98,11 +104,26 @@ For more details, please read the [Quick Start](./docs/guidebook/en/1_3_Quick_St
#### Contact Us via Administrator Email
😊 Email: [jerry.zzw@antgroup.com](mailto:jerry.zzw@antgroup.com)
#### WeChat Official Account
#### twitter
ID: [@agentuniverse_](https://x.com/agentuniverse_)
😊 Official Account ID: **agentUniverse智多星**
### Citation
The agentUniverse project is supported by the following research achievements.
You can get more related articles and information in our WeChat Official Account.
BibTeX formatted
```text
@misc{wang2024peerexpertizingdomainspecifictasks,
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
author={Yiying Wang and Xiaojing Li and Binzhu Wang and Yueyang Zhou and Han Ji and Hong Chen and Jinshi Zhang and Fei Yu and Zewei Zhao and Song Jin and Renji Gong and Wanqing Xu},
year={2024},
eprint={2407.06985},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2407.06985},
}
```
Overview: In the experimental section of this study, scores were assigned across seven dimensions: completeness, relevance, conciseness, factualness, logicality, structure, and comprehensiveness (each dimension has a maximum score of 5 points). The PEER model scored higher on average in each evaluation dimension compared to BabyAGI, and demonstrated significant advantages in the dimensions of completeness, relevance, logicality, structure, and comprehensiveness. Additionally, the PEER model achieved an 83% superior rate over BabyAGI using the GPT-3.5 turbo (16k) model, and an 81% superior rate using the GPT-4o model. For more details, please refer to the literature.
https://arxiv.org/pdf/2407.06985
## Acknowledgements
This project is partially built on excellent open-source projects such as langchain, pydantic, gunicorn, flask, SQLAlchemy, chromadb, etc. (The detailed dependency list can be found in pyproject.toml). We would like to extend special thanks to the related projects and contributors. 🙏🙏🙏

30
README_zh.md
View File

@@ -34,6 +34,7 @@
* [用户指南](#用户指南)
* [API参考](#API参考)
* [支持](#支持)
* [文献](#文献)
* [鸣谢](#鸣谢)
****************************************
## 快速开始
@@ -61,6 +62,12 @@ pip install agentUniverse
[基于PEER协同模式的金融事件分析](./docs/guidebook/zh/6_4_1_金融事件分析案例.md)
[吴恩达反思工作流翻译智能体复刻](./docs/guidebook/zh/7_1_1_翻译案例.md)
#### 🚩 DataAgent - 数据自治智能体
agentUniverse推出了DataAgent（Minimum Viable Product版本）, DataAgent旨在使用智能体能力让您的Agent拥有自我评价与演进的能力。详情见文档: [DataAgent - 数据自治智能体](./docs/guidebook/zh/8_1_1_数据自治智能体.md)
### 🌟 示例项目
[agentUniverse 示例项目](sample_standard_app)
@@ -105,7 +112,30 @@ pip install agentUniverse
😊 公众号ID：**agentUniverse智多星**
![](./docs/guidebook/_picture/wechat_official.png)
更多相关的文章与资讯你可以在微信公众号中获取。
#### twitter
ID: [@agentuniverse_](https://x.com/agentuniverse_)
### 文献
agentUniverse项目基于以下的研究成果支撑。
BibTeX formatted
```text
@misc{wang2024peerexpertizingdomainspecifictasks,
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
author={Yiying Wang and Xiaojing Li and Binzhu Wang and Yueyang Zhou and Han Ji and Hong Chen and Jinshi Zhang and Fei Yu and Zewei Zhao and Song Jin and Renji Gong and Wanqing Xu},
year={2024},
eprint={2407.06985},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2407.06985},
}
```
文献简介：该文献在研究实验部分分别从**完整性、相关性、紧凑性、事实性、逻辑性、结构性和全面性七个维度进行打分（各纬度满分为5分）**，**PEER模式在每个测评维度的平均分数均高于BabyAGI**，且在**完整性、相关性、逻辑性、结构性和全面性五个纬度有显著优势**；同时PEER模式在 GPT-3.5 turbo (16k) 模型下相较于 BabyAGI 的择优胜率达到 83%，在 GPT-4o 模型下择优胜率达到 81%，更多详情请阅读文献。
https://arxiv.org/pdf/2407.06985
## 鸣谢
本项目部分基于langchain、pydantic、gunicorn、flask、SQLAlchemy、chromadb等（详细依赖列表可见pyproject.toml）优秀开源项目实现，在此特别感谢相关项目与关联方。 🙏🙏🙏

BIN
docs/guidebook/_picture/wechat_official.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 32 KiB

7
docs/guidebook/en/0_index.md
View File

@@ -43,6 +43,8 @@
* 2.4.4.1 [Logging Component](2_6_Logging_Utils.md)
* 2.4.5 Data Collection
* 2.4.5.1 [Monitor Module](2_5_1_Monitor_Module.md)
* 2.4.6 Data Autonomous
* 2.4.6.1 [Data Autonomous Agent](8_1_1_data_autonomous_agent.md)
**3. Component Reference Manual**
* 3.1 Domain Components
@@ -89,9 +91,12 @@
* 6.3 [Discussion Group Based on Multi-Turn Multi-Agent Mode](6_2_1_Discussion_Group.md)
* 6.4 PEER Multi-Agent Cooperation Examples
* 6.4.1 [Financial Event Analysis Case](./6_4_1_Financial_Event_Analysis_Case.md)
* 6.5 [Andrew Ng's Reflexive Workflow Translation Agent Replication](./7_1_1_Translation_Case.md)
**7. Series of Articles**
**8. Frequently Asked Questions (FAQ)**
**[9. Contact Us](6_1_Contact_Us.md)**
**[9.Citation](9_1_Citation.md)**
**[10. Contact Us](6_1_Contact_Us.md)**

21
docs/guidebook/en/6_1_Contact_Us.md
View File

@@ -1,9 +1,12 @@
# Contact Us
* github: https://github.com/alipay/agentUniverse
* gitee: https://gitee.com/agentUniverse/agentUniverse
* gitcode: https://gitcode.com/agentUniverse
* Stack Overflow: https://stackoverflowteams.com/c/agentuniverse/questions
* Discord: https://discord.gg/VfhEvJzQ
* WeChat Official Account: agentUniverse智多星
* DingTalk Group:
![](../_picture/dingtalk_util20250429.png)
### Support
#### Submit Questions via GitHub Issues
😊 We recommend submitting your queries using [GitHub Issues](https://github.com/alipay/agentUniverse/issues), we typically respond within 2 days.
#### Contact Us via Discord
😊 Join our [Discord Channel](https://discord.gg/DHFcdkWAhn) to interact with us.
#### Contact Us via Administrator Email
😊 Email: [jerry.zzw@antgroup.com](mailto:jerry.zzw@antgroup.com)
#### twitter
ID: [@agentuniverse_](https://x.com/agentuniverse_)

17
docs/guidebook/en/9_1_Citation.md Normal file
View File

@@ -0,0 +1,17 @@
### Citation
The agentUniverse project is supported by the following research achievements.
BibTeX formatted
```text
@misc{wang2024peerexpertizingdomainspecifictasks,
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
author={Yiying Wang and Xiaojing Li and Binzhu Wang and Yueyang Zhou and Han Ji and Hong Chen and Jinshi Zhang and Fei Yu and Zewei Zhao and Song Jin and Renji Gong and Wanqing Xu},
year={2024},
eprint={2407.06985},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2407.06985},
}
```
Overview: In the experimental section of this study, scores were assigned across seven dimensions: completeness, relevance, conciseness, factualness, logicality, structure, and comprehensiveness (each dimension has a maximum score of 5 points). The PEER model scored higher on average in each evaluation dimension compared to BabyAGI, and demonstrated significant advantages in the dimensions of completeness, relevance, logicality, structure, and comprehensiveness. Additionally, the PEER model achieved an 83% superior rate over BabyAGI using the GPT-3.5 turbo (16k) model, and an 81% superior rate using the GPT-4o model. For more details, please refer to the literature.
https://arxiv.org/pdf/2407.06985

7
docs/guidebook/zh/0_目录.md
View File

@@ -47,6 +47,8 @@
* 2.4.4.1 [日志组件](2_4_4_日志组件.md)
* 2.4.5 数据采集
* 2.4.5.1 [monitor模块](2_5_1_监控模块.md)
* 2.4.6 数据自治
* 2.4.6.1 [数据自治智能体](8_1_1_数据自治智能体.md)
**3.组件参考手册**
* 3.1 领域组件
@@ -93,9 +95,12 @@
* 6.3 [基于多轮多Agent的讨论小组](6_2_1_讨论组.md)
* 6.4 PEER多Agent协作案例
* 6.4.1 [金融事件分析案例](./6_4_1_金融事件分析案例.md)
* 6.5 [吴恩达反思工作流翻译智能体复刻](./7_1_1_翻译案例.md)
**7.系列文章**
**8.常见问题FAQ**
**[9.联系我们](6_1_联系我们.md)**
**[9.研究文献](9_1_研究文献.md)**
**[10.联系我们](6_1_联系我们.md)**

33
docs/guidebook/zh/6_1_联系我们.md
View File

@@ -1,9 +1,24 @@
# 联系我们
* github: https://github.com/alipay/agentUniverse
* gitee: https://gitee.com/agentUniverse/agentUniverse
* gitcode: https://gitcode.com/agentUniverse
* Stack Overflow: https://stackoverflowteams.com/c/agentuniverse/questions
* Discord: https://discord.gg/VfhEvJzQ
* 微信公众号: agentUniverse智多星
* 钉钉交流群:
![](../_picture/dingtalk_util20250429.png)
### 支持
#### 通过github issue提交疑问
😊 我们建议您使用[github issue](https://github.com/alipay/agentUniverse/issues) 提交您的疑问, 我们通常会在2日内回复。
#### 通过Discord联系我们
😊 加入我们的 [Discord频道](https://discord.gg/DHFcdkWAhn) 与我们进行交流。
#### 通过钉钉群联系我们
😊 加入我们的钉钉答疑群与我们联系。
![](../_picture/dingtalk_util20250429.png)
#### 通过管理员Email联系我们
😊 Email: [jerry.zzw@antgroup.com](mailto:jerry.zzw@antgroup.com)
#### 微信公众号
😊 公众号ID：**agentUniverse智多星**
![](../_picture/wechat_official.png)
更多相关的文章与资讯你可以在微信公众号中获取。
#### twitter
ID: [@agentuniverse_](https://x.com/agentuniverse_)

17
docs/guidebook/zh/9_1_研究文献.md Normal file
View File

@@ -0,0 +1,17 @@
### 文献
agentUniverse项目基于以下的研究成果支撑。
BibTeX formatted
```text
@misc{wang2024peerexpertizingdomainspecifictasks,
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
author={Yiying Wang and Xiaojing Li and Binzhu Wang and Yueyang Zhou and Han Ji and Hong Chen and Jinshi Zhang and Fei Yu and Zewei Zhao and Song Jin and Renji Gong and Wanqing Xu},
year={2024},
eprint={2407.06985},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2407.06985},
}
```
文献简介：该文献在研究实验部分分别从**完整性、相关性、紧凑性、事实性、逻辑性、结构性和全面性七个维度进行打分（各纬度满分为5分）**，**PEER模式在每个测评维度的平均分数均高于BabyAGI**，且在**完整性、相关性、逻辑性、结构性和全面性五个纬度有显著优势**；同时PEER模式在 GPT-3.5 turbo (16k) 模型下相较于 BabyAGI 的择优胜率达到 83%，在 GPT-4o 模型下择优胜率达到 81%，更多详情请阅读文献。
https://arxiv.org/pdf/2407.06985