Skip to content

Commit 6d9bb6f

Browse files
committed
docs correction
1 parent 3c29253 commit 6d9bb6f

18 files changed

+177
-169
lines changed

README.md

+71-68
Original file line numberDiff line numberDiff line change
@@ -28,55 +28,62 @@ More patterns are coming soon...
2828
****************************************
2929

3030
## Table of Contents
31-
3231
* [Quick Start](#Quick-Start)
33-
* [How to build an agent application](#How-to-build-an-agent-application)
34-
* [Setup the visual agentic workflow platform](#Setup-the-visual-agentic-workflow-platform)
32+
|   [Quick Installation](#Quick-Installation)   |
33+
  [Run Example](#Run-the-first-example)   |
34+
* [How to build an intelligent agent application](#How-to-build-an-intelligent-agent-application)
35+
|   [Using engineering](#Using-engineering)   |
36+
  [Using platform](#Using-platform)   |
3537
* [Why use agentUniverse](#Why-use-agentUniverse)
36-
* [Sample Projects](#Sample-Projects)
37-
* [Documents](#Documents)
38-
* [Support](#Support)
38+
|   [Design Concept](#Design-Concept)   |
39+
  [Collaboration](#Multi-Agent-Collaboration)   |
40+
  [Citation](#Citation)   |
41+
  [Key Features](#Key-Features)   |
42+
* [Cases and Example Projects](#Cases-and-Example-Projects)
43+
|   [Use Cases](#Use-Cases)   |
44+
  [Example Projects](#Example-Projects)   |
45+
  [Product Cases](#Product-Cases)   |
46+
* [User Guide](#User-Guide)
47+
* [More](#More)
48+
|   Roadmap   |
49+
  [API Reference](#API-Reference)   |
50+
  [Support](#Support)   |
51+
   [Acknowledgements](#Acknowledgements)    |
3952

4053
****************************************
4154
## Quick Start
42-
43-
### Installation
55+
### Quick Installation
4456
Using pip:
4557
```shell
4658
pip install agentUniverse
4759
```
4860
### Run the first example
49-
Run your first example, and you can quickly experience the performance of the agents (or agent groups) built by agentUniverse through the tutorial.
61+
Run your first case, and you can quickly experience the performance of the agents (or groups) built by agentUniverse through the tutorial.
5062

51-
Please refer to the document for detail steps: [Run the first example](./docs/guidebook/en/1_Run_the_first_example.md)
63+
Please refer to the document for detailed steps: [Run the first example](./docs/guidebook/en/1_Run_the_first_example.md)
5264

5365
****************************************
5466

55-
## How to build an agent application
67+
## How to build an intelligent agent application
5668

57-
### Standard Project Scaffolding
58-
setup the standard project: [agentUniverse Standard Project](sample_standard_app)
59-
60-
### Create and use agents
69+
### Using engineering
70+
#### Create and use agents
6171
You can learn about the important components of agents through the [Introduction to Agents](./docs/guidebook/en/2_2_1_Agent.md). For detailed information on creating agents, refer to [Creating and Using Agents](./docs/guidebook/en/2_2_1_Agent_Create_And_Use.md). You can also deepen your understanding of the creation and usage of agents by exploring official examples, such as the [Python Code Generation and Execution Agent](./docs/guidebook/en/7_1_1_Python_Auto_Runner.md).
6272

63-
### Setting and use knowledgeBase
73+
#### Setting and use knowledgeBase
6474
In the construction of intelligent agent applications, knowledge base construction and recall are indispensable. The agentUniverse framework, based on RAG technology, provides an efficient standard operating procedure for knowledge base construction and the retrieval and recall process of RAG. You can learn about its usage through the [Knowledge Introduction](./docs/guidebook/en/2_2_4_Knowledge.md) and [Knowledge Definition and Usage](./docs/guidebook/en/2_2_4_Knowledge_Define_And_Use.md), and further master how to quickly build a knowledge base and create a recall-capable agent through [How to Build RAG Agents](./docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md).
6575

66-
### Create and use Tools
76+
#### Create and use Tools
6777
In the construction of agent applications, agents need to connect to a variety of tools. You should specify a range of tools that they can use. You can integrate various proprietary APIs and services as tool plugins through [Tool Creation and Usage](./docs/guidebook/en/2_2_3_Tool_Create_And_Use.md). The framework has already integrated LangChain and some third-party toolkits. For detailed usage, you can refer to [Integrating LangChain Tools](./docs/guidebook/en/2_2_3_Integrated_LangChain_Tools.md) and [Existing Integrated Tools](./docs/guidebook/en/2_2_3_Integrated_Tools.md).
6878

69-
### Effectiveness evaluation
79+
#### Effectiveness evaluation
7080
The effectiveness evaluation of agents can be conducted through expert assessments on one hand and by leveraging the evaluation capabilities of the agents on the other. agentUniverse has launched DataAgent (Minimum Viable Product version), which aims to empower your agents with self-evaluation and evolution capabilities using agent intelligence. You can also customize the evaluation criteria within it. For more details, see the documentation: [DataAgent - Autonomous Data Agents](./docs/guidebook/en/8_1_1_data_autonomous_agent.md).
7181

72-
### agentServe
82+
#### agentServe
7383
agentUniverse offers multiple standard web server capabilities, as well as standard HTTP and RPC protocols. You can further explore the documentation on [Service Registration and Usage](./docs/guidebook/en/2_4_1_Service_Registration_and_Usage.md) and the [Web Server](./docs/guidebook/en/2_4_1_Web_Server.md) sections.
7484

75-
****************************************
76-
77-
## Setup the visual agentic workflow platform
78-
79-
agentUniverse provides a visual canvas platform for agentic workflow . Please follow the steps below for a quick start:
85+
### Using platform
86+
agentUniverse provides a local product platform capability. Please follow the steps below for a quick start:
8087

8188
**Install via pip**
8289
```shell
@@ -95,7 +102,7 @@ This feature is jointly launched by [difizen](https://github.com/difizen/magent)
95102

96103
## Why use agentUniverse
97104

98-
### Concept
105+
### Design Concept
99106
![](docs/guidebook/_picture/agentuniverse_structure.png)
100107

101108
The core of agentUniverse provides all the key components needed to build a single intelligent agent, the collaboration mechanisms between multiple agents, and the injection of expert knowledge, enabling developers to easily create intelligent applications equipped with professional KnowHow.
@@ -107,6 +114,24 @@ The PEER model utilizes agents with four different responsibilities: Planning, E
107114

108115
The PEER model has achieved exciting results, and the latest research findings and experimental results can be found in the following literature.
109116

117+
### Citation
118+
The agentUniverse project is supported by the following research achievements.
119+
120+
BibTeX formatted
121+
```text
122+
@misc{wang2024peerexpertizingdomainspecifictasks,
123+
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
124+
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},
125+
year={2024},
126+
eprint={2407.06985},
127+
archivePrefix={arXiv},
128+
primaryClass={cs.AI},
129+
url={https://arxiv.org/abs/2407.06985},
130+
}
131+
```
132+
Overview: This document provides a detailed introduction to the mechanisms and principles of the PEER multi-agent framework. In the experimental section, 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 a superior rate of 83% over BabyAGI using the GPT-3.5 Turbo (16k) model, and 81% using the GPT-4 model. For more details, please refer to the document.
133+
🔗https://arxiv.org/pdf/2407.06985
134+
110135
### Key Features
111136
Based on the above introduction, we summarize that agentUniverse includes the following main features:
112137

@@ -117,11 +142,10 @@ Rich and Effective Multi-Agent Collaboration Models: It offers collaborative mod
117142
Easy Integration of Domain Expertise: It offers capabilities for domain prompts, knowledge construction, and management, supporting the orchestration and injection of domain-level SOPs, aligning agents with expert-level domain knowledge.
118143

119144
💡 For more features, see the [key features of agentUniverse](./docs/guidebook/en/1_Core_Features.md) section.
120-
121145
****************************************
122146

123-
## Sample Projects
124-
147+
## Cases and Example Projects
148+
### Use Cases
125149
🚩 [Legal Consultation Agent v2](./docs/guidebook/en/7_1_1_Legal_Consultation_Case.md)
126150

127151
🚩 [Python Code Generation and Execution Agent](./docs/guidebook/en/7_1_1_Python_Auto_Runner.md)
@@ -132,68 +156,47 @@ Easy Integration of Domain Expertise: It offers capabilities for domain prompts,
132156

133157
🚩 [Andrew Ng's Reflexive Workflow Translation Agent Replication](./docs/guidebook/en/7_1_1_Translation_Case.md)
134158

135-
****************************************
136-
137-
## Commercial Product base on agentUniverse
159+
### Example Projects
160+
⌨️[agentUniverse Example Projects](sample_standard_app)
138161

162+
### Product Cases
139163
🔗 [_Zhi Xiao Zhu_-AI Assistant for Financial Professionals](https://zhu.alipay.com/?from=au)
140164

165+
****************************************
166+
141167
**_Zhi Xiao Zhu_ AI Assistant: Facilitate the implementation of large models in rigorous industries to enhance the efficiency of investment research experts**
142168

143169
_Zhi Xiao Zhu_ AI Assistant is an efficient solution for the practical application of large models in rigorous industries. It is based on the Finix model, which focuses on precise applications, and the agentUniverse intelligent agent framework, which excels in professional customization. This solution targets a range of professional AI business assistants related to investment research, ESG (Environmental, Social, and Governance), finance, earnings reports, and other specialized areas. It has been extensively validated in large-scale scenarios at Ant Group, enhancing expert efficiency.
144170

171+
145172
https://private-user-images.githubusercontent.com/39180831/355437700-192f712d-1b03-46a6-8422-1ca10aa94331.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjI5NDk4NTAsIm5iZiI6MTcyMjk0OTU1MCwicGF0aCI6Ii8zOTE4MDgzMS8zNTU0Mzc3MDAtMTkyZjcxMmQtMWIwMy00NmE2LTg0MjItMWNhMTBhYTk0MzMxLm1wND9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA4MDYlMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwODA2VDEzMDU1MFomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPTU4NWMzNzVjOGZjZDNjMDMzMTE4YjQzOTk0ZWQwZGZkNWNmNWQxNWMzYWIzMTk4MzY1MjA5NWRhMjU2NGNiNzUmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.q1vdSg_Ghxr-DHLXfmQ_fVVRVSFn7H8VMHMi-_2QrjA
146173

147174
****************************************
148175

149-
## Documents
150-
151-
### User Guide
176+
## User Guide
152177
💡 For more detailed information, please read the [User Guide](./docs/guidebook/en/0_index.md).
153178

154-
### API Reference
155-
💡 Please read the [API Reference](https://agentuniverse.readthedocs.io/en/latest/).
156-
157179
****************************************
158180

159-
## Support
181+
## More
182+
### API Reference
183+
💡 Please read the [API Reference](https://agentuniverse.readthedocs.io/en/latest/).
160184

161-
### Submit Questions via GitHub Issues
185+
### Support
186+
#### Submit Questions via GitHub Issues
162187
😊 We recommend submitting your queries using [GitHub Issues](https://github.com/alipay/agentUniverse/issues), we typically respond within 2 days.
163188

164-
### Contact Us via Discord
189+
#### Contact Us via Discord
165190
😊 Join our [Discord Channel](https://discord.gg/DHFcdkWAhn) to interact with us.
166191

167-
### Contact Us via Administrator Email
192+
#### Contact Us via Administrator Email
168193
😊 Email:
169-
170-
171-
194+
195+
196+
172197

173-
### twitter
198+
#### twitter
174199
ID: [@agentuniverse_](https://x.com/agentuniverse_)
175200

176-
### Acknowledgements
177-
201+
## Acknowledgements
178202
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. 🙏🙏🙏
179-
180-
****************************************
181-
182-
## Citation
183-
184-
The agentUniverse project is supported by the following research achievements.
185-
186-
BibTeX formatted
187-
```text
188-
@misc{wang2024peerexpertizingdomainspecifictasks,
189-
title={PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods},
190-
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},
191-
year={2024},
192-
eprint={2407.06985},
193-
archivePrefix={arXiv},
194-
primaryClass={cs.AI},
195-
url={https://arxiv.org/abs/2407.06985},
196-
}
197-
```
198-
Overview: This document provides a detailed introduction to the mechanisms and principles of the PEER multi-agent framework. In the experimental section, 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 a superior rate of 83% over BabyAGI using the GPT-3.5 Turbo (16k) model, and 81% using the GPT-4 model. For more details, please refer to the document.
199-
🔗https://arxiv.org/pdf/2407.06985

docs/guidebook/en/1_Run_the_first_example.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -153,8 +153,8 @@ You need to apply for the SERPER_API_KEY on the official Serper website and conf
153153
After applying, find the corresponding key in the custom_key.toml configuration file and uncomment it as shown.
154154

155155
```toml
156-
#Google search
157-
SERPER_API_KEY='xxxxxx'
156+
##search api
157+
SEARCHAPI_API_KEY='key_xxxxxx'
158158
```
159159

160160
Follow the steps in Section 2 to execute other cases. You can now reference and run all official cases.

docs/guidebook/zh/2_2_1_智能体创建与使用.md

+7-7
Original file line numberDiff line numberDiff line change
@@ -20,11 +20,11 @@
2020
* `introduction`: 智能体角色介绍
2121
* `target`: 智能体目标
2222
* `instruction`: 智能体指令
23-
* `llm_model`: 智能体使用的LLM
24-
* `name`: LLM 名称
25-
* `model_name`: LLM 模型名
23+
* `llm_model`: 智能体使用的LLM
24+
* `name`: LLM 名称
25+
* `model_name`: LLM 模型名
2626

27-
您可以选择已有或接入任意的LLM,我们在本部分不展开说明,您可以关注[模型LLM章节](2_2_2_模型.md)
27+
其中`introduction`, `target`, `instruction`与模型prompt相关,可以通过`prompt_version`以额外的yaml进行配置。另外您可以选择已有或接入任意的LLM,我们在本部分不展开说明,您可以关注[模型LLM章节](2_2_2_模型.md)
2828

2929
### 设置智能体计划
3030
**`plan` - 智能体计划**
@@ -136,7 +136,7 @@ agent执行前的输入处理节点, agent的输入可以是自然语言或者js
136136

137137
该部分拥有两个输入参数,如下:
138138
* `input_object`: 智能体输入原始数据
139-
* 可通过 `input_object.get_data('input_key')` 方法获取input_object中的对于数据
139+
* 可通过 `input_object.get_data('input_key')` 方法获取input_object中的对应数据
140140

141141
例如: 用户对智能体输入`question=xxx`, 我们可以通过`input_object.get_data('question')`获取用户当前的提问。
142142

@@ -266,7 +266,7 @@ def parse_input(self, input_object: InputObject, agent_input: dict) -> dict:
266266
agent_input['input'] = input_object.get_data('input')
267267
return agent_input
268268
```
269-
在其对应agent设置`sample_standard_app.app.core.agent.rag_agent_case.demo_rag_agent.yaml`中的`instruction`部分我们可以看到如下配置:
269+
在其对应agent设置`sample_standard_app.app.core.prompt.demo_rag_agent_cn.yaml`中的`instruction`部分我们可以看到如下配置:
270270
```text
271271
instruction: |
272272
你需要遵守的规则是:
@@ -357,7 +357,7 @@ metadata:
357357
在agentUniverse中所有agent实体都由全局agent管理器进行管理,在任何框架执行过程中如果您需要使用智能体可以通过agent管理器。同时通过框架的服务化能力,您可以将agent快速服务化并通过标准的http或rpc协议对其进行网络调用。
358358
359359
## 方案一: 使用agent管理器
360-
通过agent管理器中的`get_instance_obj('agent_name_xxx')` 方法可以获取对应名称的agent实例,同时通过agent自身的`run(input='xxx')`方法使用agent,下面的test类中的`test_rag_agent(self)`方法就是使用该方式对于agent进行了调试。
360+
通过agent管理器中的`get_instance_obj('agent_name_xxx')` 方法可以获取对应名称的agent实例,同时通过agent自身的`run(input='xxx')`方法使用agent,下面的test类中的[`test_rag_agent(self)`](../../../sample_standard_app/app/test/test_rag_agent.py)方法就是使用该方式对于agent进行了调试。
361361
```python
362362
import unittest
363363

docs/guidebook/zh/2_2_3_集成LangChain工具.md

+15-13
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,9 @@
11
# 集成LangChain工具
22

33
根据langchain中工具对象的初始化的难易程度,可以将其分为两类:
4-
第一类,简单初始化,只需要简单的参数配置即可完成初始化。
5-
第二类,复杂初始化,内部包含一些复杂的对象需要进行初始化。
4+
- 第一类,简单初始化,只需要简单的参数配置即可完成初始化。
5+
- 第二类,复杂初始化,内部包含一些复杂的对象需要进行初始化。
6+
67
对于一类工具,你可以在aU中直接使用配置文件进行初始化,如DuDuckGo搜索工具的初始化。
78
对于第二类工具,我们实现了一个LangChainTool基础类,你只需要实现该类的init_langchain_tool方法,初始化对应的langchain工具对象即可,参考维基百科的初始化方法。
89

@@ -24,18 +25,19 @@ metadata:
2425
class: 'LangChainTool'
2526
```
2627
参数说明:
27-
langchain: 你打算使用的langchain工具,需要配置module和class_name
28-
langchain.module: langchain的模块名,例如langchain_community.tools
29-
langchain.class_name: langchain的类名,例如HumanInputRun
30-
langchain.init_params langchain的初始化参数,例如:
31-
```yaml
32-
langchain:
33-
module: langchain_community.tools
34-
class_name: HumanInputRun
35-
init_params:
36-
prompt: '请输入你的问题'
37-
```
28+
- `langchain`: 你打算使用的langchain工具,需要配置module和class_name
29+
- `langchain.module`: langchain的模块名,例如langchain_community.tools
30+
- `langchain.class_name`: langchain的类名,例如HumanInputRun
31+
- `langchain.init_params`: langchain的初始化参数,例如:
32+
```yaml
33+
langchain:
34+
module: langchain_community.tools
35+
class_name: HumanInputRun
36+
init_params:
37+
prompt: '请输入你的问题'
38+
```
3839
如果需要使用你完全重写了init_langchain_tool方法,那么你不需要配置该部分
40+
3941
该工具可以直接使用,无需任何keys
4042

4143
## 1. 集成LangChain中的DuckDuckGo工具

docs/guidebook/zh/2_2_3_集成的工具.md

+5-4
Original file line numberDiff line numberDiff line change
@@ -181,8 +181,9 @@ metadata:
181181
class: 'RequestTool'
182182
```
183183
参数说明:
184-
method 请求的方式GET/POST/PUT等
185-
headers 发送请求需要使用的 http的header,
186-
json_parse 输入参数是否需要是要HTTP解析,POST请求时需要设置为True,GET请求需要设置为False
187-
response_content_type http请求结果的解析方式,设置为json时,会返回json结果,设置为text时会返回text结果
184+
- `method`: 请求的方式GET/POST/PUT等
185+
- `headers`: 发送请求需要使用的 http的header
186+
- `json_parse`: 输入参数是否需要是要HTTP解析,POST请求时需要设置为True,GET请求需要设置为False
187+
- `response_content_type`: http请求结果的解析方式,设置为json时,会返回json结果,设置为text时会返回text结果
188+
188189
该工具可以直接使用,无需任何keys

0 commit comments

Comments
 (0)