mirror of
https://github.com/agentuniverse-ai/agentUniverse.git
synced 2026-02-09 01:59:19 +08:00
feat: Version 0.0.13 Release
This commit is contained in:
Jerry Z H
21
CHANGELOG.md
21
CHANGELOG.md
@@ -24,6 +24,27 @@ Note - Additional remarks regarding the version.
|
||||
***************************************************
|
||||
|
||||
# Version Update History
|
||||
# [0.0.13] - 2024-09-12
|
||||
### Added
|
||||
- RAG(Retrieval-Augmented Generation) Component Version Update
|
||||
- This version provides a standard operating procedure for knowledge base construction and the RAG retrieval recall stage. The component covers a series of RAG atomic capabilities, including data loading, data processing, index construction, knowledge storage, intent rewriting, and retrieval re-ranking, helping users to quickly build a general RAG intelligent agent solution in open-source scenarios.
|
||||
|
||||
- Intelligent Agent Product Platform Update
|
||||
- This version introduces new capabilities such as intelligent agent canvas orchestration, private knowledge base construction, and custom plugin support, enabling users to quickly build and orchestrate intelligent agents through a low-code, visual approach.
|
||||
|
||||
- Added GLM Default Model Component for Zhipu
|
||||
- Added SQLiteStore Storage Component
|
||||
- Added Flow Orchestration Execution Engine
|
||||
|
||||
### Note
|
||||
- Default path optimization for system_db_uri
|
||||
The default path is already compatible with the Windows platform, for more details, please refer to [issue142](https://github.com/alipay/agentUniverse/issues/142)
|
||||
- Support for configurable chain stop words in ReactAgent
|
||||
The ReactAgent YAML configuration now supports the stop_sequence keyword, allowing users to customize chain stop words. For more details, please refer to [issue127](https://github.com/alipay/agentUniverse/issues/127)
|
||||
- Added an introduction to RAG principles and a quick guide for building RAG, please pay attention to the corresponding parts in the README and user guide.
|
||||
- Added advanced guidance documents for the intelligent agent productization platform, please pay attention to the corresponding parts in the README and user guide.
|
||||
- Various code optimizations and documentation updates.
|
||||
|
||||
## [0.0.12] - 2024-08-14
|
||||
### Added
|
||||
- agentUniverse Product Version Offering
|
||||
|
||||
@@ -24,6 +24,27 @@ Note - 对于版本的额外说明。
|
||||
***************************************************
|
||||
|
||||
# 版本更新记录
|
||||
## [0.0.13] - 2024-09-12
|
||||
### Added
|
||||
- RAG检索增强能力组件版本更新
|
||||
- 本版本提供知识库构建、RAG检索召回环节标准作业流程，组件覆盖数据加载、数据处理、索引构建、知识入库、意图改写、检索重排等一系列RAG原子能力，帮助用户在开源场景下快速构建通用RAG智能体方案。
|
||||
|
||||
- 智能体产品化平台更新
|
||||
- 本版本新增支持智能体画布编排、私有知识库构建、自定义插件等能力，通过低代码、可视化的方式帮助用户快速构建与编排智能体。
|
||||
|
||||
- 新增智谱GLM默认模型组件
|
||||
- 新增SQLiteStore存储组件
|
||||
- 新增flow编排执行引擎
|
||||
|
||||
### Note
|
||||
- system_db_uri默认路径优化
|
||||
- 默认路径已兼容windows平台，详情见[issue142](https://github.com/alipay/agentUniverse/issues/142)
|
||||
- ReactAgent支持链停止词配置化
|
||||
- ReactAgent yaml配置目前已经支持stop_sequence关键词，用户可以自行配置链停止词,详情见[issue127](https://github.com/alipay/agentUniverse/issues/127)
|
||||
- 新增RAG原理介绍与RAG快速构建指导文档，请关注README与用户指南相应部分。
|
||||
- 新增智能体产品化平台高阶指导文档，请关注README与用户指南相应部分。
|
||||
- 部分代码优化与文档更新
|
||||
|
||||
## [0.0.12] - 2024-08-14
|
||||
### Added
|
||||
- agentUniverse产品化版本提供
|
||||
|
||||
@@ -5,7 +5,7 @@ Language version: [English](./README.md) | [中文](./README_zh.md) | [日本語
|
||||
|
||||
|
||||
[](LICENSE)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
|
||||
|
||||
****************************************
|
||||
@@ -67,7 +67,7 @@ pip install magent-ui ruamel.yaml
|
||||
|
||||
Run the [product_application.py](sample_standard_app/app/bootstrap/product_application.py) file located in sample_standard_app/app/bootstrap for a one-click start.
|
||||
|
||||
For more details, refer to [Quick Start for Product Platform](./docs/guidebook/en/10_1_1_Product%20Platform%20Quick%20Start.md).
|
||||
For more details, refer to [Quick Start for Product Platform](./docs/guidebook/en/10_1_1_Product%20Platform%20Quick%20Start.md) and the [Advanced Guide](./docs/guidebook/en/10_1_2_Product_Platform_Advancement_Guide.md).
|
||||
|
||||
This feature is jointly launched by [difizen](https://github.com/difizen/magent) and agentUniverse.
|
||||
|
||||
@@ -75,7 +75,7 @@ This feature is jointly launched by [difizen](https://github.com/difizen/magent)
|
||||
|
||||
## Cases and Example Projects
|
||||
### 🌟 Use Cases
|
||||
[Legal Consultation Agent](./docs/guidebook/en/7_1_1_Legal_Consultation_Case.md)
|
||||
[Legal Consultation Agent v2](./docs/guidebook/en/7_1_1_Legal_Consultation_Case.md)
|
||||
|
||||
[Python Code Generation and Execution Agent](./docs/guidebook/en/7_1_1_Python_Auto_Runner.md)
|
||||
|
||||
@@ -85,6 +85,9 @@ This feature is jointly launched by [difizen](https://github.com/difizen/magent)
|
||||
|
||||
[Andrew Ng's Reflexive Workflow Translation Agent Replication](./docs/guidebook/en/7_1_1_Translation_Case.md)
|
||||
|
||||
#### 🚩 How to Quickly Build an RAG Agent
|
||||
The RAG components have been fully upgraded. This tutorial provides a guide on how to quickly build an RAG agent in agentUniverse. You can refer to the documentation on [How to Build a RAG Agent](./docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md). For more theoretical content, please check the documentation on [Introduction to RAG](./docs/guidebook/en/2_2_4_RAG.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)
|
||||
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
|
||||
|
||||
[](LICENSE)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
|
||||
|
||||
****************************************
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
|
||||
|
||||
[](LICENSE)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
[](https://pypi.org/project/agentUniverse/)
|
||||
|
||||
|
||||
****************************************
|
||||
@@ -65,13 +65,14 @@ pip install magent-ui ruamel.yaml
|
||||
运行sample_standard_app/app/boostrap下的[product_application.py](sample_standard_app/app/bootstrap/product_application.py)文件，一键启动。
|
||||
|
||||
更多详情参考 [产品化平台快速开始](./docs/guidebook/zh/10_1_1_产品化平台快速开始.md)
|
||||
与 [产品化平台进阶指南](./10_1_2_产品化平台进阶指南.md) 。
|
||||
|
||||
本功能由 [difizen](https://github.com/difizen/magent) X agentUniverse联合推出。
|
||||
|
||||
****************************************
|
||||
## 案例与样例工程
|
||||
### 🌟 使用案例
|
||||
[法律咨询Agent](./docs/guidebook/zh/7_1_1_法律咨询案例.md)
|
||||
[法律咨询Agent_v2](./docs/guidebook/zh/7_1_1_法律咨询案例.md)
|
||||
|
||||
[Python代码生成与执行Agent](./docs/guidebook/zh/7_1_1_Python自动执行案例.md)
|
||||
|
||||
@@ -81,6 +82,8 @@ pip install magent-ui ruamel.yaml
|
||||
|
||||
[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)
|
||||
|
||||
#### 🚩 如何快速构建RAG智能体
|
||||
RAG组件全面升级，教程提供一个在agentUniverse中快速构建一个RAG智能体，可查看文档[如何构建RAG智能体](./docs/guidebook/zh/2_2_4_如何构建RAG智能体.md)，更多原理性内容可查看文档[RAG介绍](./docs/guidebook/zh/2_2_4_RAG.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)
|
||||
|
||||
@@ -31,6 +31,8 @@
|
||||
* 2.2.5.1 [Define And Use](2_2_6_Planner_Define_And_Use.md)
|
||||
* 2.2.5.2 [Related Domain Objects](2_2_6_Planner_Related_Domain_Objects.md)
|
||||
* 2.3 Technical Components
|
||||
* 2.3.1 [RAG](2_2_4_RAG.md)
|
||||
* 2.3.1.1 [How To Build A RAG Agent](2_2_4_How_To_Build_A_RAG_Agent.md)
|
||||
* 2.4 Others
|
||||
* 2.4.1 Service
|
||||
* 2.4.1.1 [Registration and Usage](2_4_1_Service_Registration_and_Usage.md)
|
||||
@@ -72,6 +74,7 @@
|
||||
* 3.2.2.1 [SQLDBWrapper](2_3_1_SQLDB_WRAPPER.md)
|
||||
* 3.2.2.2 [Milvus](3_3_1_Milvus.md)
|
||||
* 3.2.2.3 [ChromaDB](3_3_2_ChromaDB.md)
|
||||
* 3.2.2.4 [Sqlite](3_3_3_Sqlite.md)
|
||||
* 3.2.3 Msg
|
||||
* 3.2.4 Logging
|
||||
* 3.2.4.1 [Alibaba Cloud SLS](3_2_4_Alibaba_Cloud_SLS.md)
|
||||
@@ -85,7 +88,7 @@
|
||||
|
||||
**6. Use Cases**
|
||||
* 6.1 RAG-Type Agent Examples
|
||||
* 6.1.1 [Legal Consultation Agent](7_1_1_Legal_Consultation_Case.md)
|
||||
* 6.1.1 [Legal Consultation Agent v2](7_1_1_Legal_Consultation_Case.md)
|
||||
* 6.2 ReAct-Type Agent Examples
|
||||
* 6.2.1 [Python Code Generation and Execution Agent](7_1_1_Python_Auto_Runner.md)
|
||||
* 6.3 [Discussion Group Based on Multi-Turn Multi-Agent Mode](6_2_1_Discussion_Group.md)
|
||||
@@ -95,6 +98,7 @@
|
||||
|
||||
**7.Product Platform**
|
||||
* 7.1 [Quick Use](./10_1_1_Product Platform Quick Start.md)
|
||||
* 7.2 [Advancement Guide](./10_1_2_Product_Platform_Advancement_Guide.md)
|
||||
|
||||
**8. Series of Articles**
|
||||
|
||||
|
||||
@@ -7,7 +7,9 @@ In this section, we will show you how to:
|
||||
|
||||
## Workflow Agent Orchestration Feature
|
||||
``` text
|
||||
Note: existing users of the agentUniverse product platform, please upgrade the magent-ui package to version 0.1.17.
|
||||
Note: For old users of the agentUniverse productization platform orchestration capability, please upgrade the magent-ui package version to 0.1.17, and the corresponding aU version must not be lower than 0.0.13. You can use the following command for version-specific installation:
|
||||
|
||||
pip install magent-ui==0.1.17 ruamel.yaml --force-reinstall
|
||||
```
|
||||
### Create Workflow Agent
|
||||
On the aU-product homepage, click the "Create Agent" button to the right of the agent tab, and select the workflow type agent.
|
||||
|
||||
@@ -10,7 +10,8 @@ The platform has currently integrated the following list of models; please refer
|
||||
| [BaiChuan](3_1_2_BaiChuan_LLM_Use.md) |
|
||||
| [Claude](3_1_2_Claude_LLM_Use.md) |
|
||||
| [ollama](3_1_2_Ollama_LLM_Use.md) |
|
||||
| [DeepSeek](3_1_2_DeepSeek_LLM_Use.md) |
|
||||
| [DeepSeek](3_1_2_DeepSeek_LLM_Use.md) |
|
||||
| [GLM](3_1_2_GLM_LLM_Use.md) |
|
||||
|
||||
To facilitate the integration of models with OpenAI-style protocols, we offer a wrapper object based on the OpenAI general protocol. See [OpenAIStyleLLM](3_1_2_OpenAIStyleLLM_Use.md).
|
||||
|
||||
|
||||
37
docs/guidebook/en/3_1_2_GLM_LLM_Use.md
Normal file
37
docs/guidebook/en/3_1_2_GLM_LLM_Use.md
Normal file
@@ -0,0 +1,37 @@
|
||||
# GLM Usage
|
||||
## 1. Create the relevant file.
|
||||
Create a YAML file, for example, user_glm.yaml
|
||||
Paste the following content into your user_glm.yaml file.
|
||||
```yaml
|
||||
name: 'user_zhipu_llm'
|
||||
description: 'default default_zhipu_llm llm with spi'
|
||||
model_name: 'glm-4-flash'
|
||||
max_tokens: 1000
|
||||
metadata:
|
||||
type: 'LLM'
|
||||
module: 'agentuniverse.llm.default.zhipu_openai_style_llm'
|
||||
class: 'DefaultZhiPuLLM'
|
||||
```
|
||||
## 2. Environment Setup
|
||||
Must be configured: ZHIPU_API_KEY
|
||||
Optional: ZHIPU_API_BASE
|
||||
### 2.1 Configure through Python code
|
||||
```python
|
||||
import os
|
||||
os.environ['ZHIPU_API_KEY'] = '*****'
|
||||
os.environ['ZHIPU_API_BASE'] = 'xxxxx'
|
||||
```
|
||||
### 2.2 Configure through the configuration file
|
||||
In the custom_key.toml file under the config directory of the project, add the configuration:
|
||||
```toml
|
||||
ZHIPU_API_KEY='xxxxxx'
|
||||
ZHIPU_API_BASE='https://open.bigmodel.cn/api/paas/v4/'
|
||||
```
|
||||
## 3. Obtaining the GLM API KEY
|
||||
Reference GLM Official Documentation: https://maas.aminer.cn
|
||||
|
||||
## 4. Tips
|
||||
In agentuniverse, we have already created a llm with the name default_zhipu_llm. After configuring the ZHIPU_API_KEY, users can directly use it.
|
||||
|
||||
|
||||
|
||||
@@ -35,6 +35,8 @@
|
||||
* 2.2.6.1 [计划定义与使用](2_2_6_计划定义与使用.md)
|
||||
* 2.2.6.2 [计划及相关领域对象](2_2_6_计划及相关领域对象.md)
|
||||
* 2.3 技术组件
|
||||
* 2.3.1 [RAG](2_2_4_RAG.md)
|
||||
* 2.3.1.1 [如何构建RAG智能体](2_2_4_如何构建RAG智能体.md)
|
||||
* 2.4 其他
|
||||
* 2.4.1 服务化
|
||||
* 2.4.1.1 [注册与使用](2_4_1_服务注册与使用.md)
|
||||
@@ -76,6 +78,7 @@
|
||||
* 3.2.2.1 [SQLDBWrapper](2_3_1_SQLDB_WRAPPER.md)
|
||||
* 3.2.2.2 [Milvus](3_3_1_Milvus.md)
|
||||
* 3.2.2.3 [ChromaDB](3_3_2_ChromaDB.md)
|
||||
* 3.2.2.4 [Sqlite](3_3_3_Sqlite.md)
|
||||
* 3.2.3 消息(Msg)
|
||||
* 3.2.4 日志(Logging)
|
||||
* 3.2.4.1 [阿里云SLS](3_2_4_阿里云SLS.md)
|
||||
@@ -89,7 +92,7 @@
|
||||
|
||||
**6.使用案例**
|
||||
* 6.1 RAG类Agent案例
|
||||
* 6.1.1 [法律咨询Agent](7_1_1_法律咨询案例.md)
|
||||
* 6.1.1 [法律咨询Agent_v2](7_1_1_法律咨询案例.md)
|
||||
* 6.2 ReAct类Agent案例
|
||||
* 6.2.1 [Python代码生成与执行Agent](7_1_1_Python自动执行案例.md)
|
||||
* 6.3 [基于多轮多Agent的讨论小组](6_2_1_讨论组.md)
|
||||
@@ -99,6 +102,7 @@
|
||||
|
||||
**7.产品化平台**
|
||||
* 7.1 [快速使用](./10_1_1_产品化平台快速开始.md)
|
||||
* 7.2 [进阶指南](./10_1_2_产品化平台进阶指南.md)
|
||||
|
||||
**8.系列文章**
|
||||
|
||||
|
||||
@@ -7,7 +7,10 @@
|
||||
|
||||
## workflow智能体编排功能
|
||||
``` text
|
||||
注意：agentUniverse产品化平台老用户请将 magent-ui 包版本升级到0.1.17
|
||||
注意：agentUniverse产品化平台编排能力老用户请将 magent-ui 包版本升级到0.1.17，同时对应的aU版本不得低于0.0.13。
|
||||
|
||||
可使用如下语句进行版本指定覆盖安装:
|
||||
pip install magent-ui==0.1.17 ruamel.yaml --force-reinstall
|
||||
```
|
||||
### 创建workflow智能体
|
||||
产品化主页，点击智能体的右一创建智能体按钮，选择workflow类型智能体。
|
||||
|
||||
@@ -1,16 +1,17 @@
|
||||
# 模型（LLM）列表
|
||||
目前平台已经接入了如下模型列表，详细使用方式请关注本章节各LLM的说明。
|
||||
|
||||
| 模型LLM(系列)名称 |
|
||||
|----------------------------------|
|
||||
| [OpenAI](3_1_2_OpenAI使用.md) |
|
||||
| [通义千问](3_1_2_Qwen使用.md) |
|
||||
| [文心一言](3_1_2_文心使用.md) |
|
||||
| [Kimi](3_1_2_Kimi使用.md) |
|
||||
| [百川](3_1_2_百川使用.md) |
|
||||
| [Claude](3_1_2_Claude使用.md) |
|
||||
| [ollama](3_1_2_Ollama使用.md) |
|
||||
| [DeepSeek](3_1_2_DeepSeek使用.md) |
|
||||
| 模型LLM(系列)名称 |
|
||||
|---------------------------------|
|
||||
| [OpenAI](3_1_2_OpenAI使用.md) |
|
||||
| [通义千问](3_1_2_Qwen使用.md) |
|
||||
| [文心一言](3_1_2_文心使用.md) |
|
||||
| [Kimi](3_1_2_Kimi使用.md) |
|
||||
| [百川](3_1_2_百川使用.md) |
|
||||
| [Claude](3_1_2_Claude使用.md) |
|
||||
| [ollama](3_1_2_Ollama使用.md) |
|
||||
| [DeepSeek](3_1_2_DeepSeek使用.md) |
|
||||
| [智谱GLM](3_1_2_智谱GLM使用.md) |
|
||||
|
||||
为方便用户接入OpenAI风格协议的模型，提供基于OpenAI通用协议接入包装对象 [OpenAIStyleLLM](3_1_2_OpenAIStyleLLM使用.md)。
|
||||
|
||||
|
||||
36
docs/guidebook/zh/3_1_2_智谱GLM使用.md
Normal file
36
docs/guidebook/zh/3_1_2_智谱GLM使用.md
Normal file
@@ -0,0 +1,36 @@
|
||||
# GLM 使用
|
||||
## 1. 创建相关文件
|
||||
创建一个yaml文件，例如 user_glm.yaml
|
||||
将以下内容粘贴到您的user_glm.yaml文件当中
|
||||
```yaml
|
||||
name: 'user_zhipu_llm'
|
||||
description: 'default default_zhipu_llm llm with spi'
|
||||
model_name: 'glm-4-flash'
|
||||
max_tokens: 1000
|
||||
metadata:
|
||||
type: 'LLM'
|
||||
module: 'agentuniverse.llm.default.zhipu_openai_style_llm'
|
||||
class: 'DefaultZhiPuLLM'
|
||||
```
|
||||
## 2. 环境设置
|
||||
必须配置：ZHIPU_API_KEY、ZHIPU_API_BASE
|
||||
### 2.1 通过python代码配置
|
||||
```python
|
||||
import os
|
||||
os.environ['ZHIPU_API_KEY'] = '*****'
|
||||
os.environ['ZHIPU_API_BASE'] = 'xxxxx'
|
||||
```
|
||||
### 2.2 通过配置文件配置
|
||||
在项目的config目录下的custom_key.toml当中，添加配置：
|
||||
```toml
|
||||
ZHIPU_API_KEY='xxxxxx'
|
||||
ZHIPU_API_BASE='https://open.bigmodel.cn/api/paas/v4/'
|
||||
```
|
||||
## 3.ZHIPU API KEY 获取
|
||||
参考 智谱GLM 官方文档：https://maas.aminer.cn
|
||||
|
||||
## 4. Tips
|
||||
在agentuniverse中，我们已经创建了一个name为default_zhipu_llm的llm,用户在配置ZHIPU_API_KEY、ZHIPU_API_BASE之后可以直接使用。
|
||||
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "agentUniverse"
|
||||
version = "0.0.12"
|
||||
version = "0.0.13"
|
||||
description = "agentUniverse is a framework for developing applications powered by multi-agent base on large language model."
|
||||
|
||||
authors = ["AntGroup <jerry.zzw@antgroup.com>"]
|
||||
|
||||
Reference in New Issue
Block a user