update readmes docs about coagent

This commit is contained in:
shanshi 2024-01-29 11:40:31 +08:00
parent b7fdf50da7
commit 0fa4b8222c
8 changed files with 20 additions and 2 deletions

View File

@ -14,6 +14,7 @@ DevOps-ChatBot是由蚂蚁CodeFuse团队开发的开源AI智能助手致力
## 🔔 更新 ## 🔔 更新
- [2024.01.29] 开放可配置化的multi-agent框架coagent详情见[使用说明](sources/readme_docs/coagent/coagent.md)
- [2023.12.26] 基于FastChat接入开源私有化大模型和大模型接口的能力开放 - [2023.12.26] 基于FastChat接入开源私有化大模型和大模型接口的能力开放
- [2023.12.14] 量子位公众号专题报道:[文章链接](https://mp.weixin.qq.com/s/MuPfayYTk9ZW6lcqgMpqKA) - [2023.12.14] 量子位公众号专题报道:[文章链接](https://mp.weixin.qq.com/s/MuPfayYTk9ZW6lcqgMpqKA)
- [2023.12.01] Multi-Agent和代码库检索功能开放 - [2023.12.01] Multi-Agent和代码库检索功能开放

View File

@ -13,6 +13,7 @@ This project is an open-source AI intelligent assistant, specifically designed f
## 🔔 Updates ## 🔔 Updates
- [2024.01.29] A configurational multi-agent framework, CoAgent, has been open-sourced. For more details, please refer to [coagent](sources/readme_docs/coagent/coagent-en.md)
- [2023.12.26] Opening the capability to integrate with open-source private large models and large model interfaces based on FastChat - [2023.12.26] Opening the capability to integrate with open-source private large models and large model interfaces based on FastChat
- [2023.12.01] Release of Multi-Agent and codebase retrieval functionalities. - [2023.12.01] Release of Multi-Agent and codebase retrieval functionalities.
- [2023.11.15] Addition of Q&A enhancement mode based on the local codebase. - [2023.11.15] Addition of Q&A enhancement mode based on the local codebase.

View File

@ -1,4 +1,7 @@
## Attention
AttentionThe overall content is not yet complete, and further refinements to the flow and other Agent diagrams will be made in the future.
## Introduction to Core Connectors ## Introduction to Core Connectors
To facilitate everyone's understanding of the entire CoAgent link, we use a Flow format to detail how to build through configuration settings. To facilitate everyone's understanding of the entire CoAgent link, we use a Flow format to detail how to build through configuration settings.

View File

@ -1,4 +1,8 @@
## 注意
注意整体内容未完善后续还会完善flow和其它Agent的图例
## 核心Connector介绍 ## 核心Connector介绍
为了便于大家理解整个 CoAgent 的链路,我们采取 Flow 的形式来详细介绍如何通过配置构建 为了便于大家理解整个 CoAgent 的链路,我们采取 Flow 的形式来详细介绍如何通过配置构建

View File

@ -34,7 +34,7 @@ The following modules will introduce the necessary components of the Multi Agent
In summary, these five elements together construct a Multi-Agent framework, ensuring closer and more efficient cooperation between Agents while also adapting to more complex task requirements and a variety of interaction scenarios. By combining multiple Agent chains to implement a complete and complex project launch scenario (Dev Phase), such as Demand Chain (CEO), Product Argument Chain (CPO, CFO, CTO), Engineer Group Chain (Selector, Developer1~N), QA Engineer Chain (Developer, Tester), Deploy Chain (Developer, Deployer). In summary, these five elements together construct a Multi-Agent framework, ensuring closer and more efficient cooperation between Agents while also adapting to more complex task requirements and a variety of interaction scenarios. By combining multiple Agent chains to implement a complete and complex project launch scenario (Dev Phase), such as Demand Chain (CEO), Product Argument Chain (CPO, CFO, CTO), Engineer Group Chain (Selector, Developer1~N), QA Engineer Chain (Developer, Tester), Deploy Chain (Developer, Deployer).
## 模块分类 ## 模块分类
- [connector](/sources/readme_docs/coagent/connector.md) - [connector](/sources/readme_docs/coagent/connector/connector_agent.md)
- document_loaders - document_loaders
- embeddings - embeddings
- llm_models - llm_models

View File

@ -38,7 +38,7 @@
## 模块分类 ## 模块分类
- [connector](/sources/readme_docs/coagent/connector.md) - [connector](/sources/readme_docs/coagent/connector/connector_agent.md)
- document_loaders - document_loaders
- embeddings - embeddings
- llm_models - llm_models

View File

@ -11,6 +11,11 @@ aliases:
## Quick Start ## Quick Start
Attention
Testing has only been conducted on GPT-3.5-turbo and higher models.
The models need to possess strong command-following capabilities.
It is recommended to test with more powerful models like qwen-72b, openai, etc.
### First, set up the LLM configuration ### First, set up the LLM configuration
``` ```
import os, sys import os, sys

View File

@ -10,6 +10,10 @@ aliases:
## 快速使用 ## 快速使用
注意:
只在GPT-3.5-turbo及以上模型进行过测试。需要模型具备较强的指令遵循能力。
推荐拿qwen-72b、openai等较强的模型进行测试
### 首先填写LLM配置 ### 首先填写LLM配置
``` ```
import os, sys import os, sys