[**🇨🇳中文**](https://github.com/shibing624/agentica/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/agentica/blob/main/README_EN.md) | [**🇯🇵日本語**](https://github.com/shibing624/agentica/blob/main/README_JP.md)
<div align="center">
<a href="https://github.com/shibing624/agentica">
<img src="https://raw.githubusercontent.com/shibing624/agentica/main/docs/logo.png" height="150" alt="Logo">
</a>
</div>
-----------------
# Agentica: Build AI Agents
[](https://badge.fury.io/py/agentica)
[](https://pepy.tech/project/agentica)
[](CONTRIBUTING.md)
[](LICENSE)
[](requirements.txt)
[](https://github.com/shibing624/agentica/issues)
[](#Contact)
**Agentica**: A Human-Centric Framework for Large Language Model Agent Building. 快速打造你的专属Agent。
## Overview
#### LLM Agent
<img src="https://github.com/shibing624/agentica/blob/main/docs/llm_agentv2.png" width="800" />
- **规划（Planning）**：任务拆解、生成计划、反思
- **记忆（Memory）**：短期记忆（prompt实现）、长期记忆（RAG实现）
- **工具使用（Tool use）**：function call能力，调用外部API，以获取外部信息，包括当前日期、日历、代码执行能力、对专用信息源的访问等
#### Agentica Assistant Architecture
<img src="https://github.com/shibing624/agentica/blob/main/docs/agent_arch.png" width="800" />
- **Planner**：负责让LLM生成一个多步计划来完成复杂任务，生成相互依赖的“链式计划”，定义每一步所依赖的上一步的输出
- **Worker**：接受“链式计划”，循环遍历计划中的每个子任务，并调用工具完成任务，可以自动反思纠错以完成任务
- **Solver**：求解器将所有这些输出整合为最终答案
## Features
`Agentica`是一个Agent构建工具，功能：
- 简单代码快速编排Agent，支持 Reflection(反思）、Plan and Solve(计划并执行)、RAG、Agent、Multi-Agent、Multi-Role、Workflow等功能
- Agent支持prompt自定义，支持多种工具调用（tool_calls）
- 支持OpenAI/Azure/Deepseek/Moonshot/Claude/Ollama/Together API调用
## Installation
```bash
pip install -U agentica
```
or
```bash
git clone https://github.com/shibing624/agentica.git
cd agentica
pip install .
```
## Getting Started
#### 1. Install requirements
```shell
git clone https://github.com/shibing624/agentica.git
cd agentica
pip install -r requirements.txt
```
#### 2. Run the example
```shell
# Copying required .env file, and fill in the LLM api key
cp .env.example ~/.agentica/.env
cd examples
python web_search_deepseek_demo.py
```
1. 复制[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)文件为`~/.agentica/.env`，并填写LLM api key(选填DEEPSEEK_API_KEY、MOONSHOT_API_KEY、OPENAI_API_KEY等任一个即可)。
2. 使用`agentica`构建Agent并执行：
自动调用google搜索工具，示例[examples/web_search_deepseek_demo.py](https://github.com/shibing624/agentica/blob/main/examples/web_search_deepseek_demo.py)
```python
from agentica import Assistant, DeepseekLLM, SearchSerperTool
m = Assistant(llm=DeepseekLLM(), tools=[SearchSerperTool()])
r = m.run("一句话介绍林黛玉")
print(r, "".join(r))
r = m.run("北京最近的新闻top3", stream=True)
print(r, "".join(r))
r = m.run("总结前面的问答", stream=False)
print(r)
```
## Web UI
[shibing624/ChatPilot](https://github.com/shibing624/ChatPilot) 兼容`agentica`，可以通过Web UI进行交互。
Web Demo: https://chat.mulanai.com
<img src="https://github.com/shibing624/ChatPilot/blob/main/docs/shot.png" width="800" />
```shell
git clone https://github.com/shibing624/ChatPilot.git
cd ChatPilot
pip install -r requirements.txt
cp .env.example .env
bash start.sh
```
## Examples
| 示例 | 描述 |
|---------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|
| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py) | 实现了基础版RAG，基于Txt文档回答问题 |
| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py) | 实现了高级版RAG，基于PDF文档回答问题，新增功能：pdf文件解析、query改写，字面+语义多路召回，召回排序（rerank） |
| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py) | 实现了Code Interpreter功能，自动生成python代码，并执行 |
| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py) | 实现了Research功能，自动调用搜索工具，汇总信息后撰写科技报告 |
| [examples/team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/team_news_article_demo.py) | 实现了写新闻稿的team协作，multi-role实现，委托不用角色完成各自任务：研究员检索分析文章，撰写员根据排版写文章，汇总多角色成果输出结果 |
| [examples/workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_news_article_demo.py) | 实现了写新闻稿的工作流，multi-agent的实现，定义了多个Assistant和Task，多次调用搜索工具，并生成高级排版的新闻文章 |
| [examples/workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_investment_demo.py) | 实现了投资研究的工作流：股票信息收集 - 股票分析 - 撰写分析报告 - 复查报告等多个Task |
| [examples/crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage_demo.py) | 实现了网页分析工作流：从Url爬取融资快讯 - 分析网页内容和格式 - 提取核心信息 - 汇总保存为md文件 |
| [examples/find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv_demo.py) | 实现了论文推荐工作流：自动从arxiv搜索多组论文 - 相似论文去重 - 提取核心论文信息 - 保存为csv文件 |
| [examples/remove_image_background_demo.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background_demo.py) | 实现了自动去除图片背景功能，包括自动通过pip安装库，调用库实现去除图片背景 |
| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py) | 实现了自动训练分类模型的工作流：读取训练集文件并理解格式 - 谷歌搜索pytextclassifier库 - 爬取github页面了解pytextclassifier的调用方法 - 写代码并执行fasttext模型训练 - check训练好的模型预测结果 |
| [examples/llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/llm_os_demo.py) | 实现了LLM OS的初步设计，基于LLM设计操作系统，可以通过LLM调用RAG、代码执行器、Shell等工具，并协同代码解释器、研究助手、投资助手等来解决问题。 |
| [examples/workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_write_novel_demo.py) | 实现了写小说的工作流：定小说提纲 - 搜索谷歌反思提纲 - 撰写小说内容 - 保存为md文件 |
| [examples/workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_write_tutorial_demo.py) | 实现了写技术教程的工作流：定教程目录 - 反思目录内容 - 撰写教程内容 - 保存为md文件 |
| [examples/self_evolving_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/self_evolving_agent_demo.py) | 实现了基于长期记忆的自我进化智能体，可以基于历史问答信息自我调整决策 |
### LLM OS
The LLM OS design:
<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llmos.png" width="800" />
#### Run the LLM OS App
```shell
cd examples
streamlit run llm_os_demo.py
```
<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png" width="800" />
### Self-evolving Agent
The self-evolving agent design:
<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/sage_arch.png" width="800" />
#### Feature
具有反思和增强记忆能力的自我进化智能体(self-evolving Agents with Reflective and Memory-augmented Abilities, SAGE)
实现方法:
1. 使用PythonAssistant作为SAGE智能体，使用AzureOpenAILLM作为LLM, 具备code-interpreter功能，可以执行Python代码，并自动纠错。
2. 使用CsvMemoryDb作为SAGE智能体的记忆，用于存储用户的问题和答案，下次遇到相似的问题时，可以直接返回答案。
#### Run Self-evolving Agent App
```shell
cd examples
streamlit run self_evolving_agent_demo.py
```
<img alt="sage_snap" src="https://github.com/shibing624/agentica/blob/main/docs/sage_snap.png" width="800" />
## Contact
- Issue(建议)
：[](https://github.com/shibing624/agentica/issues)
- 邮件我：xuming: xuming624@qq.com
- 微信我： 加我*微信号：xuming624, 备注：姓名-公司-NLP* 进NLP交流群。
<img src="https://github.com/shibing624/agentica/blob/main/docs/wechat.jpeg" width="200" />
## Citation
如果你在研究中使用了`agentica`，请按如下格式引用：
APA:
```
Xu, M. agentica: A Human-Centric Framework for Large Language Model Agent Workflows (Version 0.0.2) [Computer software]. https://github.com/shibing624/agentica
```
BibTeX:
```
@misc{Xu_agentica,
title={agentica: A Human-Centric Framework for Large Language Model Agent Workflows},
author={Xu Ming},
year={2024},
howpublished={\url{https://github.com/shibing624/agentica}},
}
```
## License
授权协议为 [The Apache License 2.0](/LICENSE)，可免费用做商业用途。请在产品说明中附加`agentica`的链接和授权协议。
## Contribute
项目代码还很粗糙，如果大家对代码有所改进，欢迎提交回本项目，在提交之前，注意以下两点：
- 在`tests`添加相应的单元测试
- 使用`python -m pytest`来运行所有单元测试，确保所有单测都是通过的
之后即可提交PR。
## Acknowledgements
- [https://github.com/langchain-ai/langchain](https://github.com/langchain-ai/langchain)
- [https://github.com/simonmesmith/agentflow](https://github.com/simonmesmith/agentflow)
- [https://github.com/phidatahq/phidata](https://github.com/phidatahq/phidata)
Thanks for their great work!
Raw data
{
"_id": null,
"home_page": "https://github.com/shibing624/agentica",
"name": "agentica",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8.0",
"maintainer_email": null,
"keywords": "Agentica, Agent Tool, action, agent, agentica",
"author": "XuMing",
"author_email": "xuming624@qq.com",
"download_url": "https://files.pythonhosted.org/packages/94/53/8f2f794124f9e8e54c924bf4efab196773646525075c03938d8d2453ebfe/agentica-0.1.8.tar.gz",
"platform": null,
"description": "[**\ud83c\udde8\ud83c\uddf3\u4e2d\u6587**](https://github.com/shibing624/agentica/blob/main/README.md) | [**\ud83c\udf10English**](https://github.com/shibing624/agentica/blob/main/README_EN.md) | [**\ud83c\uddef\ud83c\uddf5\u65e5\u672c\u8a9e**](https://github.com/shibing624/agentica/blob/main/README_JP.md)\n\n<div align=\"center\">\n <a href=\"https://github.com/shibing624/agentica\">\n <img src=\"https://raw.githubusercontent.com/shibing624/agentica/main/docs/logo.png\" height=\"150\" alt=\"Logo\">\n </a>\n</div>\n\n-----------------\n\n# Agentica: Build AI Agents\n[](https://badge.fury.io/py/agentica)\n[](https://pepy.tech/project/agentica)\n[](CONTRIBUTING.md)\n[](LICENSE)\n[](requirements.txt)\n[](https://github.com/shibing624/agentica/issues)\n[](#Contact)\n\n\n**Agentica**: A Human-Centric Framework for Large Language Model Agent Building. \u5feb\u901f\u6253\u9020\u4f60\u7684\u4e13\u5c5eAgent\u3002\n\n## Overview\n\n#### LLM Agent\n<img src=\"https://github.com/shibing624/agentica/blob/main/docs/llm_agentv2.png\" width=\"800\" />\n\n- **\u89c4\u5212\uff08Planning\uff09**\uff1a\u4efb\u52a1\u62c6\u89e3\u3001\u751f\u6210\u8ba1\u5212\u3001\u53cd\u601d\n- **\u8bb0\u5fc6\uff08Memory\uff09**\uff1a\u77ed\u671f\u8bb0\u5fc6\uff08prompt\u5b9e\u73b0\uff09\u3001\u957f\u671f\u8bb0\u5fc6\uff08RAG\u5b9e\u73b0\uff09\n- **\u5de5\u5177\u4f7f\u7528\uff08Tool use\uff09**\uff1afunction call\u80fd\u529b\uff0c\u8c03\u7528\u5916\u90e8API\uff0c\u4ee5\u83b7\u53d6\u5916\u90e8\u4fe1\u606f\uff0c\u5305\u62ec\u5f53\u524d\u65e5\u671f\u3001\u65e5\u5386\u3001\u4ee3\u7801\u6267\u884c\u80fd\u529b\u3001\u5bf9\u4e13\u7528\u4fe1\u606f\u6e90\u7684\u8bbf\u95ee\u7b49\n\n#### Agentica Assistant Architecture \n<img src=\"https://github.com/shibing624/agentica/blob/main/docs/agent_arch.png\" width=\"800\" />\n\n- **Planner**\uff1a\u8d1f\u8d23\u8ba9LLM\u751f\u6210\u4e00\u4e2a\u591a\u6b65\u8ba1\u5212\u6765\u5b8c\u6210\u590d\u6742\u4efb\u52a1\uff0c\u751f\u6210\u76f8\u4e92\u4f9d\u8d56\u7684\u201c\u94fe\u5f0f\u8ba1\u5212\u201d\uff0c\u5b9a\u4e49\u6bcf\u4e00\u6b65\u6240\u4f9d\u8d56\u7684\u4e0a\u4e00\u6b65\u7684\u8f93\u51fa\n- **Worker**\uff1a\u63a5\u53d7\u201c\u94fe\u5f0f\u8ba1\u5212\u201d\uff0c\u5faa\u73af\u904d\u5386\u8ba1\u5212\u4e2d\u7684\u6bcf\u4e2a\u5b50\u4efb\u52a1\uff0c\u5e76\u8c03\u7528\u5de5\u5177\u5b8c\u6210\u4efb\u52a1\uff0c\u53ef\u4ee5\u81ea\u52a8\u53cd\u601d\u7ea0\u9519\u4ee5\u5b8c\u6210\u4efb\u52a1\n- **Solver**\uff1a\u6c42\u89e3\u5668\u5c06\u6240\u6709\u8fd9\u4e9b\u8f93\u51fa\u6574\u5408\u4e3a\u6700\u7ec8\u7b54\u6848\n\n\n## Features\n`Agentica`\u662f\u4e00\u4e2aAgent\u6784\u5efa\u5de5\u5177\uff0c\u529f\u80fd\uff1a\n\n- \u7b80\u5355\u4ee3\u7801\u5feb\u901f\u7f16\u6392Agent\uff0c\u652f\u6301 Reflection(\u53cd\u601d\uff09\u3001Plan and Solve(\u8ba1\u5212\u5e76\u6267\u884c)\u3001RAG\u3001Agent\u3001Multi-Agent\u3001Multi-Role\u3001Workflow\u7b49\u529f\u80fd\n- Agent\u652f\u6301prompt\u81ea\u5b9a\u4e49\uff0c\u652f\u6301\u591a\u79cd\u5de5\u5177\u8c03\u7528\uff08tool_calls\uff09\n- \u652f\u6301OpenAI/Azure/Deepseek/Moonshot/Claude/Ollama/Together API\u8c03\u7528\n\n## Installation\n\n```bash\npip install -U agentica\n```\n\nor\n\n```bash\ngit clone https://github.com/shibing624/agentica.git\ncd agentica\npip install .\n```\n\n## Getting Started\n\n#### 1. Install requirements\n\n```shell\ngit clone https://github.com/shibing624/agentica.git\ncd agentica\npip install -r requirements.txt\n```\n\n#### 2. Run the example\n```shell\n# Copying required .env file, and fill in the LLM api key\ncp .env.example ~/.agentica/.env\n\ncd examples\npython web_search_deepseek_demo.py\n```\n\n1. \u590d\u5236[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)\u6587\u4ef6\u4e3a`~/.agentica/.env`\uff0c\u5e76\u586b\u5199LLM api key(\u9009\u586bDEEPSEEK_API_KEY\u3001MOONSHOT_API_KEY\u3001OPENAI_API_KEY\u7b49\u4efb\u4e00\u4e2a\u5373\u53ef)\u3002\n\n2. \u4f7f\u7528`agentica`\u6784\u5efaAgent\u5e76\u6267\u884c\uff1a\n\n\u81ea\u52a8\u8c03\u7528google\u641c\u7d22\u5de5\u5177\uff0c\u793a\u4f8b[examples/web_search_deepseek_demo.py](https://github.com/shibing624/agentica/blob/main/examples/web_search_deepseek_demo.py)\n\n```python\nfrom agentica import Assistant, DeepseekLLM, SearchSerperTool\n\nm = Assistant(llm=DeepseekLLM(), tools=[SearchSerperTool()])\n\nr = m.run(\"\u4e00\u53e5\u8bdd\u4ecb\u7ecd\u6797\u9edb\u7389\")\nprint(r, \"\".join(r))\nr = m.run(\"\u5317\u4eac\u6700\u8fd1\u7684\u65b0\u95fbtop3\", stream=True)\nprint(r, \"\".join(r))\nr = m.run(\"\u603b\u7ed3\u524d\u9762\u7684\u95ee\u7b54\", stream=False)\nprint(r)\n```\n\n\n## Web UI\n\n[shibing624/ChatPilot](https://github.com/shibing624/ChatPilot) \u517c\u5bb9`agentica`\uff0c\u53ef\u4ee5\u901a\u8fc7Web UI\u8fdb\u884c\u4ea4\u4e92\u3002\n\nWeb Demo: https://chat.mulanai.com\n\n<img src=\"https://github.com/shibing624/ChatPilot/blob/main/docs/shot.png\" width=\"800\" />\n\n```shell\ngit clone https://github.com/shibing624/ChatPilot.git\ncd ChatPilot\npip install -r requirements.txt\n\ncp .env.example .env\n\nbash start.sh\n```\n\n\n## Examples\n\n| \u793a\u4f8b | \u63cf\u8ff0 |\n|---------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|\n| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py) | \u5b9e\u73b0\u4e86\u57fa\u7840\u7248RAG\uff0c\u57fa\u4e8eTxt\u6587\u6863\u56de\u7b54\u95ee\u9898 |\n| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py) | \u5b9e\u73b0\u4e86\u9ad8\u7ea7\u7248RAG\uff0c\u57fa\u4e8ePDF\u6587\u6863\u56de\u7b54\u95ee\u9898\uff0c\u65b0\u589e\u529f\u80fd\uff1apdf\u6587\u4ef6\u89e3\u6790\u3001query\u6539\u5199\uff0c\u5b57\u9762+\u8bed\u4e49\u591a\u8def\u53ec\u56de\uff0c\u53ec\u56de\u6392\u5e8f\uff08rerank\uff09 |\n| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py) | \u5b9e\u73b0\u4e86Code Interpreter\u529f\u80fd\uff0c\u81ea\u52a8\u751f\u6210python\u4ee3\u7801\uff0c\u5e76\u6267\u884c |\n| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py) | \u5b9e\u73b0\u4e86Research\u529f\u80fd\uff0c\u81ea\u52a8\u8c03\u7528\u641c\u7d22\u5de5\u5177\uff0c\u6c47\u603b\u4fe1\u606f\u540e\u64b0\u5199\u79d1\u6280\u62a5\u544a |\n| [examples/team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/team_news_article_demo.py) | \u5b9e\u73b0\u4e86\u5199\u65b0\u95fb\u7a3f\u7684team\u534f\u4f5c\uff0cmulti-role\u5b9e\u73b0\uff0c\u59d4\u6258\u4e0d\u7528\u89d2\u8272\u5b8c\u6210\u5404\u81ea\u4efb\u52a1\uff1a\u7814\u7a76\u5458\u68c0\u7d22\u5206\u6790\u6587\u7ae0\uff0c\u64b0\u5199\u5458\u6839\u636e\u6392\u7248\u5199\u6587\u7ae0\uff0c\u6c47\u603b\u591a\u89d2\u8272\u6210\u679c\u8f93\u51fa\u7ed3\u679c |\n| [examples/workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_news_article_demo.py) | \u5b9e\u73b0\u4e86\u5199\u65b0\u95fb\u7a3f\u7684\u5de5\u4f5c\u6d41\uff0cmulti-agent\u7684\u5b9e\u73b0\uff0c\u5b9a\u4e49\u4e86\u591a\u4e2aAssistant\u548cTask\uff0c\u591a\u6b21\u8c03\u7528\u641c\u7d22\u5de5\u5177\uff0c\u5e76\u751f\u6210\u9ad8\u7ea7\u6392\u7248\u7684\u65b0\u95fb\u6587\u7ae0 |\n| [examples/workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_investment_demo.py) | \u5b9e\u73b0\u4e86\u6295\u8d44\u7814\u7a76\u7684\u5de5\u4f5c\u6d41\uff1a\u80a1\u7968\u4fe1\u606f\u6536\u96c6 - \u80a1\u7968\u5206\u6790 - \u64b0\u5199\u5206\u6790\u62a5\u544a - \u590d\u67e5\u62a5\u544a\u7b49\u591a\u4e2aTask |\n| [examples/crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage_demo.py) | \u5b9e\u73b0\u4e86\u7f51\u9875\u5206\u6790\u5de5\u4f5c\u6d41\uff1a\u4eceUrl\u722c\u53d6\u878d\u8d44\u5feb\u8baf - \u5206\u6790\u7f51\u9875\u5185\u5bb9\u548c\u683c\u5f0f - \u63d0\u53d6\u6838\u5fc3\u4fe1\u606f - \u6c47\u603b\u4fdd\u5b58\u4e3amd\u6587\u4ef6 |\n| [examples/find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv_demo.py) | \u5b9e\u73b0\u4e86\u8bba\u6587\u63a8\u8350\u5de5\u4f5c\u6d41\uff1a\u81ea\u52a8\u4ecearxiv\u641c\u7d22\u591a\u7ec4\u8bba\u6587 - \u76f8\u4f3c\u8bba\u6587\u53bb\u91cd - \u63d0\u53d6\u6838\u5fc3\u8bba\u6587\u4fe1\u606f - \u4fdd\u5b58\u4e3acsv\u6587\u4ef6 |\n| [examples/remove_image_background_demo.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background_demo.py) | \u5b9e\u73b0\u4e86\u81ea\u52a8\u53bb\u9664\u56fe\u7247\u80cc\u666f\u529f\u80fd\uff0c\u5305\u62ec\u81ea\u52a8\u901a\u8fc7pip\u5b89\u88c5\u5e93\uff0c\u8c03\u7528\u5e93\u5b9e\u73b0\u53bb\u9664\u56fe\u7247\u80cc\u666f |\n| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py) | \u5b9e\u73b0\u4e86\u81ea\u52a8\u8bad\u7ec3\u5206\u7c7b\u6a21\u578b\u7684\u5de5\u4f5c\u6d41\uff1a\u8bfb\u53d6\u8bad\u7ec3\u96c6\u6587\u4ef6\u5e76\u7406\u89e3\u683c\u5f0f - \u8c37\u6b4c\u641c\u7d22pytextclassifier\u5e93 - \u722c\u53d6github\u9875\u9762\u4e86\u89e3pytextclassifier\u7684\u8c03\u7528\u65b9\u6cd5 - \u5199\u4ee3\u7801\u5e76\u6267\u884cfasttext\u6a21\u578b\u8bad\u7ec3 - check\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u9884\u6d4b\u7ed3\u679c |\n| [examples/llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/llm_os_demo.py) | \u5b9e\u73b0\u4e86LLM OS\u7684\u521d\u6b65\u8bbe\u8ba1\uff0c\u57fa\u4e8eLLM\u8bbe\u8ba1\u64cd\u4f5c\u7cfb\u7edf\uff0c\u53ef\u4ee5\u901a\u8fc7LLM\u8c03\u7528RAG\u3001\u4ee3\u7801\u6267\u884c\u5668\u3001Shell\u7b49\u5de5\u5177\uff0c\u5e76\u534f\u540c\u4ee3\u7801\u89e3\u91ca\u5668\u3001\u7814\u7a76\u52a9\u624b\u3001\u6295\u8d44\u52a9\u624b\u7b49\u6765\u89e3\u51b3\u95ee\u9898\u3002 |\n| [examples/workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_write_novel_demo.py) | \u5b9e\u73b0\u4e86\u5199\u5c0f\u8bf4\u7684\u5de5\u4f5c\u6d41\uff1a\u5b9a\u5c0f\u8bf4\u63d0\u7eb2 - \u641c\u7d22\u8c37\u6b4c\u53cd\u601d\u63d0\u7eb2 - \u64b0\u5199\u5c0f\u8bf4\u5185\u5bb9 - \u4fdd\u5b58\u4e3amd\u6587\u4ef6 |\n| [examples/workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_write_tutorial_demo.py) | \u5b9e\u73b0\u4e86\u5199\u6280\u672f\u6559\u7a0b\u7684\u5de5\u4f5c\u6d41\uff1a\u5b9a\u6559\u7a0b\u76ee\u5f55 - \u53cd\u601d\u76ee\u5f55\u5185\u5bb9 - \u64b0\u5199\u6559\u7a0b\u5185\u5bb9 - \u4fdd\u5b58\u4e3amd\u6587\u4ef6 |\n| [examples/self_evolving_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/self_evolving_agent_demo.py) | \u5b9e\u73b0\u4e86\u57fa\u4e8e\u957f\u671f\u8bb0\u5fc6\u7684\u81ea\u6211\u8fdb\u5316\u667a\u80fd\u4f53\uff0c\u53ef\u4ee5\u57fa\u4e8e\u5386\u53f2\u95ee\u7b54\u4fe1\u606f\u81ea\u6211\u8c03\u6574\u51b3\u7b56 |\n\n\n### LLM OS\nThe LLM OS design:\n\n<img alt=\"LLM OS\" src=\"https://github.com/shibing624/agentica/blob/main/docs/llmos.png\" width=\"800\" />\n\n#### Run the LLM OS App\n\n```shell\ncd examples\nstreamlit run llm_os_demo.py\n```\n\n<img alt=\"LLM OS\" src=\"https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png\" width=\"800\" />\n\n### Self-evolving Agent\nThe self-evolving agent design:\n\n<img alt=\"LLM OS\" src=\"https://github.com/shibing624/agentica/blob/main/docs/sage_arch.png\" width=\"800\" />\n\n#### Feature\n\n\u5177\u6709\u53cd\u601d\u548c\u589e\u5f3a\u8bb0\u5fc6\u80fd\u529b\u7684\u81ea\u6211\u8fdb\u5316\u667a\u80fd\u4f53(self-evolving Agents with Reflective and Memory-augmented Abilities, SAGE)\n\n\u5b9e\u73b0\u65b9\u6cd5:\n\n1. \u4f7f\u7528PythonAssistant\u4f5c\u4e3aSAGE\u667a\u80fd\u4f53\uff0c\u4f7f\u7528AzureOpenAILLM\u4f5c\u4e3aLLM, \u5177\u5907code-interpreter\u529f\u80fd\uff0c\u53ef\u4ee5\u6267\u884cPython\u4ee3\u7801\uff0c\u5e76\u81ea\u52a8\u7ea0\u9519\u3002\n2. \u4f7f\u7528CsvMemoryDb\u4f5c\u4e3aSAGE\u667a\u80fd\u4f53\u7684\u8bb0\u5fc6\uff0c\u7528\u4e8e\u5b58\u50a8\u7528\u6237\u7684\u95ee\u9898\u548c\u7b54\u6848\uff0c\u4e0b\u6b21\u9047\u5230\u76f8\u4f3c\u7684\u95ee\u9898\u65f6\uff0c\u53ef\u4ee5\u76f4\u63a5\u8fd4\u56de\u7b54\u6848\u3002\n\n#### Run Self-evolving Agent App\n\n```shell\ncd examples\nstreamlit run self_evolving_agent_demo.py\n```\n\n<img alt=\"sage_snap\" src=\"https://github.com/shibing624/agentica/blob/main/docs/sage_snap.png\" width=\"800\" />\n\n\n## Contact\n\n- Issue(\u5efa\u8bae)\n \uff1a[](https://github.com/shibing624/agentica/issues)\n- \u90ae\u4ef6\u6211\uff1axuming: xuming624@qq.com\n- \u5fae\u4fe1\u6211\uff1a \u52a0\u6211*\u5fae\u4fe1\u53f7\uff1axuming624, \u5907\u6ce8\uff1a\u59d3\u540d-\u516c\u53f8-NLP* \u8fdbNLP\u4ea4\u6d41\u7fa4\u3002\n\n<img src=\"https://github.com/shibing624/agentica/blob/main/docs/wechat.jpeg\" width=\"200\" />\n\n## Citation\n\n\u5982\u679c\u4f60\u5728\u7814\u7a76\u4e2d\u4f7f\u7528\u4e86`agentica`\uff0c\u8bf7\u6309\u5982\u4e0b\u683c\u5f0f\u5f15\u7528\uff1a\n\nAPA:\n\n```\nXu, M. agentica: A Human-Centric Framework for Large Language Model Agent Workflows (Version 0.0.2) [Computer software]. https://github.com/shibing624/agentica\n```\n\nBibTeX:\n\n```\n@misc{Xu_agentica,\n title={agentica: A Human-Centric Framework for Large Language Model Agent Workflows},\n author={Xu Ming},\n year={2024},\n howpublished={\\url{https://github.com/shibing624/agentica}},\n}\n```\n\n## License\n\n\u6388\u6743\u534f\u8bae\u4e3a [The Apache License 2.0](/LICENSE)\uff0c\u53ef\u514d\u8d39\u7528\u505a\u5546\u4e1a\u7528\u9014\u3002\u8bf7\u5728\u4ea7\u54c1\u8bf4\u660e\u4e2d\u9644\u52a0`agentica`\u7684\u94fe\u63a5\u548c\u6388\u6743\u534f\u8bae\u3002\n## Contribute\n\n\u9879\u76ee\u4ee3\u7801\u8fd8\u5f88\u7c97\u7cd9\uff0c\u5982\u679c\u5927\u5bb6\u5bf9\u4ee3\u7801\u6709\u6240\u6539\u8fdb\uff0c\u6b22\u8fce\u63d0\u4ea4\u56de\u672c\u9879\u76ee\uff0c\u5728\u63d0\u4ea4\u4e4b\u524d\uff0c\u6ce8\u610f\u4ee5\u4e0b\u4e24\u70b9\uff1a\n\n- \u5728`tests`\u6dfb\u52a0\u76f8\u5e94\u7684\u5355\u5143\u6d4b\u8bd5\n- \u4f7f\u7528`python -m pytest`\u6765\u8fd0\u884c\u6240\u6709\u5355\u5143\u6d4b\u8bd5\uff0c\u786e\u4fdd\u6240\u6709\u5355\u6d4b\u90fd\u662f\u901a\u8fc7\u7684\n\n\u4e4b\u540e\u5373\u53ef\u63d0\u4ea4PR\u3002\n\n## Acknowledgements \n\n- [https://github.com/langchain-ai/langchain](https://github.com/langchain-ai/langchain)\n- [https://github.com/simonmesmith/agentflow](https://github.com/simonmesmith/agentflow)\n- [https://github.com/phidatahq/phidata](https://github.com/phidatahq/phidata)\n\n\nThanks for their great work!\n",
"bugtrack_url": null,
"license": "Apache License 2.0",
"summary": "LLM agents",
"version": "0.1.8",
"project_urls": {
"Homepage": "https://github.com/shibing624/agentica"
},
"split_keywords": [
"agentica",
" agent tool",
" action",
" agent",
" agentica"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "94538f2f794124f9e8e54c924bf4efab196773646525075c03938d8d2453ebfe",
"md5": "9d05ebb5c07637e537a2e467cda5b245",
"sha256": "61be8d6a87c95acda00ea6f98f99848d60a9d4bf6214cfeebfcbe991323d4821"
},
"downloads": -1,
"filename": "agentica-0.1.8.tar.gz",
"has_sig": false,
"md5_digest": "9d05ebb5c07637e537a2e467cda5b245",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.0",
"size": 119823,
"upload_time": "2024-09-24T10:31:47",
"upload_time_iso_8601": "2024-09-24T10:31:47.358389Z",
"url": "https://files.pythonhosted.org/packages/94/53/8f2f794124f9e8e54c924bf4efab196773646525075c03938d8d2453ebfe/agentica-0.1.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-24 10:31:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "shibing624",
"github_project": "agentica",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "agentica"
}
JSON
