agentica 0.1.8__tar.gz → 0.2.0__tar.gz

agentica-0.2.0/PKG-INFO

@@ -0,0 +1,275 @@
+Metadata-Version: 2.1
+Name: agentica
+Version: 0.2.0
+Summary: LLM agents
+Home-page: https://github.com/shibing624/agentica
+Author: XuMing
+Author-email: xuming624@qq.com
+License: Apache License 2.0
+Keywords: Agentica,Agent Tool,action,agent,agentica
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: loguru
+Requires-Dist: markdownify
+Requires-Dist: openai
+Requires-Dist: python-dotenv
+Requires-Dist: pydantic
+Requires-Dist: requests
+Requires-Dist: sqlalchemy
+Requires-Dist: scikit-learn
+Requires-Dist: tqdm
+Requires-Dist: rich
+
+[**🇨🇳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
+[![PyPI version](https://badge.fury.io/py/agentica.svg)](https://badge.fury.io/py/agentica)
+[![Downloads](https://static.pepy.tech/badge/agentica)](https://pepy.tech/project/agentica)
+[![Contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg)](CONTRIBUTING.md)
+[![License Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
+[![python_version](https://img.shields.io/badge/Python-3.5%2B-green.svg)](requirements.txt)
+[![GitHub issues](https://img.shields.io/github/issues/shibing624/agentica.svg)](https://github.com/shibing624/agentica/issues)
+[![Wechat Group](https://img.shields.io/badge/wechat-group-green.svg?logo=wechat)](#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
+
+#### 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_moonshot_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)。或者使用`export`命令设置环境变量：
+    
+    ```shell
+    export MOONSHOT_API_KEY=your_moonshot_api_key
+    export SERPER_API_KEY=your_serper_api_key
+    ```
+
+2. 使用`agentica`构建Agent并执行：
+
+自动调用google搜索工具，示例[examples/web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/web_search_moonshot_demo.py)
+
+```python
+from agentica import Agent, MoonshotChat, SearchSerperTool
+
+m = Agent(model=MoonshotChat(), tools=[SearchSerperTool()], add_datetime_to_instructions=True)
+r = m.run("下一届奥运会在哪里举办")
+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/01_llm_demo.py](https://github.com/shibing624/agentica/blob/main/examples/01_llm_demo.py)                                                   | LLM问答Demo                                                                                                                         |
+| [examples/02_user_prompt_demo.py](https://github.com/shibing624/agentica/blob/main/examples/02_user_prompt_demo.py)                                   | 自定义用户prompt的Demo                                                                                                                  |
+| [examples/03_user_messages_demo.py](https://github.com/shibing624/agentica/blob/main/examples/03_user_messages_demo.py)                               | 自定义输入用户消息的Demo                                                                                                                    |
+| [examples/04_memory_demo.py](https://github.com/shibing624/agentica/blob/main/examples/04_memory_demo.py)                                             | Agent的记忆Demo                                                                                                                      |
+| [examples/05_response_model_demo.py](https://github.com/shibing624/agentica/blob/main/examples/05_response_model_demo.py)                             | 按指定格式（pydantic的BaseModel）回复的Demo                                                                                                  |
+| [examples/06_calc_with_csv_file_demo.py](https://github.com/shibing624/agentica/blob/main/examples/06_calc_with_csv_file_demo.py)                     | LLM加载CSV文件，并执行计算来回答的Demo                                                                                                          |
+| [examples/07_create_image_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/07_create_image_tool_demo.py)                       | 实现了创建图像工具的Demo                                                                                                                    |
+| [examples/08_ocr_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/08_ocr_tool_demo.py)                                         | 实现了OCR工具的Demo                                                                                                                     |
+| [examples/09_remove_image_background_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/09_remove_image_background_tool_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/10_vision_demo.py](https://github.com/shibing624/agentica/blob/main/examples/10_vision_demo.py)                                             | 视觉理解Demo                                                                                                                          |
+| [examples/11_web_search_openai_demo.py](https://github.com/shibing624/agentica/blob/main/examples/11_web_search_openai_demo.py)                       | 基于OpenAI的function call做网页搜索Demo                                                                                                   |
+| [examples/12_web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/12_web_search_moonshot_demo.py)                   | 基于Moonshot的function call做网页搜索Demo                                                                                                 |
+| [examples/13_storage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/13_storage_demo.py)                                           | Agent的存储Demo                                                                                                                      |
+| [examples/14_custom_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/14_custom_tool_demo.py)                                   | 自定义工具，并用大模型自主选择调用的Demo                                                                                                            |
+| [examples/15_crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/15_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 - 汇总存为md文件                                                                             |
+| [examples/16_get_top_papers_demo.py](https://github.com/shibing624/agentica/blob/main/examples/16_get_top_papers_demo.py)                             | 解析每日论文，并保存为json格式的Demo                                                                                                            |
+| [examples/17_find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/17_find_paper_from_arxiv_demo.py)               | 实现了论文推荐的Demo：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/18_agent_input_is_list.py](https://github.com/shibing624/agentica/blob/main/examples/18_agent_input_is_list.py)                             | 展示Agent的message可以是列表的Demo                                                                                                         |
+| [examples/19_naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/19_naive_rag_demo.py)                                       | 实现了基础版RAG，基于Txt文档回答问题                                                                                                             |
+| [examples/20_advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/20_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+语义多路混合召回，召回排序（rerank）                                                               |
+| [examples/21_memorydb_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/21_reference_in_prompt_rag_demo.py)                      | 把参考资料放到prompt的传统RAG做法的Demo                                                                                                        |
+| [examples/22_chat_pdf_app_demo.py](https://github.com/shibing624/agentica/blob/main/examples/22_chat_pdf_app_demo.py)                                 | 对PDF文档做深入对话的Demo                                                                                                                  |
+| [examples/23_python_agent_memory_demo.py](https://github.com/shibing624/agentica/blob/main/examples/23_python_agent_memory_demo.py)                   | 实现了带记忆的Code Interpreter功能，自动生成python代码并执行，下次执行时从记忆获取结果                                                                            |
+| [examples/24_context_demo.py](https://github.com/shibing624/agentica/blob/main/examples/24_context_demo.py)                                           | 实现了传入上下文进行对话的Demo                                                                                                                 |
+| [examples/25_tools_with_context_demo.py](https://github.com/shibing624/agentica/blob/main/examples/25_tools_with_context_demo.py)                     | 工具带上下文传参的Demo                                                                                                                     |
+| [examples/26_complex_translate_demo.py](https://github.com/shibing624/agentica/blob/main/examples/26_complex_translate_demo.py)                       | 实现了复杂翻译Demo                                                                                                                       |
+| [examples/27_research_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/27_research_agent_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/28_rag_integrated_langchain_demo.py](https://github.com/shibing624/agentica/blob/main/examples/28_rag_integrated_langchain_demo.py)         | 集成LangChain的RAG Demo                                                                                                              |
+| [examples/29_rag_integrated_llamaindex_demo.py](https://github.com/shibing624/agentica/blob/main/examples/29_rag_integrated_llamaindex_demo.py)       | 集成LlamaIndex的RAG Demo                                                                                                             |
+| [examples/30_text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/30_text_classification_demo.py)                   | 实现了自动训练分类模型的Agent：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/31_team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/31_team_news_article_demo.py)                       | Team实现：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/32_team_debate_demo.py](https://github.com/shibing624/agentica/blob/main/examples/32_team_debate_demo.py)                                   | Team实现：基于委托做双人辩论Demo，特朗普和拜登辩论                                                                                                     |
+| [examples/33_self_evolving_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/33_self_evolving_agent_demo.py)                   | 实现了自我进化Agent的Demo                                                                                                                 |
+| [examples/34_llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/34_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/35_workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/35_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/36_workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/36_workflow_news_article_demo.py)               | 实现了写新闻稿的工作流，multi-agent的实现，多次调用搜索工具，并生成高级排版的新闻文章                                                                                  |
+| [examples/37_workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/37_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/38_workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/38_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/39_audio_multi_turn_demo.py](https://github.com/shibing624/agentica/blob/main/examples/39_audio_multi_turn_demo.py)                         | 基于openai的语音api做多轮音频对话的Demo                                                                                                        |
+
+
+### 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PythonAgent作为SAGE智能体，使用AzureOpenAIChat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 33_self_evolving_agent_demo.py
+```
+
+<img alt="sage_snap" src="https://github.com/shibing624/agentica/blob/main/docs/sage_snap.png" width="800" />
+
+
+### 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 34_llm_os_demo.py
+```
+
+<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png" width="800" />
+
+## Contact
+
+- Issue(建议)
+  ：[![GitHub issues](https://img.shields.io/github/issues/shibing624/agentica.svg)](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!

agentica-0.2.0/README.md

@@ -0,0 +1,244 @@
+[**🇨🇳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
+[![PyPI version](https://badge.fury.io/py/agentica.svg)](https://badge.fury.io/py/agentica)
+[![Downloads](https://static.pepy.tech/badge/agentica)](https://pepy.tech/project/agentica)
+[![Contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg)](CONTRIBUTING.md)
+[![License Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)
+[![python_version](https://img.shields.io/badge/Python-3.5%2B-green.svg)](requirements.txt)
+[![GitHub issues](https://img.shields.io/github/issues/shibing624/agentica.svg)](https://github.com/shibing624/agentica/issues)
+[![Wechat Group](https://img.shields.io/badge/wechat-group-green.svg?logo=wechat)](#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
+
+#### 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_moonshot_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)。或者使用`export`命令设置环境变量：
+    
+    ```shell
+    export MOONSHOT_API_KEY=your_moonshot_api_key
+    export SERPER_API_KEY=your_serper_api_key
+    ```
+
+2. 使用`agentica`构建Agent并执行：
+
+自动调用google搜索工具，示例[examples/web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/web_search_moonshot_demo.py)
+
+```python
+from agentica import Agent, MoonshotChat, SearchSerperTool
+
+m = Agent(model=MoonshotChat(), tools=[SearchSerperTool()], add_datetime_to_instructions=True)
+r = m.run("下一届奥运会在哪里举办")
+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/01_llm_demo.py](https://github.com/shibing624/agentica/blob/main/examples/01_llm_demo.py)                                                   | LLM问答Demo                                                                                                                         |
+| [examples/02_user_prompt_demo.py](https://github.com/shibing624/agentica/blob/main/examples/02_user_prompt_demo.py)                                   | 自定义用户prompt的Demo                                                                                                                  |
+| [examples/03_user_messages_demo.py](https://github.com/shibing624/agentica/blob/main/examples/03_user_messages_demo.py)                               | 自定义输入用户消息的Demo                                                                                                                    |
+| [examples/04_memory_demo.py](https://github.com/shibing624/agentica/blob/main/examples/04_memory_demo.py)                                             | Agent的记忆Demo                                                                                                                      |
+| [examples/05_response_model_demo.py](https://github.com/shibing624/agentica/blob/main/examples/05_response_model_demo.py)                             | 按指定格式（pydantic的BaseModel）回复的Demo                                                                                                  |
+| [examples/06_calc_with_csv_file_demo.py](https://github.com/shibing624/agentica/blob/main/examples/06_calc_with_csv_file_demo.py)                     | LLM加载CSV文件，并执行计算来回答的Demo                                                                                                          |
+| [examples/07_create_image_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/07_create_image_tool_demo.py)                       | 实现了创建图像工具的Demo                                                                                                                    |
+| [examples/08_ocr_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/08_ocr_tool_demo.py)                                         | 实现了OCR工具的Demo                                                                                                                     |
+| [examples/09_remove_image_background_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/09_remove_image_background_tool_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/10_vision_demo.py](https://github.com/shibing624/agentica/blob/main/examples/10_vision_demo.py)                                             | 视觉理解Demo                                                                                                                          |
+| [examples/11_web_search_openai_demo.py](https://github.com/shibing624/agentica/blob/main/examples/11_web_search_openai_demo.py)                       | 基于OpenAI的function call做网页搜索Demo                                                                                                   |
+| [examples/12_web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/12_web_search_moonshot_demo.py)                   | 基于Moonshot的function call做网页搜索Demo                                                                                                 |
+| [examples/13_storage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/13_storage_demo.py)                                           | Agent的存储Demo                                                                                                                      |
+| [examples/14_custom_tool_demo.py](https://github.com/shibing624/agentica/blob/main/examples/14_custom_tool_demo.py)                                   | 自定义工具，并用大模型自主选择调用的Demo                                                                                                            |
+| [examples/15_crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/15_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 - 汇总存为md文件                                                                             |
+| [examples/16_get_top_papers_demo.py](https://github.com/shibing624/agentica/blob/main/examples/16_get_top_papers_demo.py)                             | 解析每日论文，并保存为json格式的Demo                                                                                                            |
+| [examples/17_find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/17_find_paper_from_arxiv_demo.py)               | 实现了论文推荐的Demo：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/18_agent_input_is_list.py](https://github.com/shibing624/agentica/blob/main/examples/18_agent_input_is_list.py)                             | 展示Agent的message可以是列表的Demo                                                                                                         |
+| [examples/19_naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/19_naive_rag_demo.py)                                       | 实现了基础版RAG，基于Txt文档回答问题                                                                                                             |
+| [examples/20_advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/20_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+语义多路混合召回，召回排序（rerank）                                                               |
+| [examples/21_memorydb_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/21_reference_in_prompt_rag_demo.py)                      | 把参考资料放到prompt的传统RAG做法的Demo                                                                                                        |
+| [examples/22_chat_pdf_app_demo.py](https://github.com/shibing624/agentica/blob/main/examples/22_chat_pdf_app_demo.py)                                 | 对PDF文档做深入对话的Demo                                                                                                                  |
+| [examples/23_python_agent_memory_demo.py](https://github.com/shibing624/agentica/blob/main/examples/23_python_agent_memory_demo.py)                   | 实现了带记忆的Code Interpreter功能，自动生成python代码并执行，下次执行时从记忆获取结果                                                                            |
+| [examples/24_context_demo.py](https://github.com/shibing624/agentica/blob/main/examples/24_context_demo.py)                                           | 实现了传入上下文进行对话的Demo                                                                                                                 |
+| [examples/25_tools_with_context_demo.py](https://github.com/shibing624/agentica/blob/main/examples/25_tools_with_context_demo.py)                     | 工具带上下文传参的Demo                                                                                                                     |
+| [examples/26_complex_translate_demo.py](https://github.com/shibing624/agentica/blob/main/examples/26_complex_translate_demo.py)                       | 实现了复杂翻译Demo                                                                                                                       |
+| [examples/27_research_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/27_research_agent_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/28_rag_integrated_langchain_demo.py](https://github.com/shibing624/agentica/blob/main/examples/28_rag_integrated_langchain_demo.py)         | 集成LangChain的RAG Demo                                                                                                              |
+| [examples/29_rag_integrated_llamaindex_demo.py](https://github.com/shibing624/agentica/blob/main/examples/29_rag_integrated_llamaindex_demo.py)       | 集成LlamaIndex的RAG Demo                                                                                                             |
+| [examples/30_text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/30_text_classification_demo.py)                   | 实现了自动训练分类模型的Agent：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/31_team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/31_team_news_article_demo.py)                       | Team实现：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/32_team_debate_demo.py](https://github.com/shibing624/agentica/blob/main/examples/32_team_debate_demo.py)                                   | Team实现：基于委托做双人辩论Demo，特朗普和拜登辩论                                                                                                     |
+| [examples/33_self_evolving_agent_demo.py](https://github.com/shibing624/agentica/blob/main/examples/33_self_evolving_agent_demo.py)                   | 实现了自我进化Agent的Demo                                                                                                                 |
+| [examples/34_llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/34_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/35_workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/35_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/36_workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/36_workflow_news_article_demo.py)               | 实现了写新闻稿的工作流，multi-agent的实现，多次调用搜索工具，并生成高级排版的新闻文章                                                                                  |
+| [examples/37_workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/37_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/38_workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/38_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/39_audio_multi_turn_demo.py](https://github.com/shibing624/agentica/blob/main/examples/39_audio_multi_turn_demo.py)                         | 基于openai的语音api做多轮音频对话的Demo                                                                                                        |
+
+
+### 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PythonAgent作为SAGE智能体，使用AzureOpenAIChat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 33_self_evolving_agent_demo.py
+```
+
+<img alt="sage_snap" src="https://github.com/shibing624/agentica/blob/main/docs/sage_snap.png" width="800" />
+
+
+### 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 34_llm_os_demo.py
+```
+
+<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png" width="800" />
+
+## Contact
+
+- Issue(建议)
+  ：[![GitHub issues](https://img.shields.io/github/issues/shibing624/agentica.svg)](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!

agentica-0.2.0/agentica/__init__.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+"""
+@author:XuMing(xuming624@qq.com)
+@description: 
+"""
+from agentica.version import __version__  # noqa, isort: skip
+from agentica.config import (
+    AGENTICA_HOME,
+    AGENTICA_DOTENV_PATH,
+    AGENTICA_LOG_LEVEL,
+    AGENTICA_LOG_FILE,
+)  # noqa, isort: skip
+from agentica.utils.log import set_log_level_to_debug, logger
+from agentica.utils.io import write_audio_to_file
+# model
+from agentica.model.openai.chat import OpenAIChat
+from agentica.model.azure.openai_chat import AzureOpenAIChat
+from agentica.model.moonshot import MoonshotChat
+from agentica.model.deepseek.chat import DeepSeekChat
+from agentica.model.doubao.chat import DoubaoChat
+from agentica.model.together.togetherchat import TogetherChat
+from agentica.model.xai.grok import GrokChat
+from agentica.model.yi.chat import YiChat
+
+# memory
+from agentica.model.base import Model, Message
+from agentica.memory import (
+    Memory,
+    MemoryRetrieval,
+    MemoryClassifier,
+    MemoryManager,
+    AgentMemory,
+    WorkflowMemory,
+)
+from agentica.memorydb import MemoryDb, CsvMemoryDb, InMemoryDb, SqliteMemoryDb, PgMemoryDb, MemoryRow
+from agentica.template import PromptTemplate
+# rag
+from agentica.run_response import (
+    RunResponse,
+    RunEvent,
+    RunResponseExtraData,
+    pprint_run_response,
+)
+from agentica.knowledge.base import Knowledge
+from agentica.document import Document
+# vectordb
+from agentica.vectordb.base import SearchType, Distance, VectorDb
+from agentica.vectordb.memory_vectordb import MemoryVectorDb
+# emb
+from agentica.emb.base import Emb
+from agentica.emb.openai_emb import OpenAIEmb
+from agentica.emb.azure_openai_emb import AzureOpenAIEmb
+from agentica.emb.hash_emb import HashEmb
+from agentica.emb.ollama_emb import OllamaEmb
+from agentica.emb.together_emb import TogetherEmb
+from agentica.emb.fireworks_emb import FireworksEmb
+
+# file
+from agentica.file.base import File
+from agentica.file.csv import CsvFile
+from agentica.file.txt import TextFile
+
+# storage
+from agentica.storage.agent.base import AgentStorage
+from agentica.storage.agent.postgres import PgAgentStorage
+from agentica.storage.agent.sqlite import SqlAgentStorage
+from agentica.storage.agent.json_file import JsonFileAgentStorage
+from agentica.storage.agent.yaml_file import YamlFileAgentStorage
+from agentica.storage.workflow.base import WorkflowStorage
+from agentica.storage.workflow.sqlite import SqlWorkflowStorage
+from agentica.storage.workflow.postgres import PgWorkflowStorage
+
+# tool
+from agentica.tools.base import Tool, Toolkit, Function, FunctionCall
+from agentica.tools.search_serper_tool import SearchSerperTool
+from agentica.tools.run_python_code_tool import RunPythonCodeTool
+from agentica.tools.analyze_image_tool import AnalyzeImageTool
+from agentica.tools.calculator_tool import CalculatorTool
+from agentica.tools.create_image_tool import CreateImageTool
+from agentica.tools.file_tool import FileTool
+from agentica.tools.hackernews_tool import HackerNewsTool
+from agentica.tools.jina_tool import JinaTool
+from agentica.tools.shell_tool import ShellTool
+from agentica.tools.text_analysis_tool import TextAnalysisTool
+
+# agent
+from agentica.agent import Agent
+from agentica.agent_session import AgentSession
+from agentica.python_agent import PythonAgent
+from agentica.workflow import Workflow
+from agentica.workflow_session import WorkflowSession