Metadata-Version: 2.1
Name: sz-researcher
Version: 0.7.4
Summary: sz-researcher是一款为中文研究而设计的自主智能体，适用于多种任务。
Home-page: https://github.com/yiouyou/sz-researcher
Author: Zack Song
Author-email: zhuosong@gmail.com
License: MIT
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: beautifulsoup4
Requires-Dist: colorama
Requires-Dist: duckduckgo-search (==5.3.1b1)
Requires-Dist: md2pdf
Requires-Dist: playwright
Requires-Dist: openai
Requires-Dist: python-dotenv
Requires-Dist: pyyaml
Requires-Dist: pydantic
Requires-Dist: python-multipart
Requires-Dist: markdown
Requires-Dist: langchain (<0.3,>=0.2)
Requires-Dist: langchain-community (<0.3,>=0.2)
Requires-Dist: langchain-openai (<0.2,>=0.1)
Requires-Dist: langchain-google-genai (<2,>=1)
Requires-Dist: langchain-groq (<0.2,>=0.1)
Requires-Dist: langchain-anthropic (<0.2,>=0.1)
Requires-Dist: langchain-mistralai (<0.2,>=0.1)
Requires-Dist: langchain-huggingface (<0.1,>=0.0.1)
Requires-Dist: langchain-together (<0.2,>=0.1)
Requires-Dist: langchain-cohere
Requires-Dist: langchain-google-vertexai
Requires-Dist: langchain-fireworks
Requires-Dist: langchain-aws
Requires-Dist: tiktoken
Requires-Dist: tavily-python
Requires-Dist: arxiv
Requires-Dist: PyMuPDF
Requires-Dist: requests
Requires-Dist: aiofiles
Requires-Dist: newspaper3k
Requires-Dist: SQLAlchemy
Requires-Dist: mistune
Requires-Dist: python-docx
Requires-Dist: htmldocx
Requires-Dist: lxml[html_clean]
Requires-Dist: websockets
Requires-Dist: unstructured
Requires-Dist: pandas
Requires-Dist: json-repair

# 🔎 sz-researcher

**sz-researcher是一款为中文研究而设计的自主智能体，适用于多种任务。**

该智能体能够生成详尽、真实、无偏见的研究报告，并提供定制选项，专注于相关资源、大纲和课程。受最近发布的[计划与解决](https://arxiv.org/abs/2305.04091)和[RAG](https://arxiv.org/abs/2005.11401)论文的启发，sz-researcher解决了速度、确定性和可靠性的问题，通过并行化智能体工作，而非同步操作，提供了更稳定的性能和更快的处理速度。

主要参考源自：[GPT Researcher](https://github.com/assafelovic/gpt-researcher)

**我们的使命是通过利用人工智能的力量，为个人和组织提供准确、无偏见、真实的信息。**

#### PIP软件包
> **步骤0** - 安装Python 3.11或更高版本。[点击这里](https://www.tutorialsteacher.com/python/install-python) 查看逐步指南。
> **步骤1** - 安装sz-researcher软件包 [PyPI页面](https://pypi.org/project/sz-researcher/)
```bash
$ pip install sz-researcher
```
> **步骤2** - 创建.env文件并填入您的OpenAI密钥和Tavily API密钥，或者直接导出它们
```bash
$ export OPENAI_API_KEY={您的OpenAI API密钥}
```
> **步骤3** - 在您自己的代码中开始使用sz-researcher，示例：
```python
from sz_researcher import SZResearcher
import asyncio

async def get_report(query: str, report_type: str) -> str:
    researcher = SZResearcher(query, report_type)
    report = await researcher.run()
    return report

if __name__ == "__main__":
    query = "北溪天然气管道是谁炸的？"
    report_type = "研究"

    report = asyncio.run(get_report(query, report_type))
    print(report)
```

