Preparation for installation
- 安装Python 3.8或更高版本
- 安装Git工具用于克隆仓库
- 安装vLLM（建议0.5.5版本）以支持高效的模型推理
Detailed installation steps
- Cloning GitHub repositories:
git clone https://github.com/tablegpt/tablegpt-agent.git
cd tablegpt-agent - Install the dependency packages:
pip install -r requirements.txt - 如需完整功能，安装额外依赖：
pip install ".[local]"
Model deployment
需要从Hugging Face下载TableGPT2模型（如TableGPT2-7B），然后使用vLLM启动服务：python -m vllm.entrypoints.openai.api_server --served-model-name TableGPT2-7B --model path/to/weights
服务将默认监听http://localhost:8000。
Configuring the Agent
编辑代码或配置文件，将LLM的API地址指向vLLM服务：llm = ChatOpenAI(openai_api_base="http://localhost:8000/v1", openai_api_key="whatever", model_name="TableGPT2-7B")
This answer comes from the articleTableGPT Agent: Intelligent Tool Designed to Analyze Complex Tabular DataThe
May not be reproduced without permission:AI productivity tools " 如何安装和配置TableGPT Agent？
English 
简体中文 
日本語 
Deutsch 
Português do Brasil