Getting Started

安装指南 / Getting Started

中英双语 | Bilingual: Chinese & English

---

中文

前置条件

组件	要求
Python	3.11+
PostgreSQL	16+ 并安装 PostGIS 3.4 扩展
Node.js	20+ (前端构建)
Google Cloud	Vertex AI 项目 或 Google AI API Key

方式一：Docker 部署（推荐）

git clone https://github.com/zhouning/gisdataagent.git
cd gisdataagent
cp .env.example data_agent/.env
# 编辑 data_agent/.env，填入你的数据库和 Google AI 凭据
docker-compose up -d
# 浏览器打开 http://localhost:8000
# 默认账号：admin / admin123

方式二：本地开发

git clone https://github.com/zhouning/gisdataagent.git
cd gisdataagent

# 创建虚拟环境
python -m venv .venv
# Windows: .venv\Scripts\activate
# Linux/Mac: source .venv/bin/activate
pip install -r requirements.txt

# 配置环境变量
cp .env.example data_agent/.env
# 编辑 data_agent/.env

# 数据库迁移（按顺序执行 30 个 SQL 脚本）
for f in data_agent/migrations/*.sql; do psql -U agent_user -d gis_agent -f "$f"; done

# 构建前端
cd frontend && npm install && npm run build && cd ..

# 启动
export PYTHONPATH=.
chainlit run data_agent/app.py -w

默认凭据

• 用户名：admin，密码：admin123（首次启动自动创建）
• 登录页支持在线注册新账号

下一步

• 环境变量参考 — 完整 .env 配置说明
• 首次使用教程 — 上传数据并运行首次分析

---

English

Prerequisites

Component	Requirement
Python	3.11+
PostgreSQL	16+ with PostGIS 3.4 extension
Node.js	20+ (frontend build)
Google Cloud	Vertex AI project or Google AI API Key

Option 1: Docker Deployment (Recommended)

git clone https://github.com/zhouning/gisdataagent.git
cd gisdataagent
cp .env.example data_agent/.env
# Edit data_agent/.env with your database and Google AI credentials
docker-compose up -d
# Open http://localhost:8000
# Default login: admin / admin123

Option 2: Local Development

git clone https://github.com/zhouning/gisdataagent.git
cd gisdataagent

# Create virtual environment
python -m venv .venv
# Windows: .venv\Scripts\activate
# Linux/Mac: source .venv/bin/activate
pip install -r requirements.txt

# Configure environment
cp .env.example data_agent/.env
# Edit data_agent/.env

# Run database migrations (30 SQL scripts in order)
for f in data_agent/migrations/*.sql; do psql -U agent_user -d gis_agent -f "$f"; done

# Build frontend
cd frontend && npm install && npm run build && cd ..

# Start
export PYTHONPATH=.
chainlit run data_agent/app.py -w

Default Credentials

• Username: admin, Password: admin123 (auto-seeded on first run)
• Self-registration available on the login page

Next Steps

• Environment Variables — Complete .env reference
• First Steps — Upload data and run your first analysis