PromtEngineer/localGPT 源码下载与部署教程

项目概述

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

项目地址

https://github.com/PromtEngineer/localGPT

项目页面预览

关键指标

• Stars：22038
• 主要语言：Python
• License：MIT License
• 最近更新：2025-10-02T03:35:22Z
• 默认分支：main

本站高速下载（国内可用）

• 源码压缩包下载：点击下载（本站镜像）
• SHA256：7d744b29b0d53330c7a9c2c19cc7f5250ea4204efbcbc7646d86d25f732e195d

安装部署要点（README 精选）

Option 1: Docker Deployment

# Clone the repository
git clone https://github.com/PromtEngineer/localGPT.git
cd localGPT

# Install Ollama locally (required even for Docker)
curl -fsSL https://ollama.ai/install.sh | sh
ollama pull qwen3:0.6b
ollama pull qwen3:8b

# Start Ollama
ollama serve

# Start with Docker (in a new terminal)
./start-docker.sh

# Access the application
open http://localhost:3000

Docker Management Commands:

# Check container status
docker compose ps

# View logs
docker compose logs -f

# Stop containers
./start-docker.sh stop

Detailed Installation

1. Install System Dependencies

Ubuntu/Debian:

sudo apt update
sudo apt install python3.8 python3-pip nodejs npm docker.io docker-compose

macOS:

brew install python@3.8 node npm docker docker-compose

Windows:

# Install Python 3.8+, Node.js, and Docker Desktop
# Then use PowerShell or WSL2

2. Install AI Models

Install Ollama (Recommended):

# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh

# Pull recommended models
ollama pull qwen3:0.6b          # Fast generation model
ollama pull qwen3:8b            # High-quality generation model

常用命令（从 README 提取）

git clone -b localgpt-v2 https://github.com/PromtEngineer/localGPT.git
cd localGPT

# Clone the repository
git clone https://github.com/PromtEngineer/localGPT.git
cd localGPT

# Install Ollama locally (required even for Docker)
curl -fsSL https://ollama.ai/install.sh | sh
ollama pull qwen3:0.6b
ollama pull qwen3:8b

# Start Ollama
ollama serve

# Start with Docker (in a new terminal)
./start-docker.sh

# Access the application
open http://localhost:3000

# Check container status
docker compose ps

# View logs
docker compose logs -f

# Stop containers
./start-docker.sh stop

通用部署说明（适用于大多数项目）

1. 下载源码并阅读 README
2. 安装依赖（pip/npm/yarn 等）
3. 配置环境变量（API Key、模型路径、数据库等）
4. 启动服务并测试访问
5. 上线建议：Nginx 反代 + HTTPS + 进程守护（systemd / pm2）

免责声明与版权说明

本文仅做开源项目整理与教程索引，源码版权归原作者所有，请遵循对应 License 合规使用。