LandPPT

What it is

LandPPT is an AI-driven platform that converts topics or documents into editable PowerPoint presentations. It supports multiple AI providers, templates, image management, outline-driven workflow, and exports to formats including PDF, HTML, PPTX, images, DOCX, and Markdown. It also provides speech/audio generation options and an API-compatible interface for integration.

How it works

The project described features a four-stage AI workflow: demand confirmation, outline generation, task tracking, and PPT generation. It can fetch and summarize web information, integrate image sources, and generate slides in parallel. It supports editing via a side panel, generates speaker notes, and can export various formats. It exposes an API and supports OAuth/open authentication and multiple providers (OpenAI, Anthropic, Google, Azure, Ollama).

Getting started

Installation and run options include:

• "方式一：uv（推荐本地）" with commands:

git clone https://github.com/sligter/LandPPT.git
cd LandPPT

# 安装 uv（如未安装）
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

uv sync --extra dev
cp .env.example .env
# 编辑 .env，至少配置一个 AI API Key

# 默认 :8000，SQLite + 内存缓存
uv run python run.py

• "方式二：pip" with commands:

git clone https://github.com/sligter/LandPPT.git
cd LandPPT

python -m venv venv
# Windows: venv\Scripts\activate
# macOS / Linux: source venv/bin/activate

pip install -e .
cp .env.example .env
# 编辑 .env，配置 AI API Key

python run.py

• "方式三：Docker 单容器" with commands:

docker pull bradleylzh/landppt:latest

docker run -d \
  --name landppt \
  -p 8000:8000 \
  -v $(pwd)/.env:/app/.env \
  -v landppt_data:/app/data \
  -v landppt_uploads:/app/uploads \
  -v landppt_reports:/app/research_reports \
  -v landppt_cache:/app/temp \
  -v landppt_lib:/app/lib \
  bradleylzh/landppt:latest

docker logs -f landppt

• "方式四：Docker Compose（推荐生产）" with commands:

cp .env.example .env
# 至少配置：AI Key、SECRET_KEY、POSTGRES_PASSWORD

docker compose up -d
docker compose logs -f landppt

• 访问地址- Web 界面：http://localhost:8000

Prerequisites

Python 3.11+, SQLite by default, ffmpeg for video export, Docker optional.

配置与最小可跑

最小可跑示例在 README 中列出，需至少一个 AI 提供商及 AI Key 不同示例已给出。

其他要点

• 提供多 AI 提供商支持、深度研究、图像服务、模板和导出选项、并行生成等特性。
• 依赖项和能力边界强调需要 API Key、模型、图像服务、及可选的 Apryse license 用于标准 PPTX 导出。
• 公开发布的快速开始、配置和常见问题部分覆盖了环境配置、网络代理、调试与导出格式。