LandPPT is an AI-powered platform for generating professional presentations from documents, targeting users who need to create high-quality slides efficiently. It automates the conversion of text-based content into structured presentations with AI-assisted image selection, deep research capabilities, and a rich template system, significantly reducing manual effort.

How It Works

The platform leverages a multi-stage workflow, starting with content ingestion from various document formats (PDF, Word, Markdown, TXT, Excel) using specialized parsers like MinerU and MarkItDown. It then integrates with multiple LLM providers (OpenAI, Anthropic, Google, Ollama) to generate presentation outlines and content. A key differentiator is its "deep research" functionality, which uses search APIs (Tavily, SearXNG) to gather up-to-date information, and an AI-driven image system that sources visuals from local libraries, web searches (Pixabay, Unsplash), or AI generation (DALL-E, SiliconFlow, Pollinations).

Quick Start & Requirements

• Installation: Clone the repository and use uv sync or pip install -e . for local setup. Docker deployment is also available.
• Prerequisites: Python 3.11+, SQLite. Optional: Docker, apryse-sdk for PPTX export.
• Configuration: Requires setting API keys for chosen AI providers, search engines, and image services via environment variables (.env file).
• Resources: Local deployment is supported, including with Ollama for local LLM models.
• Documentation: API docs available at /docs and /redoc after service startup.

Highlighted Details

• Supports a wide array of LLM providers including OpenAI (GPT-4o), Anthropic (Claude 3.5), Google (Gemini 1.5), and local Ollama models.
• Features an integrated AI image system for sourcing visuals from local, web, and generative AI sources.
• Includes "deep research" capabilities using Tavily and SearXNG for up-to-date information gathering.
• Offers multi-format export options including PDF, HTML, and PPTX (requires Apryse SDK).

Maintenance & Community

The project is maintained by the LandPPT Team. Community interaction is encouraged through GitHub Issues and Discussions.

Licensing & Compatibility

Licensed under the Apache License 2.0. This permissive license allows for commercial use and integration with closed-source projects.

Limitations & Caveats

PPTX export requires a separate license key for the Apryse SDK. Configuration of BASE_URL is necessary when using reverse proxies to ensure correct asset loading.