The main contributor of this repo is a Master's student graduating in 2026, currently on the job market. Feel free to reach out for collaboration or job opportunities.

本仓库的主要贡献者是一名 2026 届硕士毕业生，正在求职中，欢迎联系。

• [2026/01]: We support freeform and template generation support PPTX export, offline mode now! .
• [2025/12]: 🔥 Released V2 with major improvements - Deep Research Integration, Free-Form Visual Design, Autonomous Asset Creation, Text-to-Image Generation, and Agent Environment with sandbox & 20+ tools.
• [2025/09]: 🛠️ MCP server support added - see MCP Server for configuration details
• [2025/09]: 🚀 Released v2 with major improvements - see release notes for details
• [2025/08]: 🎉 Paper accepted to EMNLP 2025!
• [2025/05]: ✨ Released v1 with core functionality and 🌟 breakthrough: reached 1,000 stars on GitHub! - see release notes for details
• [2025/01]: 🔓 Open-sourced the codebase, with experimental code archived at experiment release

• Agent sandbox (Docker): Build the sandbox image using the provided Dockerfile:

  bash deeppresenter/docker/build.sh

• MinerU: Apply for an API key at mineru.net. Note that each key is valid for 14 days.

• Tavily (optional): Apply for an API key at tavily.com.

• LLM: Copy deeppresenter/deeppresenter/config.yaml.example to deeppresenter/deeppresenter/config.yaml, then set your model endpoint, API keys, and related parameters.

• MCP server: Copy deeppresenter/deeppresenter/mcp.json.example to deeppresenter/deeppresenter/mcp.json, then configure the MCP server.

• Additional tools:

  pip install playwright
  playwright install-deps
  playwright install chromium
  npm install
  npx playwright install chromium

• MinerU: Deploy the MinerU server by following the instructions at MinerU docker guide
• Config switch: Set offline_mode: true in config.yaml to avoid loading network-dependent tools (e.g., research, fetch, search).
• MinerU endpoint: Set MINERU_API_URL in mcp.json to your local MinerU service URL

From the project root directory, run:

pip install -e deeppresenter

Also from the project root directory, run:

python webui.py

• Prompt: Please present the given document to me.

• Prompt: 请介绍小米 SU7 的外观和价格

• Prompt: 请制作一份高中课堂展示课件，主题为“解码立法过程：理解其对国际关系的影响”

If you find this project helpful, please use the following to cite it:

@inproceedings{zheng-etal-2025-pptagent,
    title = "{PPTA}gent: Generating and Evaluating Presentations Beyond Text-to-Slides",
    author = "Zheng, Hao  and
      Guan, Xinyan  and
      Kong, Hao  and
      Zhang, Wenkai  and
      Zheng, Jia  and
      Zhou, Weixiang  and
      Lin, Hongyu  and
      Lu, Yaojie  and
      Han, Xianpei  and
      Sun, Le",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.728/",
    doi = "10.18653/v1/2025.emnlp-main.728",
    pages = "14413--14429",
    ISBN = "979-8-89176-332-6",
    abstract = "Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PPTAgent significantly outperforms existing automatic presentation generation methods across all three dimensions."
}