<div align="right">
<details>
<summary >🌐 Language</summary>
<div>
<div align="center">
<a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=en">English</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=zh-CN">简体中文</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=zh-TW">繁體中文</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ja">日本語</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ko">한국어</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=hi">हिन्दी</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=th">ไทย</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=fr">Français</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=de">Deutsch</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=es">Español</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=it">Italiano</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ru">Русский</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=pt">Português</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=nl">Nederlands</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=pl">Polski</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ar">العربية</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=fa">فارسی</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=tr">Türkçe</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=vi">Tiếng Việt</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=id">Bahasa Indonesia</a>
| <a href="https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=as">অসমীয়া</
</div>
</div>
</details>
</div>
# PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
<p align="center">
📄 <a href="https://arxiv.org/abs/2501.03936" target="_blank">Paper</a> |
🤗 <a href="#open-source-" target="_blank">OpenSource</a> |
📝 <a href="./DOC.md" target="_blank">Documentation</a> |
<a href="https://deepwiki.com/icip-cas/PPTAgent" target="_blank"><img src="https://deepwiki.com/icon.png" alt="Ask DeepWiki"> DeepWiki</a> |
🙏 <a href="#citation-" target="_blank">Citation</a>
</p>
We present PPTAgent, an innovative system that automatically generates presentations from documents. Drawing inspiration from human presentation creation methods, our system employs a two-step process to ensure excellence in overall quality. Additionally, we introduce **PPTEval**, a comprehensive evaluation framework that assesses presentations across multiple dimensions.
> [!TIP]
> 🚀 Get started quickly with our pre-built Docker image - [See Docker instructions](DOC.md/#docker-)
## 📅 News
- [2025/09]: 🛠️ We support MCP server now, see [MCP Server](./DOC.md#mcp-server-) for details
- [2025/09]: 🚀 Released v2 with major improvements - see [release notes](https://github.com/icip-cas/PPTAgent/releases/tag/v0.2.0) 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](https://github.com/icip-cas/PPTAgent/releases/tag/v0.1.0) for details
- [2025/01]: 🔓 Open-sourced the codebase, with experimental code archived at [experiment release](https://github.com/icip-cas/PPTAgent/releases/tag/experiment)
## Open Source 🤗
We have released our model and data at [HuggingFace](https://huggingface.co/collections/ICIP/pptagent-68b80af43b4f4e0cb14d0bb2).
## Demo Video 🎥
https://github.com/user-attachments/assets/c3935a98-4d2b-4c46-9b36-e7c598d14863
## Distinctive Features ✨
- **Dynamic Content Generation**: Creates slides with seamlessly integrated text and images
- **Smart Reference Learning**: Leverages existing presentations without requiring manual annotation
- **Comprehensive Quality Assessment**: Evaluates presentations through multiple quality metrics
## Case Study 💡
- #### [Iphone 16 Pro](https://www.apple.com/iphone-16-pro/)
<div style="display: flex; flex-wrap: wrap; gap: 10px;">
<img src="resource/iphone16pro/0001.jpg" alt="图片1" width="200"/>
<img src="resource/iphone16pro/0002.jpg" alt="图片2" width="200"/>
<img src="resource/iphone16pro/0003.jpg" alt="图片3" width="200"/>
<img src="resource/iphone16pro/0004.jpg" alt="图片4" width="200"/>
<img src="resource/iphone16pro/0005.jpg" alt="图片5" width="200"/>
<img src="resource/iphone16pro/0006.jpg" alt="图片6" width="200"/>
<img src="resource/iphone16pro/0007.jpg" alt="图片7" width="200"/>
</div>
- #### [Build Effective Agents](https://www.anthropic.com/research/building-effective-agents)
<div style="display: flex; flex-wrap: wrap; gap: 10px;">
<img src="resource/build_effective_agents/0001.jpg" alt="图片1" width="200"/>
<img src="resource/build_effective_agents/0002.jpg" alt="图片2" width="200"/>
<img src="resource/build_effective_agents/0003.jpg" alt="图片3" width="200"/>
<img src="resource/build_effective_agents/0004.jpg" alt="图片4" width="200"/>
<img src="resource/build_effective_agents/0005.jpg" alt="图片5" width="200"/>
<img src="resource/build_effective_agents/0006.jpg" alt="图片6" width="200"/>
<img src="resource/build_effective_agents/0007.jpg" alt="图片7" width="200"/>
<img src="resource/build_effective_agents/0008.jpg" alt="图片8" width="200"/>
<img src="resource/build_effective_agents/0009.jpg" alt="图片9" width="200"/>
<img src="resource/build_effective_agents/0010.jpg" alt="图片10" width="200"/>
</div>
## PPTAgent 🤖
PPTAgent follows a two-phase approach:
1. **Analysis Phase**: Extracts and learns from patterns in reference presentations
2. **Generation Phase**: Develops structured outlines and produces visually cohesive slides
Our system's workflow is illustrated below:
## PPTEval ⚖️
PPTEval evaluates presentations across three dimensions:
- **Content**: Check the accuracy and relevance of the slides.
- **Design**: Assesses the visual appeal and consistency.
- **Coherence**: Ensures the logical flow of ideas.
The workflow of PPTEval is shown below:
<p align="center">
<img src="resource/fig3.jpg" alt="PPTEval Workflow" style="width:70%;"/>
</p>
## Citation 🙏
If you find this project helpful, please use the following to cite it:
```bibtex
@article{zheng2025pptagent,
title={PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides},
author={Zheng, Hao and Guan, Xinyan and Kong, Hao and Zheng, Jia and Zhou, Weixiang and Lin, Hongyu and Lu, Yaojie and He, Ben and Han, Xianpei and Sun, Le},
journal={arXiv preprint arXiv:2501.03936},
year={2025}
}
```
[](https://star-history.com/#icip-cas/PPTAgent&Date)
Raw data
{
"_id": null,
"home_page": null,
"name": "pptagent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "presentation, powerpoint, ppt, llm, ai, document-processing",
"author": null,
"author_email": "Hao Zheng <wszh712811@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/f0/2a/ace69eace520cffdda88dcd436f6d3e85c46952fbd5dd122941afa68e349/pptagent-0.2.14.tar.gz",
"platform": null,
"description": "<div align=\"right\">\n <details>\n <summary >\ud83c\udf10 Language</summary>\n <div>\n <div align=\"center\">\n <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=en\">English</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=zh-CN\">\u7b80\u4f53\u4e2d\u6587</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=zh-TW\">\u7e41\u9ad4\u4e2d\u6587</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ja\">\u65e5\u672c\u8a9e</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ko\">\ud55c\uad6d\uc5b4</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=hi\">\u0939\u093f\u0928\u094d\u0926\u0940</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=th\">\u0e44\u0e17\u0e22</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=fr\">Fran\u00e7ais</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=de\">Deutsch</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=es\">Espa\u00f1ol</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=it\">Italiano</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ru\">\u0420\u0443\u0441\u0441\u043a\u0438\u0439</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=pt\">Portugu\u00eas</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=nl\">Nederlands</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=pl\">Polski</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=ar\">\u0627\u0644\u0639\u0631\u0628\u064a\u0629</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=fa\">\u0641\u0627\u0631\u0633\u06cc</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=tr\">T\u00fcrk\u00e7e</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=vi\">Ti\u1ebfng Vi\u1ec7t</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=id\">Bahasa Indonesia</a>\n | <a href=\"https://openaitx.github.io/view.html?user=icip-cas&project=PPTAgent&lang=as\">\u0985\u09b8\u09ae\u09c0\u09af\u09bc\u09be</\n </div>\n </div>\n </details>\n</div>\n\n# PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides\n<p align=\"center\">\n \ud83d\udcc4 <a href=\"https://arxiv.org/abs/2501.03936\" target=\"_blank\">Paper</a> | \n \ud83e\udd17 <a href=\"#open-source-\" target=\"_blank\">OpenSource</a> | \n \ud83d\udcdd <a href=\"./DOC.md\" target=\"_blank\">Documentation</a> | \n <a href=\"https://deepwiki.com/icip-cas/PPTAgent\" target=\"_blank\"><img src=\"https://deepwiki.com/icon.png\" alt=\"Ask DeepWiki\"> DeepWiki</a> | \n \ud83d\ude4f <a href=\"#citation-\" target=\"_blank\">Citation</a>\n</p>\n\nWe present PPTAgent, an innovative system that automatically generates presentations from documents. Drawing inspiration from human presentation creation methods, our system employs a two-step process to ensure excellence in overall quality. Additionally, we introduce **PPTEval**, a comprehensive evaluation framework that assesses presentations across multiple dimensions.\n\n> [!TIP]\n> \ud83d\ude80 Get started quickly with our pre-built Docker image - [See Docker instructions](DOC.md/#docker-)\n\n## \ud83d\udcc5 News\n\n- [2025/09]: \ud83d\udee0\ufe0f We support MCP server now, see [MCP Server](./DOC.md#mcp-server-) for details\n- [2025/09]: \ud83d\ude80 Released v2 with major improvements - see [release notes](https://github.com/icip-cas/PPTAgent/releases/tag/v0.2.0) for details\n- [2025/08]: \ud83c\udf89 Paper accepted to **EMNLP 2025**!\n- [2025/05]: \u2728 Released v1 with core functionality and \ud83c\udf1f breakthrough: reached 1,000 stars on GitHub! - see [release notes](https://github.com/icip-cas/PPTAgent/releases/tag/v0.1.0) for details\n- [2025/01]: \ud83d\udd13 Open-sourced the codebase, with experimental code archived at [experiment release](https://github.com/icip-cas/PPTAgent/releases/tag/experiment)\n\n## Open Source \ud83e\udd17\nWe have released our model and data at [HuggingFace](https://huggingface.co/collections/ICIP/pptagent-68b80af43b4f4e0cb14d0bb2).\n\n## Demo Video \ud83c\udfa5\n\nhttps://github.com/user-attachments/assets/c3935a98-4d2b-4c46-9b36-e7c598d14863\n\n## Distinctive Features \u2728\n\n- **Dynamic Content Generation**: Creates slides with seamlessly integrated text and images\n- **Smart Reference Learning**: Leverages existing presentations without requiring manual annotation\n- **Comprehensive Quality Assessment**: Evaluates presentations through multiple quality metrics\n\n## Case Study \ud83d\udca1\n\n- #### [Iphone 16 Pro](https://www.apple.com/iphone-16-pro/)\n\n<div style=\"display: flex; flex-wrap: wrap; gap: 10px;\">\n\n <img src=\"resource/iphone16pro/0001.jpg\" alt=\"\u56fe\u72471\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0002.jpg\" alt=\"\u56fe\u72472\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0003.jpg\" alt=\"\u56fe\u72473\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0004.jpg\" alt=\"\u56fe\u72474\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0005.jpg\" alt=\"\u56fe\u72475\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0006.jpg\" alt=\"\u56fe\u72476\" width=\"200\"/>\n\n <img src=\"resource/iphone16pro/0007.jpg\" alt=\"\u56fe\u72477\" width=\"200\"/>\n\n</div>\n\n- #### [Build Effective Agents](https://www.anthropic.com/research/building-effective-agents)\n\n<div style=\"display: flex; flex-wrap: wrap; gap: 10px;\">\n\n <img src=\"resource/build_effective_agents/0001.jpg\" alt=\"\u56fe\u72471\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0002.jpg\" alt=\"\u56fe\u72472\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0003.jpg\" alt=\"\u56fe\u72473\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0004.jpg\" alt=\"\u56fe\u72474\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0005.jpg\" alt=\"\u56fe\u72475\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0006.jpg\" alt=\"\u56fe\u72476\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0007.jpg\" alt=\"\u56fe\u72477\" width=\"200\"/>\n\n <img src=\"resource/build_effective_agents/0008.jpg\" alt=\"\u56fe\u72478\" width=\"200\"/>\n\n<img src=\"resource/build_effective_agents/0009.jpg\" alt=\"\u56fe\u72479\" width=\"200\"/>\n\n<img src=\"resource/build_effective_agents/0010.jpg\" alt=\"\u56fe\u724710\" width=\"200\"/>\n\n</div>\n\n## PPTAgent \ud83e\udd16\n\nPPTAgent follows a two-phase approach:\n1. **Analysis Phase**: Extracts and learns from patterns in reference presentations\n2. **Generation Phase**: Develops structured outlines and produces visually cohesive slides\n\nOur system's workflow is illustrated below:\n\n\n\n\n## PPTEval \u2696\ufe0f\n\nPPTEval evaluates presentations across three dimensions:\n- **Content**: Check the accuracy and relevance of the slides.\n- **Design**: Assesses the visual appeal and consistency.\n- **Coherence**: Ensures the logical flow of ideas.\n\nThe workflow of PPTEval is shown below:\n<p align=\"center\">\n<img src=\"resource/fig3.jpg\" alt=\"PPTEval Workflow\" style=\"width:70%;\"/>\n</p>\n\n\n## Citation \ud83d\ude4f\n\nIf you find this project helpful, please use the following to cite it:\n```bibtex\n@article{zheng2025pptagent,\n title={PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides},\n author={Zheng, Hao and Guan, Xinyan and Kong, Hao and Zheng, Jia and Zhou, Weixiang and Lin, Hongyu and Lu, Yaojie and He, Ben and Han, Xianpei and Sun, Le},\n journal={arXiv preprint arXiv:2501.03936},\n year={2025}\n}\n```\n\n[](https://star-history.com/#icip-cas/PPTAgent&Date)\n",
"bugtrack_url": null,
"license": null,
"summary": "PPTAgent, a tool for utilizing LLMs to generate PowerPoint presentations from documents.",
"version": "0.2.14",
"project_urls": {
"Bug Tracker": "https://github.com/icip-cas/PPTAgent/issues",
"Homepage": "https://github.com/icip-cas/PPTAgent"
},
"split_keywords": [
"presentation",
" powerpoint",
" ppt",
" llm",
" ai",
" document-processing"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "431d3317e9757cdb29e046b5fdc08ef07c747c21f9d54857209b3156533022c5",
"md5": "90f735b85fa81e1b869b6aed83221679",
"sha256": "eb6acf59af3280837ba3664726af5e719787c00ebac0b74c24499fb3eb251d1c"
},
"downloads": -1,
"filename": "pptagent-0.2.14-py3-none-any.whl",
"has_sig": false,
"md5_digest": "90f735b85fa81e1b869b6aed83221679",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 4748974,
"upload_time": "2025-10-29T09:19:20",
"upload_time_iso_8601": "2025-10-29T09:19:20.043848Z",
"url": "https://files.pythonhosted.org/packages/43/1d/3317e9757cdb29e046b5fdc08ef07c747c21f9d54857209b3156533022c5/pptagent-0.2.14-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f02aace69eace520cffdda88dcd436f6d3e85c46952fbd5dd122941afa68e349",
"md5": "c0b2f9e1360eee81ab13ce98ddfaec11",
"sha256": "941977fada9c6e6b62c144a2e79529f0ed896e9c6e17cb70f2804e10153a5e60"
},
"downloads": -1,
"filename": "pptagent-0.2.14.tar.gz",
"has_sig": false,
"md5_digest": "c0b2f9e1360eee81ab13ce98ddfaec11",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 4735229,
"upload_time": "2025-10-29T09:19:23",
"upload_time_iso_8601": "2025-10-29T09:19:23.832184Z",
"url": "https://files.pythonhosted.org/packages/f0/2a/ace69eace520cffdda88dcd436f6d3e85c46952fbd5dd122941afa68e349/pptagent-0.2.14.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-29 09:19:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "icip-cas",
"github_project": "PPTAgent",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "pptagent"
}
JSON
