Metadata-Version: 2.4
Name: pptagent
Version: 1.1.33
Summary: An Agentic Framework for Reflective PowerPoint Generation
Author-email: Hao Zheng <wszh712811@gmail.com>
License-Expression: MIT
Project-URL: Homepage, https://github.com/icip-cas/PPTAgent
Project-URL: Bug Tracker, https://github.com/icip-cas/PPTAgent/issues
Keywords: presentation,powerpoint,ppt,llm,ai,document-processing
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: MacOS
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Office/Business :: Office Suites
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aiohttp>=3.9.0
Requires-Dist: aiometer
Requires-Dist: aiofiles
Requires-Dist: arxiv>=2.2.0
Requires-Dist: beautifulsoup4
Requires-Dist: binaryornot>=0.4.4
Requires-Dist: colorlog>=6.9.0
Requires-Dist: docker>=7.1.0
Requires-Dist: fake-useragent>=2.2.0
Requires-Dist: fastapi[all]
Requires-Dist: fastmcp<2.14.0,>=2.10.0
Requires-Dist: fasttext>=0.9.3
Requires-Dist: filelock>=3.0.0
Requires-Dist: firecrawl-py>=4.10.2
Requires-Dist: func_argparse
Requires-Dist: gradio<6.0,>=5.47.2
Requires-Dist: html2image
Requires-Dist: httpx>=0.28.0
Requires-Dist: httpx-retries>=0.4.5
Requires-Dist: jinja2>=3.1.6
Requires-Dist: json-repair>=0.51.0
Requires-Dist: jsonlines>=4.0.0
Requires-Dist: langchain_mcp_adapters
Requires-Dist: lxml
Requires-Dist: markitdown[all]
Requires-Dist: mcp>=1.14.0
Requires-Dist: mistune>=3.1.4
Requires-Dist: numpy<2.0.0
Requires-Dist: oaib
Requires-Dist: openai>=1.108.2
Requires-Dist: opencv-python-headless
Requires-Dist: openpyxl
Requires-Dist: pdf2image
Requires-Dist: pillow
Requires-Dist: playwright>=1.55.0
Requires-Dist: pptagent-pptx>=0.0.1
Requires-Dist: pre-commit>=4.3.0
Requires-Dist: pydantic>=2.11.9
Requires-Dist: pypdf>=6.1.1
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: python-Levenshtein
Requires-Dist: python-multipart
Requires-Dist: python-pptx>=0.6.21
Requires-Dist: PyYAML
Requires-Dist: pytest
Requires-Dist: pytest-asyncio
Requires-Dist: pytest-xdist
Requires-Dist: rich>=13.0.0
Requires-Dist: semanticscholar>=0.11.0
Requires-Dist: socksio
Requires-Dist: tavily-python>=0.7.14
Requires-Dist: tenacity
Requires-Dist: textual<0.90,>=0.89.1
Requires-Dist: trafilatura>=2.0.0
Requires-Dist: typer>=0.9.0
Requires-Dist: uvicorn
Requires-Dist: modelscope>=1.35.1
Provides-Extra: full
Requires-Dist: transformers<4.50.0; extra == "full"
Requires-Dist: fasttext; extra == "full"
Requires-Dist: einops; extra == "full"
Requires-Dist: peft; extra == "full"
Requires-Dist: huggingface_hub; extra == "full"
Requires-Dist: timm; extra == "full"
Requires-Dist: unoserver; extra == "full"
Dynamic: license-file


<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</a>
      </div>
    </div>
  </details>
</div>

<div align="center">
  <img src="resource/pptagent-logo.jpg" width="240px" alt="https://github.com/icip-cas/PPTAgent">
</div>

<table>
  <tr>
    <td width="50%">
      <video controls width="100%" src="https://github.com/user-attachments/assets/314bed6a-185e-4c81-9de5-35728e83e22a">
      </video>
    </td>
    <td width="50%">
      <video controls width="100%" src="https://github.com/user-attachments/assets/96eee616-5f79-4ea1-bd7f-bcaa466eda9e">
      </video>
    </td>
  </tr>
</table>

## Contact 📫
> The main contributor of this repo is a Master's student graduating in 2026, feel free to reach out for collaboration or opportunities.
>
> 本仓库的主要贡献者是一名 2026 届硕士毕业生，欢迎联系合作或交流机会。

<div align="center">
  <img src="resource/wechat.jpg" width="140px">
</div>

## News 📅
- [2026/03]: We now support CLI and have released our fine-tuned models on [Hugging Face 🤗](https://huggingface.co/collections/ICIP/deeppresenter)!
- [2026/01]: We support freeform and template generation support PPTX export, offline mode now! Context management is added to avoid context overflow.
- [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](PPTAgent/DOC.md#mcp-server-) for configuration 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)

## Usage 📖

> [!IMPORTANT]
> Windows is not supported. If you are on Windows, please use WSL.
>
> We strongly recommend starting with the CLI and minimum task to confirm dependencies and environment is configured correctly.

### Configuration

If you use the CLI, `pptagent onboard` can help create and update these configurations interactively. If you use Docker Compose or build from source, you should prepare them manually:

```bash
cp deeppresenter/config.yaml.example deeppresenter/config.yaml
cp deeppresenter/mcp.json.example deeppresenter/mcp.json
```

#### Optional Services That Improve Quality

The following services can noticeably improve generation quality, especially for research depth, PDF parsing, and visual asset creation:

- **Tavily**: improves web search quality. Apply for an API key at [tavily.com](https://www.tavily.com/), then set `TAVILY_API_KEY` in [`deeppresenter/mcp.json`](deeppresenter/mcp.json).
- **MinerU**: improves PDF parsing quality. You can either apply for an API key at [mineru.net](https://mineru.net/apiManage/docs) and set `MINERU_API_KEY` in [`deeppresenter/mcp.json`](deeppresenter/mcp.json), or deploy MinerU locally and set `MINERU_API_URL` instead.
- **Text-to-image model**: improves image generation quality. Configure `t2i_model` in [`deeppresenter/config.yaml`](deeppresenter/config.yaml).


If you want a fully offline setup, deploy MinerU locally and set `offline_mode: true` in `deeppresenter/config.yaml` to avoid loading network-dependent tools such as web search.

More configurable variables can be found in [constants.py](deeppresenter/utils/constants.py).

### 1. Personal Use / OpenClaw Integration: CLI

> [!NOTE]
> On macOS, the CLI may automatically install several local dependencies, including Homebrew, Node.js, Docker, poppler, Playwright, and llama.cpp.
>
> On Linux, you should prepare the environment by yourself.

Use this mode if you want the fastest local setup or want to plug DeepPresenter into OpenClaw through the CLI.

```bash
# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

# First-time interactive setup
uvx pptagent onboard

# Generate a presentation
uvx pptagent generate "Single Page with Title: Hello World" -o hello.pptx

# Generate with attachments
uvx pptagent generate "Q4 Report" \
  -f data.xlsx \
  -f charts.pdf \
  -p "10-12" \
  -o report.pptx
```

| Command             | Description                                       |
| ------------------- | ------------------------------------------------- |
| `pptagent onboard`  | Interactive configuration wizard                  |
| `pptagent generate` | Generate presentations                            |
| `pptagent config`   | View current configuration                        |
| `pptagent reset`    | Reset configuration                               |
| `pptagent serve`    | Start the local inference service used by the CLI |

### 2. Minimal Setup / Development: Build From Source

Use this mode if you want the smallest abstraction layer and full control over dependencies during development.

```bash
uv pip install -e .
playwright install-deps
playwright install chromium
npm install --prefix deeppresenter/html2pptx
modelscope download forceless/fasttext-language-id

docker pull forceless/deeppresenter-sandbox
docker pull forceless/deeppresenter-host
docker tag forceless/deeppresenter-sandbox deeppresenter-sandbox

# or build from dockerfile
docker build -t deeppresenter-sandbox -f deeppresenter/docker/SandBox.Dockerfile .
```

Start the app:

```bash
python webui.py
```

### 3. Server Deployment: Docker Compose

Use this mode for a stable server environment with explicit dependencies.

```bash
# Pull the public images to avoid build from source
docker pull forceless/deeppresenter-sandbox
docker tag forceless/deeppresenter-sandbox deeppresenter-sandbox

# Or build from source
docker build -t deeppresenter-sandbox -f deeppresenter/docker/SandBox.Dockerfile .

# Start the host service
docker compose up -d
```

The service exposes the web UI on `http://localhost:7861`.

## Case Study 💡

- #### Prompt: Please present the given document to me.

<div style="display: flex; flex-wrap: wrap; gap: 10px;">

  <img src="resource/v2/manuscript/0001.jpg" alt="图片1" width="200"/>

  <img src="resource/v2/manuscript/0002.jpg" alt="图片2" width="200"/>

  <img src="resource/v2/manuscript/0003.jpg" alt="图片3" width="200"/>

  <img src="resource/v2/manuscript/0004.jpg" alt="图片4" width="200"/>

  <img src="resource/v2/manuscript/0005.jpg" alt="图片5" width="200"/>

  <img src="resource/v2/manuscript/0006.jpg" alt="图片6" width="200"/>

  <img src="resource/v2/manuscript/0007.jpg" alt="图片7" width="200"/>

  <img src="resource/v2/manuscript/0008.jpg" alt="图片8" width="200"/>

  <img src="resource/v2/manuscript/0009.jpg" alt="图片9" width="200"/>

  <img src="resource/v2/manuscript/0010.jpg" alt="图片10" width="200"/>

</div>

- #### Prompt: 请介绍小米 SU7 的外观和价格

<div style="display: flex; flex-wrap: wrap; gap: 10px;">

  <img src="resource/v2/presentation1/0001.jpg" alt="图片1" width="200"/>

  <img src="resource/v2/presentation1/0002.jpg" alt="图片2" width="200"/>

  <img src="resource/v2/presentation1/0003.jpg" alt="图片3" width="200"/>

  <img src="resource/v2/presentation1/0004.jpg" alt="图片4" width="200"/>

  <img src="resource/v2/presentation1/0005.jpg" alt="图片5" width="200"/>

  <img src="resource/v2/presentation1/0006.jpg" alt="图片6" width="200"/>

</div>

- #### 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”

<div style="display: flex; flex-wrap: wrap; gap: 10px;">

  <img src="resource/v2/presentation2/0001.jpg" alt="图片1" width="200"/>

  <img src="resource/v2/presentation2/0002.jpg" alt="图片2" width="200"/>

  <img src="resource/v2/presentation2/0003.jpg" alt="图片3" width="200"/>

  <img src="resource/v2/presentation2/0004.jpg" alt="图片4" width="200"/>

  <img src="resource/v2/presentation2/0005.jpg" alt="图片5" width="200"/>

  <img src="resource/v2/presentation2/0006.jpg" alt="图片6" width="200"/>

  <img src="resource/v2/presentation2/0007.jpg" alt="图片7" width="200"/>

  <img src="resource/v2/presentation2/0008.jpg" alt="图片8" width="200"/>

  <img src="resource/v2/presentation2/0009.jpg" alt="图片9" width="200"/>

  <img src="resource/v2/presentation2/0010.jpg" alt="图片10" width="200"/>

  <img src="resource/v2/presentation2/0011.jpg" alt="图片11" width="200"/>

  <img src="resource/v2/presentation2/0012.jpg" alt="图片12" width="200"/>

  <img src="resource/v2/presentation2/0013.jpg" alt="图片13" width="200"/>

  <img src="resource/v2/presentation2/0014.jpg" alt="图片14" width="200"/>

  <img src="resource/v2/presentation2/0015.jpg" alt="图片15" width="200"/>

</div>

---

## Contributors 🌟

<table>
<tr>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Force1ess>
            <img src=https://avatars.githubusercontent.com/u/72636351?v=4 width="80;"  alt=Force1ess/>
            <br />
            <sub style="font-size:14px"><b>Force1ess</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Puellaquae>
            <img src=https://avatars.githubusercontent.com/u/22560343?v=4 width="80;"  alt=Puelloc/>
            <br />
            <sub style="font-size:14px"><b>Puelloc</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/hysyyds>
            <img src=https://avatars.githubusercontent.com/u/80150669?v=4 width="80;"  alt=hongyan/>
            <br />
            <sub style="font-size:14px"><b>hongyan</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Dnoob>
            <img src=https://avatars.githubusercontent.com/u/92987618?v=4 width="80;"  alt=Dnoob/>
            <br />
            <sub style="font-size:14px"><b>Dnoob</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Sadahlu>
            <img src=https://avatars.githubusercontent.com/u/126563707?v=4 width="80;"  alt=Sadahlu/>
            <br />
            <sub style="font-size:14px"><b>Sadahlu</b></sub>
        </a>
    </td>
</tr>
<tr>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/KurisuMakiseSame>
            <img src=https://avatars.githubusercontent.com/u/168447425?v=4 width="80;"  alt=KurisuMakiseSame/>
            <br />
            <sub style="font-size:14px"><b>KurisuMakiseSame</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Angelenx>
            <img src=https://avatars.githubusercontent.com/u/39873863?v=4 width="80;"  alt=Angelen/>
            <br />
            <sub style="font-size:14px"><b>Angelen</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/kylooh>
            <img src=https://avatars.githubusercontent.com/u/26456650?v=4 width="80;"  alt=Eliot White/>
            <br />
            <sub style="font-size:14px"><b>Eliot White</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/EvolvedGhost>
            <img src=https://avatars.githubusercontent.com/u/92856393?v=4 width="80;"  alt=EvolvedGhost/>
            <br />
            <sub style="font-size:14px"><b>EvolvedGhost</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/ISCAS-zwl>
            <img src=https://avatars.githubusercontent.com/u/179820048?v=4 width="80;"  alt=ISCAS-zwl/>
            <br />
            <sub style="font-size:14px"><b>ISCAS-zwl</b></sub>
        </a>
    </td>
</tr>
<tr>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/James4Ever0>
            <img src=https://avatars.githubusercontent.com/u/103997068?v=4 width="80;"  alt=James Brown/>
            <br />
            <sub style="font-size:14px"><b>James Brown</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/LasRuinasCirculares>
            <img src=https://avatars.githubusercontent.com/u/119716645?v=4 width="80;"  alt=JunZhang/>
            <br />
            <sub style="font-size:14px"><b>JunZhang</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/openaitx-system>
            <img src=https://avatars.githubusercontent.com/u/215529505?v=4 width="80;"  alt=Open AI Tx/>
            <br />
            <sub style="font-size:14px"><b>Open AI Tx</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/haosenwang1018>
            <img src=https://avatars.githubusercontent.com/u/167664334?v=4 width="80;"  alt=Sense_wang/>
            <br />
            <sub style="font-size:14px"><b>Sense_wang</b></sub>
        </a>
    </td>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/DeJeune>
            <img src=https://avatars.githubusercontent.com/u/67425183?v=4 width="80;"  alt=SuYao/>
            <br />
            <sub style="font-size:14px"><b>SuYao</b></sub>
        </a>
    </td>
</tr>
<tr>
    <td align="center" style="word-wrap: break-word; width: 120.0; height: 120.0">
        <a href=https://github.com/Dormiveglia-elf>
            <img src=https://avatars.githubusercontent.com/u/81767213?v=4 width="80;"  alt=Zhenyu/>
            <br />
            <sub style="font-size:14px"><b>Zhenyu</b></sub>
        </a>
    </td>
</tr>
</table>

[![Star History Chart](https://api.star-history.com/svg?repos=icip-cas/PPTAgent&type=Date)](https://star-history.com/#icip-cas/PPTAgent&Date)

## Citation 🙏

If you find this project helpful, please use the following to cite it:
```bibtex
@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."
}

@misc{zheng2026deeppresenterenvironmentgroundedreflectionagentic,
      title={DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation},
      author={Hao Zheng and Guozhao Mo and Xinru Yan and Qianhao Yuan and Wenkai Zhang and Xuanang Chen and Yaojie Lu and Hongyu Lin and Xianpei Han and Le Sun},
      year={2026},
      eprint={2602.22839},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2602.22839},
}
```
