🌐 语言

联系方式 📫

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。

新闻动态 📅

[2026/03]: 现已支持 CLI，并在 Hugging Face 🤗 发布了我们的微调模型！
[2026/01]: 支持自由格式和模板生成，支持 PPTX 导出，现已支持离线模式！新增上下文管理，避免上下文溢出。
[2025/12]: 🔥 发布 V2，重大改进——深度研究集成、自由视觉设计、自主资源生成、文本转图像、带沙盒和 20+ 工具的智能体环境。
[2025/09]: 🛠️ 新增 MCP 服务器支持——配置详情请见 MCP Server
[2025/09]: 🚀 发布 v2，重大改进——详细信息请查阅 release notes
[2025/08]: 🎉 论文被 EMNLP 2025 录用！
[2025/05]: ✨ 发布 v1，核心功能和 🌟 突破：在 GitHub 上获得 1,000 星！——详细信息请查阅 release notes
[2025/01]: 🔓 代码开源，实验代码归档于 experiment release

使用方法 📖

[!重要]

暂不支持 Windows。如果您在 Windows 系统上，请使用 WSL。

强烈建议先用 CLI 和最小任务启动，以确认依赖和环境配置正确。

配置

如果您使用 CLI，pptagent onboard 可以帮助您交互式创建和更新这些配置。如果您使用 Docker Compose 或源码构建，则需手动准备：

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

#### 提升质量的可选服务

以下服务可以显著提升生成质量，特别是在研究深度、PDF解析和视觉资产创建方面：

Tavily：提升网页搜索质量。在 tavily.com 申请 API 密钥，然后在 deeppresenter/mcp.json 中设置 TAVILY_API_KEY。
MinerU：提升 PDF 解析质量。你可以在 mineru.net 申请 API 密钥，并在 deeppresenter/mcp.json 中设置 MINERU_API_KEY，或者本地部署 MinerU 并设置 MINERU_API_URL。
文本转图像模型：提升图片生成质量。在 deeppresenter/config.yaml 中配置 t2i_model。

如果你想要完全离线的环境，可以本地部署 MinerU，并在 deeppresenter/config.yaml 中设置 offline_mode: true，以避免加载如网页搜索等依赖网络的工具。

更多可配置变量可在 constants.py 中找到。

1. 个人使用 / OpenClaw 集成：命令行界面（CLI）

[!NOTE]

在 macOS 上，命令行界面可能会自动安装多个本地依赖，包括 Homebrew、Node.js、Docker、poppler、Playwright 和 llama.cpp。

在 Linux 上，你需要自行准备运行环境。

如果你想要最快的本地部署，或希望通过命令行将 DeepPresenter 插件集成到 OpenClaw，请使用此模式。

# 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

| 命令 | 描述 | | ------------------- | ------------------------------------------------- | | pptagent onboard | 交互式配置向导 | | pptagent generate | 生成演示文稿 | | pptagent config | 查看当前配置 | | pptagent reset | 重置配置 | | pptagent serve | 启动 CLI 使用的本地推理服务 |

2. 最小化设置 / 开发：从源码构建

如果你想要最小的抽象层并在开发过程中完全控制依赖项，请使用此模式。

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 .

启动应用程序：

python webui.py

3. 服务器部署：Docker Compose

使用此模式可获得具有明确依赖关系的稳定服务器环境。

# 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.

#### 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”

贡献者 🌟

_Force1ess	_Puelloc	_hongyan	_Dnoob	_Sadahlu
_{KurisuMakiseSame}	_Angelen	_BrandonHu	_{Eliot White}	_EvolvedGhost
_ISCAS-zwl	_{James Brown}	_JunZhang	_{Open AI Tx}	_{Sense_wang}
_苏尧	_{Zakir Jiwani}	_臻宇	_lnennnn

引用 🙏

如果您觉得本项目对您有帮助，请使用以下方式引用：

@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}, }

--- Tranlated By Open Ai Tx | Last indexed: 2026-04-09 ---