Web Analytics

PPTAgent

⭐ 3354 stars Portuguese by icip-cas

🌐 Idioma

https://github.com/user-attachments/assets/938889e8-d7d8-4f4f-b2a1-07ee3ef3991a

📫 Contato

O principal contribuidor deste repositório é um estudante de mestrado com graduação prevista para 2026, fique à vontade para entrar em contato para colaboração ou oportunidades.

>

O principal colaborador deste repositório é um estudante de mestrado da turma de 2026. Contato para oportunidades de cooperação ou intercâmbio é bem-vindo.

📅 Novidades

📖 Uso

[!IMPORTANTE]
1. Todas essas chaves de API, configurações e serviços são obrigatórios.
2. Recomendação de Backbone de Agente: Use Claude para o Agente de Pesquisa e Gemini para o Agente de Design. GLM-4.7 também é uma boa escolha entre modelos open-source.
3. O modo offline é suportado com capacidades limitadas (veja Configuração Offline abaixo).

1. Configuração do Ambiente

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

  • Configuração online:
  • MinerU: Solicite uma chave de API em mineru.net. Observe que cada chave é válida por 14 dias.
  • Tavily: Solicite uma chave de API em tavily.com.
  • LLM: Defina o endpoint do seu modelo, chaves de API e parâmetros relacionados em config.yaml.
  • Configuração offline:
  • MinerU: Implemente o servidor MinerU seguindo as instruções em Guia Docker do MinerU
  • Alternância de configuração: Defina offline_mode: true em config.yaml para evitar o carregamento de ferramentas dependentes da rede (por exemplo, fetch, search).
  • Endpoint do MinerU: Defina MINERU_API_URL em mcp.json para a URL do seu serviço MinerU local

2. Inicialização do Serviço

Construa as imagens docker: docker compose build

  • Via Docker Compose:
`bash docker compose up -d `

  • Executando localmente:
`bash cd deeppresenter pip install -e . playwright install-deps playwright install chromium npm install npx playwright install chromium python webui.py `

[!TIP]
🚀 All configurable variables can be found in constants.py.

💡 Case Study

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

图片1

图片2

图片3

图片4

图片5

图片6

图片7

图片8

图片9

图片10

  • #### Prompt: 请介绍小米 SU7 的外观和价格

图片1

图片2

图片3

图片4

图片5

图片6

  • #### 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”

图片1

图片2

图片3

图片4

图片5

图片6

图片7

图片8

图片9

图片10

图片11

图片12

图片13

图片14

图片15


Star History Chart

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." } ``

--- Tranlated By Open Ai Tx | Last indexed: 2026-02-22 ---