关于中文档案馆

我们的使命

互联网内容转瞬即逝,无数珍贵的中文互联网记忆正在消失。中文档案馆的使命是帮助人们发现和重新连接那些被遗忘的数字历史。

工作原理

我们通过整合互联网档案馆的存档快照和其他公开数据源,建立了一个专注于中文内容的元数据索引。AI 技术帮助我们更好地理解搜索意图,提供更精准的结果。

Tech Stack

Next.js
Frontend
🐍
FastAPI
Backend
🔍
Meilisearch
Search
🤖
OpenAI
AI

核心原则

1

只索引元数据,不存储版权内容

2

优先使用存档快照

3

AI辅助搜索,但不浏览实时网络

4

尊重内容创作者的权利

5

保护用户隐私

Project Timeline

Phase 1

Foundation

Core infrastructure, Archive.org integration, basic search functionality

Phase 2

AI Enhancement

Query understanding, result summarization, keyword expansion

Phase 3

Content Expansion

More sources, community contributions, advanced filters

团队

中文档案馆是一个开源项目,由对中文互联网历史感兴趣的志愿者共同维护。

Open Source Contributors

Chinese Archive is built by people who believe in preserving digital history. We welcome contributors from all backgrounds.

View on GitHub

联系我们

如有问题或建议,请通过项目仓库提交 Issue。

Bug Reports

Found a bug? Please open an issue on GitHub with details.

Open Issue →

Feature Requests

Have ideas for improvement? We'd love to hear them.

Suggest Feature →

Acknowledgments

Chinese Archive would not be possible without these amazing projects and organizations:

Internet ArchiveMeilisearchOpenAINext.jsFastAPIPostgreSQLTailwind CSS