Knowhere extracts, parses,、outputs structured chunks ready 为 AI Agents、检索增强生成.GitHub 1,853 ⭐ / 222 Fork，主要使用 Python 开发。标签：agent,ai-agents,chromadb,claude,claude-code。访问项目：https://github.com/Ontos-AI/knowhere
项目介绍
Knowhere extracts, parses,、outputs structured chunks ready 为 AI Agents、检索增强生成.
核心功能
- June 1, 2026: 📚 Knowhere now supports ultra-long PDFs and atlas-style documents. The parsing pipeline can process long-form PDFs with hundreds of pages (for example, 300, 500, or more) and route technical atlases or drawing collections through a dedicated layout-aware parser. - May 7, 2026: 🚀 Knowhere is now Open Source! We have open-sourced our entire stack for document ingestion, parsing, and agentic RAG. You can now self-host the full platform using [knowhere-self-hosted](https://github.com/Ontos-AI/knowhere-self-hosted). Check out our [Contribution Guide](CONTRIBUTING.md) to get involved!
使用指南
快速启动 1. Syncworkspace dependencies: ``` uv sync --all-packages ``` 2. Copyenvironment examples: ``` cp apps/api/.env.示例 apps/api/.env cp apps/worker/.env.示例 apps/worker/.env ``` 3. Updatecopied `.env` files 与 the values 你 need 为本地 work: - 数据库、Redis 连接 设置 - S3-compatible 存储 credentials -在 least one 大语言模型 provider 密钥: `DS_KEY`, `ALI_API_KEYS`, `GPT_API_KEY`,、`GLM_API_KEY` - `MINERU_API_KEYS` if 你 need PDF parsing -vision-capable model provider if 你 need 图像 summaries, 文字识别, atlas classification,、图像-aware retrieval - any optional billing、webhook providers 你 want 到 enable Most parser、retrieval tuning values 代码 defaults. Start 与 the required external services first,那么 override model names, provider URLs, budgets,、concurrency limits only when 你的部署 needs different full 依赖 matrix. 4. Start 本地 infrastructure stack: ``` ./deploy/本地-dev/start-dev.sh ``` 5. StartAPI、worker 在 separate terminals: ``` cd apps/api && uv run main.py cd apps/worker && uv run worker.py ```
项目信息
| 项目 | 信息 |
|---|---|
| 项目名称 | Ontos-AI/knowhere |
| Star 数 | 1,853 |
| Fork 数 | 222 |
| 编程语言 | Python |
| 开源协议 | Apache-2.0 |
| 创建时间 | 2026-04-30 |
| 最近更新 | 2026-07-03 |
| 主题标签 | agent、ai-agents、chromadb、claude、claude-code |
项目地址
GitHub 仓库：<https://github.com/Ontos-AI/knowhere>
> 完整 URL：[https://github.com/Ontos-AI/knowhere](https://github.com/Ontos-AI/knowhere)
如需查看完整源码、安装命令、使用示例、API 文档，请直接访问上方项目地址。所有信息均以 GitHub 仓库为准。