I built Kintara because apparently having too many hobbies eventually leads to building your own document management system

说明与用途

Kintara 是一个自托管的文档库，自动索引 PDF、Markdown 和文本文件，支持可选 AI 元数据和搜索功能，可通过浏览器或 PWA 在任何设备上访问。

问题

Users need a lightweight, self‑hosted document library that automatically indexes PDFs, Markdown, and text files, supports AI‑powered metadata suggestions, and can be accessed from any device.

结果

Kintara transforms a raw collection of documents into a searchable, AI‑enhanced library that can be accessed from any device, reducing manual metadata work and improving search precision.

工作流

• 1. Deploy Kintara using the Docker image. 2. Point the container to a shared folder (e.g., NAS). 3. Drop PDFs, Markdown, or text files into the folder. 4. Kintara watches the folder, indexes new files, extracts text, metadata, and thumbnails. 5. Optionally enable AI features via OpenAI or Gemini. 6. Use the web UI or PWA to browse, search, tag, and share documents.
• 7. For AI metadata suggestions, select desired fields and apply them to the document.
• 8. Use the AI search feature to retrieve exact passages with page numbers.
• 9. Share private libraries with other users via GitHub OAuth.

证据

Drop PDFs, Markdown, or text files into the directory and it indexes them automatically, extracts searchable text and metadata, generates thumbnails, and makes the whole library available through a browser or installable PWA.

来源

I added an option to use OpenAI or Gemini, and with so few tokens being spent, it's a fraction of a cent to use most of them, aside from the cover image generation, which is bit more, but makes the library look so much prettier!

来源

Kintara can read the document and suggest a title, author, summary, keywords, DOI, ISBN, and publication year. Then it displays the suggestions and I choose which fields I want, apply them to the form.

来源