开源雷达国内 GitHub 镜像站
加速通道已就绪 返回列表
全部项目

nampara-ai/librarian

Text corpus cleaner and organizer. Local-first document parsing/copyediting/indexing pipeline. Feed it transcripts, PDFs, DOCX, images, or scans. Librarian extracts the text, cleans it with an LLM to CMOS style and punctuation standards, files each document under a Dewey-style classification, and makes the whole collection full-text searchable.

语言:Python · GitHub 星标:49 · Fork:2

在 GitHub 上查看原仓库

正在读取项目信息…