1
OCR It – pull text out of un-copyable documents for your LLM
把扫描书、PPT、防复制PDF一键OCR成文本，喂给LLM零配置，开箱即用。
Article URL: https://github.com/thiagotigaz/ocr-it Comments URL: https://news.ycombinator.com/item?id=49415852 Points: 111 # Comments: 26
2
Timed YouTube video transcripts in .txt and .pdf
一键提取 YouTube 视频带时间戳的转录文本，支持导出为纯净 TXT 或 PDF 文件，省去手动抄录的麻烦。
hello people, I want to share with you the tool Im working on at the moment that does exactly what you see in the title, something pretty simple, want…
3
LLM for the development of FCM
用本地大模型从文本中提取数据，自动构建模糊认知图，让建模更智能。
arXiv:2607.04983v1 Announce Type: cross Abstract: This article is about the development of a fuzzy cognitive map using a local large language model. I…
4
Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives
零样本代理LLM工作流助力临床叙述精准提取肺部病理信息，无需标注数据即高效完成专业文本挖掘。
arXiv:2606.19852v1 Announce Type: cross Abstract: Information extraction from pathology reports is essential for cancer staging, tumor registry popula…