1
LLM-free, layout-aware PDF chunker in pure Rust
纯Rust实现、无需大模型、能感知布局的PDF智能分块工具，开源可自建。
Article URL: https://github.com/matthiasnordwig/pdf-struct-chunker Comments URL: https://news.ycombinator.com/item?id=48716707 Points: 2 # Comments: 0
2
LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding
布局导向的细粒度RAG方法，破解多模态文档理解中复杂结构信息的获取难题
arXiv:2605.22829v1 Announce Type: cross Abstract: Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing L…