#documents

• 24 Apr 2026 · Study

  LangChain · Document loaders

  The Document object (page_content + metadata), writing a small custom loader for text and CSV files, and why metadata matters later for filtering and citing sources.

• 17 Mar 2025 · Paper summary

  Paper summary: SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

  SmolDocling is a 256M-parameter vision-language model that converts whole document pages end to end into DocTags, a markup capturing content, structure and location of every element.

• 2 Jan 2024 · Paper summary

  Paper summary: DocLLM: A layout-aware generative language model for multimodal document understanding

  DocLLM adds layout awareness to an LLM using only text bounding boxes, with no image encoder, via disentangled text/layout attention and a text-infilling pre-training objective.