unstructured-io

【文档与办公】Unstructured.io library for partitioning documents by filetype (PDF, DOCX, HTML, EPUB, PPT, email). Covers partition strategies (fast, hi_res, ocr_only, auto), chunking by title, metadata extraction, and serverless API usage. USE WHEN: user mentions "unstructured.io", "unstructured library", "partition documents", "multi-format ingestion", "DOCX to …

独立 GitHub 快照 · 自动分类 · 以原作者文档为准