{"avoid_when":"数据已是干净文本","content_hash":"699e366f1e7b7542ba5254c92d3e06bf0538b0c61569d861d01214f27a3da411","domain":"ai-agents","evidence_urls":["https://github.com/Unstructured-IO/unstructured"],"id":"unstructured","language":"Python","license":"","name":"Unstructured","niche":"document ETL","repo":"https://github.com/Unstructured-IO/unstructured","source_updated_at":null,"status":"active","summary":"文档解析与预处理，服务 RAG 摄取。","tags":["dataset","rag"],"use_when":"要把 PDF/HTML 等弄成可索引文本","verification_status":"unverified","verified_at":null}