Unstructured

Open-source ETL for turning complex documents into clean, structured data

7d Not tracked yet — first tracked 2026-08-21
30d Not tracked yet — first tracked 2026-08-21
90d Not tracked yet — first tracked 2026-08-21

15,328 → 15,351 stars since Aug 21

data-pipelinesdeep-learningdocument-image-analysisdocument-image-processingdocument-parserdocument-parsingdocxdonutinformation-retrievallangchainllmmachine-learningmlnatural-language-processingnlpocrpdfpdf-to-jsonpdf-to-textpreprocessing