Tools / product
Unstructured
Unstructured is an organization maintaining open-source tools for document ETL, including the unstructured library that converts documents such as PDFs and DOCX files into structured formats for language models, plus API clients, OCR pipelines, and platform plugins.
githubopen-sourceparserdatallmapiautomationdocument-parsingetlpdf-to-jsonocrnlppreprocessinglangchain