nlm-ingestor
Open-source rule-based PDF parser for RAG that extracts sections, paragraphs, tables and lists, removes headers and watermarks, and offers OCR for scanned pages.
Open sourceData & Analytics
Visit website(opens in a new tab)
Open-source rule-based PDF parser for RAG that extracts sections, paragraphs, tables and lists, removes headers and watermarks, and offers OCR for scanned pages.