Skip to content

Document Processing

Elsai provides dedicated packages for extracting content from every common document format.

Packages

PackageVersionPurpose
elsai-text-extractors0.1.0PDF, DOCX, CSV, Excel — structured text extraction
elsai-ocr-extractors2.0.1OCR from scanned PDFs — Azure, Amazon Textract, Mistral, LlamaParse
elsai-parsers0.1.0Natural language queries over Excel/CSV using an LLM
elsai-nli0.1.0Natural language interface for CSV data

Choosing the right package

Document type        Recommended package
─────────────────────────────────────────────────────
Digital PDF/DOCX     elsai-text-extractors
Scanned PDF/image    elsai-ocr-extractors
Excel (NL query)     elsai-parsers
CSV (NL query)       elsai-nli

Next steps

Copyright © 2026 Elsai Foundry.