Tag
4 posts tagged #document-ai
Browse 4 posts tagged Document AI, including practical setup notes, reviews, comparisons, and workflow patterns for engineers working with AI tools.
Kita uses vision AI to parse bank statements, tax returns, and P&L documents for credit underwriting, handling messy photos and scans that break standard OCR tools.
Open-source platform for extracting structured data from unstructured documents using LLMs. Deploy as API or ETL pipeline.
Extract is a YC P25 hosted OCR and document parsing API that turns PDFs, PPTX, DOCX, and scans into text chunks with bounding boxes. 81.9% accuracy, 2x faster than AWS Textract, $3 per 1K pages.
Kita uses vision-language models to automate document-based credit review for lenders in emerging markets, parsing 50+ document types from PDFs to photos.