PDF Text Extraction

Extract high-quality text from PDFs using two OCR engines:

• asta pdf-extraction olmocr — cloud-based extraction via olmOCR (best for large batches, S3, and complex layouts)
• asta pdf-extraction remote — quick single-file extraction via the Asta remote OCR API

Quick Start

olmocr (cloud batch extraction)

# Extract text from a PDF using a temporary workspace
TEMP_WORKSPACE=$(mktemp -d)
asta pdf-extraction olmocr "$TEMP_WORKSPACE" \
  --pdfs document.pdf \
  --markdown

# Output will be in $TEMP_WORKSPACE/markdown/document.md