Purpose: convert canonical PDF or Markdown artifacts into StructuredBlock rows.
Commands:
uv run victus-processing pdf-processing markdown --limit 10
uv run victus-processing pdf-processing run --limit 5
uv run victus-processing pdf-processing run --pdf data/artifacts/pdfs/{paper_id}.pdf
uv run victus-processing pdf-processing json-from-markdown --input-dir data/artifacts/markdown --shuffle --limit 5
Inputs:
data/artifacts/pdfs/;data/artifacts/markdown/;src/prompts/;config/pdf_processing.yaml;Outputs:
structured_blocks PostgreSQL rows;paper_processing_state.last_successful_stage = pdf.process after refresh;paper_processing_state.next_stage = classification.classify after refresh.Validation:
uv run victus-processing pdf-processing --help
uv run victus-processing pdf-processing run --help
uv run victus-processing processing-state refresh