Skip to content
AI Runtime & Agent Substrate

document-pipeline

Ingestion for PDF / docx / markdown — chunk, table-aware extract, embed, route to @nebutra/knowledge-base. OCR fallback for image-only pages.

packages/ai/document-pipeline · Source ↗ · Docs ↗

document pipeline
PDF· upload
OCR· 47p
chunk· 248
embed
unstructured.io · multi-format