ade-document-processing-skills

Parses, extracts, and classifies documents using LandingAI's Agentic Document Extraction (ADE). Supports PDFs, images, spreadsheets, and presentations; outputs structured Markdown with hierarchical JSON. Covers schema-based field extraction (JSON Schema or Pydantic), document classification and splitting by type, page-level classification (Classify API), hierarchical table of contents generation (Section API), async processing for large files (Parse Jobs) and async extraction for long documents or large schemas (Extract Jobs), and visual grounding (bounding boxes, page numbers). Use when parsing documents into structured Markdown, extracting specific fields with a schema, classifying mixed document batches, classifying pages before parsing, generating a table of contents from a document, processing large files asynchronously, running long-running extractions asynchronously, or when the user mentions bounding boxes, word locations, grounding, or highlighting where data appears in a document.

Builds end-to-end document processing pipelines using LandingAI ADE. Covers batch and async processing, classify-then-extract workflows for mixed document types, RAG pipelines with vector DB ingestion, database integration (Snowflake, CSV, DataFrames), visualization (bounding box overlays, cropped chunk images, word-level annotation), and Streamlit UIs. Use when composing ADE parse/extract/split operations into multi-step pipelines, processing document batches in parallel, loading extraction results into databases, or visualizing/annotating extracted content. Complements the document-extraction skill (which covers single ADE SDK operations); use when those operations need to be chained into workflows or when word-level grounding, bounding box visualization, or annotation is required.