Document AI Toolkit

Multi-format document parser (PDF/DOCX/HTML/MD/TXT), 5 chunking strategies, table extraction, schema-guided extraction, and summarization.

Parse a document, choose a chunking strategy, and see the results with stats.

Sample Document Chunking Strategy Chunk Size Chunk Overlap

Parse Results

Configure and process.

Full version includes multi-format parser, 5 chunkers, table/schema extractors, summarization chains, and OCR interface.

🤖 AI/LLM Toolkit — Document AI Toolkit Demo