Upload regulatory documents, compliance frameworks, or any structured text and get back RAG-ready JSONL chunks with full normalisation, section-aware chunking, and provenance metadata.
Parse PDF, DOCX, YAML, JSON, Markdown and plain text into clean UTF-8.
OCR cleanup, heading promotion, paragraph splitting, and markdown standardisation.
Section-aware splitting with configurable word targets, heading depth, and preamble.
Download JSONL chunks or normalised Markdown. Results also pushed to S3.
Supported formats:
PDF DOCX YAML JSON Markdown Plain Text
Paste the API key provided by your Ontic admin to unlock the pipeline.
Upload files or paste structured text to produce RAG-ready JSONL chunks.
Drag and drop or browse for documents to process.
Drop files here or click to browse
Alternatively, paste structured text, markdown, or raw content.
| Step | Duration | Detail |
|---|