Overview
The parsed documents dataset provides the extracted text content of reports and slide presentations as clean, machine-readable Markdown. Instead of parsing PDFs yourself, you get structured Markdown that’s ready for full-text search, retrieval-augmented generation (RAG), and other LLM-based workflows.How it works
Each document is parsed into Markdown — the text content with headings, tables, and structure preserved, ideal for display, indexing, and LLM context. Documents are requested one at a time. As with our PDFs, the endpoint returns a CDN link to the parsed Markdown file rather than the content inline; download the file from the returned link.Access
Parsed documents is a separate data package. Retrieving a document’s parsed text requires theparsed documents permission in addition to that document’s dataset permission — reports for reports, slides for slides. Missing either permission results in a 403 error.
Parsed documents is sold separately. Please get in touch if you’re
interested in access or pricing details.
How to access this data
Reports (REST API)
Retrieve the parsed text link for a report.
Slides (REST API)
Retrieve the parsed text link for a slide deck.