Can I connect PDFs and documents to iDBQuery?
Yes. iDBQuery reads PDFs and documents — including scanned ones — using OCR to extract text and tables, then makes them queryable in plain language. You can ask questions across contracts, statements and reports and get answers cited back to the exact page and document.
PDFs and documents are a core source type in iDBQuery, not an afterthought. You upload a PDF and iDBQuery extracts its text and tables; for scanned or image-based documents, OCR converts the pages into structured, queryable content.
- Scanned documents handled — OCR reads image-only PDFs so even paper-origin files become searchable and queryable.
- Tables extracted — figures locked inside document tables are pulled out so you can aggregate and filter them.
- Ask in plain language — question a single document or many at once, and iDBQuery returns answers with citations to the source page and document.
- Blend with structured data — a value from a PDF can be reconciled against a database or spreadsheet in the same question.
This is how teams turn a pile of statements, reports or agreements into something they can actually analyze. Instead of reading every file, you ask a question and iDBQuery surfaces the answer with a precise citation, so you can verify it in seconds. PDFs sit alongside your databases and spreadsheets in one live model, so a single question can draw on documents and structured data together.
Updated 2026-06-22