Custom Knowledge Base

Chat with your PDFs, docs and spreadsheets

Upload files and NovaBOT extracts, structures and indexes them for grounded answers.

Drop in product manuals, policy PDFs, price lists and spreadsheets. NovaBOT extracts the text — running OCR on scanned files — and preserves structure so answers stay coherent.

Large libraries are handled with smart chunking and reused embeddings on re-upload, keeping ingestion fast and affordable.

Highlights

All the formats

PDF, DOCX, TXT, CSV and spreadsheets.

OCR built in

Scanned PDFs and images become searchable text.

Smart chunking

Content is split to keep answers coherent and cited.

Frequently asked questions

What file types are supported?

PDF, DOCX, TXT, CSV and common spreadsheet formats, with OCR for scanned documents and images.

See it in action

Train your AI agent and try it free — live in minutes.