Spreadsheets & CSVs
Rows are loaded into PostgreSQL with typed columns. Totals, averages, medians and percentiles are computed by SQL, and the answer shows how many rows and which filters it used.
No setup, no connectors. Upload what you already have and start asking.
PDF, Word, PowerPoint, Excel/CSV, images, or paste a URL. Files2BI reads each one and works out its structure.
For spreadsheets and CSVs it builds a real column schema (types, samples, distributions) so questions are answered with SQL, not guesses.
For PDFs and Office files it extracts text, tables and form fields (invoice number, total, due date) so both prose and field-level questions work.
Every answer is cited — page number, row count, matching documents, or invoice number with a one-click Open button.
Open Visual Dashboards on any tabular file for auto-suggested charts, or build your own from a prompt or by picking columns.
Rows are loaded into PostgreSQL with typed columns. Totals, averages, medians and percentiles are computed by SQL, and the answer shows how many rows and which filters it used.
Text, tables and figures are extracted and indexed for meaning, not just keywords. Answers quote the passage and cite the page.
Fields such as invoice number, date, vendor, total, due date and line items are read automatically, so you can filter and total them across every file.
Paste a URL and up to 10 pages on the same site are read and indexed, so documentation and policy portals become searchable.
Files are stored encrypted and indexed in the cloud. Every feature works — spreadsheets as SQL, invoices, dashboards, URLs — from any device, and your team can share them.
Files stay on your computer and the search index is kept in your browser. To build it, their text is sent to Files2BI, masked and indexed with the same model as Cloud — nothing is stored on our servers.
Questions about a rollout? Talk to us.
Start with 50K free tokens. No credit card. No commitment.