Know your data.
Cast with confidence.

Open-source tools for analysts who need to understand their data before they query it.

See it work

Point FineType at a CSV. Get the semantic type and confidence score for every column.

$ finetype profile -f contacts.csv

Column        Type                                Confidence
────────────  ──────────────────────────────────  ──────────
name          identity.person.full_name            0.92
email         identity.person.email                0.99
created_at    datetime.timestamp.iso_8601          0.98
ip_address    technology.internet.ip_v4            0.97
amount        representation.numeric.decimal       0.94

Is that column of numbers a postal code, a year, or a price? FineType detects 209 semantic types and maps each one to a DuckDB expression — so your casts work on every row, not just the first ten.

What you get

Every type prediction is a guarantee, not a guess.

209 Semantic Types
Dates, emails, IPs, UUIDs, coordinates, phone numbers, and financial identifiers — across 7 domains and 65+ locales.
Guaranteed Casts
Every type maps to a DuckDB SQL expression. Profile your data, then cast with confidence. No more surprises at row 47,000.
Fast and Local
Pure Rust, no Python. 600+ classifications per second, 8.5 MB memory. Runs on your laptop — no cloud required.

Get started

FineType is free, open source (MIT), and ready to use.