Tabify.ai — Instant In-Context Tabular Predictions with Local TabPFN

Description and use

Tabify.ai delivers instant, privacy‑first tabular predictions locally, eliminating training loops and cloud data transfer.

Problem

Traditional tabular machine learning requires extensive data cleaning, pipeline setup, cross‑validation, and hyperparameter tuning, and uploading sensitive CSVs to cloud APIs risks privacy and compliance.

Outcome

Tabify.ai delivers instant, privacy‑first tabular predictions locally, removing the need for training loops, hyperparameter tuning, and cloud data transfer, thereby accelerating experimentation for data professionals.

Workflow

• 1. Install Docker Compose and run docker compose up --build to start FastAPI backend and Vue 3 frontend.
• 2. Open the local web dashboard at http://localhost:5173 or the Swagger API at http://localhost:8000/docs.
• 3. Upload a CSV file via the dashboard or POST to /api/predict.
• 4. TabPFN performs in‑context inference in a single forward pass (≈0.1–1.5 s).
• 5. View predictions, evaluation metrics, and visualizations directly in the UI.
• 6. Export results or use the REST API for programmatic access.

Evidence

Tabify.ai is a privacy‑first web application designed for instantaneous, zero‑training machine learning on tabular data (CSV).

Source

Zero Training Required: No fitting loops, no epochs, no hyperparameter tuning. TabPFN behaves like an LLM for tables, delivering predictions in a single forward pass (~0.1 to 1.5 seconds).

Source

100% Local & Private: All data processing runs strictly on your own hardware (NVIDIA GPU, Apple Silicon MPS, AMD ROCm/DirectML, or multi‑core CPU). Zero bytes leave your machine.

Source

With Docker Compose (docker compose up --build), both the FastAPI backend and Vue 3 frontend start instantly.

Source