Downloads 369this week

GitHub stars 3

Extension repository on GitHub

Extension descriptor (YAML)

Zero-shot tabular machine learning inside DuckDB — classification and regression with real tabular foundation models (Mitra, TabPFN v2, TabICL, TabFM) on ONNX Runtime, no training loop

Installing and Loading

INSTALL anofox_tabfm FROM community;
LOAD anofox_tabfm;

Example

-- Fetch a real tabular foundation model once (Mitra, Apache-2.0, ~300 MB,
-- no license gate). Cached under ~/.cache/anofox-tabfm and reused after.
INSTALL httpfs; LOAD httpfs;                       -- weights are fetched over HTTPS
CALL tabfm_download('classification', model := 'mitra');

-- Label a few rows; leave the ones you want scored as NULL. The model reads
-- the labelled rows as in-context examples and predicts the rest — no training.
CREATE TABLE iris AS SELECT * FROM VALUES
  (5.1, 3.5, 1.4, 0.2, 'setosa'),
  (4.9, 3.0, 1.4, 0.2, 'setosa'),
  (7.0, 3.2, 4.7, 1.4, 'versicolor'),
  (6.4, 3.2, 4.5, 1.5, 'versicolor'),
  (6.3, 3.3, 6.0, 2.5, 'virginica'),
  (5.8, 2.7, 5.1, 1.9, 'virginica'),
  (5.0, 3.6, 1.4, 0.2, NULL),                      -- predict me
  (6.5, 3.0, 5.8, 2.2, NULL)                       -- and me
  AS t(sepal_len, sepal_wid, petal_len, petal_wid, species);

SELECT petal_len, petal_wid, yhat AS predicted_species, yhat_score
FROM tabfm_classify('iris', 'species', model := 'mitra')
WHERE species IS NULL;

About anofox_tabfm

anofox_tabfm embeds real tabular foundation models — TabPFN-style in-context learners — into DuckDB, so tabular classification and regression become a single SQL statement. There is no training loop, no Python, and no MLOps: the model reads your labelled rows as context and predicts the rest.

Built-in models

Four models ship in the extension and are selected with model := (or a SET anofox_tabfm_default_model once per session):

• mitra — AWS AutoGluon (Apache-2.0), no license gate, ~300 MB. A great default.
• tabpfn-v2 — Prior Labs (Apache-2.0, attribution).
• tabicl-v2 — Inria (BSD-3-Clause).
• tabfm-v1 — Google TabFM (non-commercial, gated; ~6.6 GB).

Only weight-free computation graphs are bundled — no model weights are distributed with the extension. You download the weights yourself from Hugging Face into a local cache (~/.cache/anofox-tabfm), and for the gated Google model you first accept its license (SET anofox_tabfm_accept_hf_license = true).

Bring your own model

Register any compatible model entirely from SQL — no external JSON manifest. Weights can be .safetensors or a native PyTorch .ckpt (read without Python):

CALL tabfm_register_model(
  id := 'my-model',
  classification_graph   := 'model.onnx',
  classification_weights := 'model.safetensors',
  license := 'apache-2.0');

Inference

Runs on ONNX Runtime, statically linked into the extension (CPU execution provider). CUDA and ROCm/MIGraphX flavors exist in the source tree for self-builds; this community build ships the portable CPU flavor.

Surface

• tabfm_classify / tabfm_regress — zero-shot predict (a single table with NULL targets, or a separate test := set)
• tabfm_predict, tabfm_predict_by, tabfm_predict_agg, tabfm_predict_win
• tabfm_register_model / tabfm_unregister_model — pure-SQL model registration
• tabfm_download / tabfm_models / tabfm_list_models / tabfm_load / tabfm_unload / tabfm_remove — all accept model :=
• tabfm_devices — discover CPU/GPU execution providers
• SET anofox_tabfm_* settings (default model, license gate, cache dir, threads, device, tracing)

Full function names are anofox_tabfm_* with short tabfm_* aliases. See the project repository for the full SQL API and examples.

Added Functions

Overloaded Functions

This extension does not add any function overloads.

Added Types

This extension does not add any types.

Added Settings