UV Scripts

Run a data or ML task over a Hugging Face dataset in one command: OCR, transcription, classification, embeddings, deduplication and more. Run it on your own machine, or on a pay-per-second GPU with Hugging Face Jobs. For people and coding agents.

Each recipe is one Python file with its dependencies declared inside it (UV script), so it runs straight from its URL: no clone, no virtualenv, no pip install. Most recipes read a Hub dataset and write a new one, so one recipe's output can be the next one's input.

Quickstart

First install the hf CLI. See the recipe families (no GPU, no account):

hf datasets ls --author uv-scripts

List a family's scripts without downloading them:

hf download uv-scripts/ocr --repo-type dataset --include "*.py" --dry-run

OCR seven scanned pages on a GPU from a NASA booklet. Sign in with a token that can write to your account; Jobs needs pre-paid credits. Replace your-username with your Hugging Face username (hf auth whoami shows it):

hf jobs uv run --flavor a10g-small --timeout 15m --secrets HF_TOKEN \
  https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py \
  uv-scripts/ocr-demo your-username/ocr-demo-results

This takes about 4 minutes on an a10g-small ($1.00/hour), so about $0.07. Most of that is startup. The Job saves a new dataset with a markdown column. Follow the OCR walkthrough to use your own scans or PDFs and to check the results.

Use it with your coding agent

A recipe runs from a URL and documents itself in its header, so a coding agent (Claude Code, Codex, Cursor, …) can pick one and run it with no setup. Paste this to start:

List the uv-scripts recipe families and tell me which fit my task:
  hf datasets ls --author uv-scripts
List a family's scripts with:
  hf download uv-scripts/<family> --repo-type dataset --include "*.py" --dry-run
Read the matching family's README on the Hub. Before running a script, read its header and docstring for the arguments and hardware.
Use my username from `hf auth whoami` for output datasets, and always set --timeout.

Using uv-scripts, OCR a sample dataset on Hugging Face Jobs. Find my username
with `hf auth whoami`, then run:
  hf jobs uv run --flavor a10g-small --timeout 15m --secrets HF_TOKEN \
    https://huggingface.co/datasets/uv-scripts/ocr/raw/main/glm-ocr.py \
    uv-scripts/ocr-demo <my-username>/ocr-demo-results
Then open the output dataset and show me the `markdown` column.

I need a dataset for <my task>. uv-scripts has recipes that create, OCR,
transcribe, classify, deduplicate and embed datasets on Hugging Face. List them:
  hf datasets ls --author uv-scripts
Pick the family that fits, read its README, then read the script's header and docstring: arguments, input and
output types, and the hardware it needs. Start with a small sample if the recipe
has a --max-samples option, choose a --flavor and an explicit --timeout, and run
it with `hf jobs uv run`. Check each step's output before chaining the next.

To teach your agent the rest of the hf CLI, install Hugging Face's hf CLI skill with hf skills add.

Built with uv-scripts

Most recipes tag the dataset card they push with uv-script, and many add a Reproduction section with the exact command. 386 datasets carry the tag (October 2026), from more than 40 accounts besides this org and its maintainer. Built something? Keep the tag so others can find it, and share the link.

Browse

Every recipe is in the list below: OCR, detection and segmentation, audio transcription, NER and classification, embeddings and atlas maps, batch LLM/VLM inference, synthetic data and dataset creation. Or browse on GitHub. Run hf jobs hardware for GPU flavors and prices.