Artifacts

Builds a text corpus or dataset on a topic with an LLM and pushes it to your Hugging Face account.

Search for datasets that a language model generates on request, and save the ones you want.

Ultra-compact multilingual embedding model that runs in the browser for similarity search.

Swaps the delimiter in a CSV file, for example from commas to semicolons.

Rearranges CSV data so rows become columns.

Scans a CSV file for rows with missing or empty fields and lists them.

Inserts new columns into a CSV file at a position you choose.

Exchanges the positions of two columns in a CSV file.

Flips a CSV table so rows and columns trade places.

Searches Wikipedia passages using a quantized embedding retrieval method.

Search places and view American Community Survey demographics through the Census Reporter API.

Looks up US places and their American Community Survey statistics via the Census Reporter API.

Paste GeoJSON features, style fill and opacity, and see them drawn on an OpenStreetMap base layer.

Finds tables in pasted HTML or rich text, previews each one and exports it as CSV, TSV, JSON, Markdown or HTML.

Pulls out every string in a JSON document that is long or contains line breaks.

Browse and analyze large collections of machine learning model repositories in an interactive explorer.