---
title: Data-use Extraction — WebGPU
emoji: 🐈
colorFrom: indigo
colorTo: blue
sdk: static
sdk_version: 1.0.0
pinned: false
license: apache-2.0
short_description: In-browser data-use extraction on WebGPU
---

# Data-use Extraction — WebGPU

Fully client-side demo that extracts data mentions from research text and
attributes each one with provenance and usage/impact — all running locally in
your browser on WebGPU. No server, no uploads; nothing leaves your machine.

## Pipeline

```
text
  → span model (GLiNER)          → mention spans + specificity
  → LFM2.5-350M multitask        → provenance {producer, year, geography, acronym}
                                   + usage/impact {data_type, usage_action, impact_label, usage_summary}
  → verbatim filter → render
```

## Models

| stage | model | HF repo |
|---|---|---|
| span detection | GLiNER | [`rafmacalaba/gliner_datause_extended-onnx`](https://huggingface.co/rafmacalaba/gliner_datause_extended-onnx) |
| attribution | LFM2.5-350M multitask | [`rafmacalaba/lfm2.5-350M-datause-multitask-onnx`](https://huggingface.co/rafmacalaba/lfm2.5-350M-datause-multitask-onnx) |

Models download from the Hub on first load and are cached in your browser's
IndexedDB. Requires a WebGPU-capable browser (Chrome/Edge with WebGPU enabled).

## Run locally

```bash
git clone https://github.com/rafmacalaba/ai4data-playground.git
cd ai4data-playground/web && python3 -m http.server 8000
# open http://localhost:8000
```