Spaces:
Running
Running
|
Download README.md from raphaelmansuy/edgextract: direct link, hf CLI and curl.
- Browser
- Download file 1.34 kB
-
https://huggingface.co/spaces/raphaelmansuy/edgextract/resolve/main/README.md
- Command line
-
hf download hf://spaces/raphaelmansuy/edgextract/README.md
-
curl -L -o README.md https://huggingface.co/spaces/raphaelmansuy/edgextract/resolve/main/README.md
1.34 kB
metadata
title: edgextract
emoji: 🕸️
colorFrom: gray
colorTo: indigo
sdk: static
app_file: index.html
pinned: false
license: apache-2.0
short_description: Markdown in, a knowledge graph out. Tev1 on WebGPU.
custom_headers:
cross-origin-embedder-policy: credentialless
cross-origin-opener-policy: same-origin
cross-origin-resource-policy: cross-origin
edgextract
Turn markdown into a knowledge graph with an ontology you write and a cutoff you own. It runs in this tab (Rust → WebAssembly + Tev1 on WebGPU). Your text never goes to our server.
Open the Space on *.hf.space (not only the Hub iframe) so SharedArrayBuffer / WebGPU isolation works.
- First Load Tev1 downloads ~1 GB from
raphaelmansuy/tev1-0.8b-onnx-webgpuinto the browser cache. - Chromium with WebGPU.
- This hosted page cannot call
127.0.0.1Ollama. Optional remote host:?backend=ollama&host=https://…plusOLLAMA_ORIGINS.
Source: github.com/raphaelmansuy/edgextract · also on GitHub Pages. Attribution: third-party notices.