Downloads · 30 days
0
kaidjuric/daily-pipeline-director-cut
daily-pipeline-director-cut is a machine learning model from kaidjuric. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Point this Space at a folder of director-cut daily deep-dive HTMLs. The app auto-discovers, parses, and surfaces the corpus. Zero config.
Downloads · 30 days
0
Access
Public
Updated Aug 10, 2026
Repo size
182 KB
Likes
0
Public
Click a slice to open those files.
.html585 KB · 71%
From the Hugging Face model README
Point this Space at a folder of director-cut daily deep-dive HTMLs. The app auto-discovers, parses, and surfaces the corpus. Zero config.
DAILY_DIR/*.html
↓
parse_html() ← BeautifulSoup, ~26 ms / file
↓
load_corpus()
↓
aggregate() ← tab-weighted topic fingerprint
↓
Gradio UI ← 4 tabs: Corpus / Inspector / Trace / Raw JSON
DAILY_DIR*.html files following the daily deep-dive template (h1 + 8 .tab + 8 .panel with .card / .prompt / .verdict / .bench)DAILY_DIR → copy-driven empty state, no crashYYYY-MM-DD_<slug>.html into data/hf upload for an existing Space)docker build -t daily-pipeline .
docker run -p 7860:7860 -v "$PWD/data:/app/data" daily-pipeline
# or without Docker:
DAILY_DIR=./data python app.py