Got a digitised collection that needs OCR? uv-scripts is a set of single-file Python scripts that OCR a whole image dataset to markdown in one command — 20+ open VLMs to pick from, nothing to install but uv. github.com/davanstrien/...
Who's Who of AI
Daniel van Strien
Machine Learning Librarian at Hugging Face
Machine Learning Librarian at @hf.co
What they're sharing
GitHub - davanstrien/uv-scripts-for-ai: Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents. github.com
Dataset Lineage Explorer - a Hugging Face Space by davanstrien huggingface.co
huggingface.co
DiffusionGemma vs Gemma-4 — Post-OCR Correction - a Hugging Face Space by davanstrien huggingface.co
Archival Index Card Detector - a Hugging Face Space by small-models-for-glam huggingface.co
huggingface.co
huggingface.co
huggingface.co
AI Design Patterns for Information Professionals danielvanstrien.xyz
danielvanstrien.xyz
12 Extending a Community Model – AI Design Patterns for Information Professionals danielvanstrien.xyz
Articles & links
Derived datasets are bigger on Hugging Face Hub than people realise. ~73% of analysed datasets on the Hub are derivatives of something else, i.e. cleaned, translated, extended, etc. Built an explorer that infers the missing lineage from content: huggingface.co/spaces/davan...
You can now run SQL over 2.19 BILLION web pages — zero download. @commoncrawl.bsky.social April 2026 crawl + URL index are on Hugging Face Storage Buckets. DuckDB reads it straight over hf:// — I counted all 2.19B in ~35s. Or point your own agent at it 👇 huggingface.co/spaces/…
Try it: live demo on @hf.co ZeroGPU with the step-by-step denoising replay, side-by-side diffs vs the human transcription, and the full benchmark table. huggingface.co/spaces/davan...
Demo for the model: huggingface.co/spaces/small...
Zero-setup UV script, runs on HF Jobs: huggingface.co/datasets/uv-... Example: 49 NLS Advocates Library cards → JSON: huggingface.co/datasets/dav... Model by NuMind: huggingface.co/numind/NuExt...
Zero-setup UV script, runs on HF Jobs: huggingface.co/datasets/uv-... Example: 49 NLS Advocates Library cards → JSON: huggingface.co/datasets/dav... Model by NuMind: huggingface.co/numind/NuExt...
Zero-setup UV script, runs on HF Jobs: huggingface.co/datasets/uv-... Example: 49 NLS Advocates Library cards → JSON: huggingface.co/datasets/dav... Model by NuMind: huggingface.co/numind/NuExt...
What is "AI for libraries" beyond a catalogue chatbot? IMO: design patterns (OCR, extraction, classification, search), and agents that both run them and develop the small models behind them. As part of work with @natlibscot.bsky.social started a book on this: danielvanstrien.x…
Built a useful GLAM model this week: flags blank index cards before expensive OCR. Cheap, scales, adapts. IMO the technical barrier is now very low, the main one is knowing how. So I wrote this up as a chapter: danielvanstrien.xyz/ai-patterns-for-glam/patterns/index-card-class…
Recipe for doing this: danielvanstrien.xyz/ai-patterns-for-glam/patterns/extending-a-community-model.html
Their own posts
Recent commentary
NuExtract3 (4B, Apache-2.0) does OCR *and* structured extraction. Point it at a dataset of scanned index cards + a JSON schema → clean catalog JSON One command on huggingface Jobs. (or skip the schema for plain Markdown OCR) Script + dataset 👇
What could a rich ecosystem of small GLAM AI models enable? IMO: cheaper, better-fitted, more robust models. Example: I extended an existing @natlibscot.bsky.social archival card detector to 4 collections to make a more generic index card detector. Took an hour or two and minimal $
Their network
In Daniel van Strien's orbit
Center = Daniel van Strien. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.