cilabuniba/artseek
ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval
Combines late-interaction dense retrieval (ColQwen2) with a specialized multi-head classifier (LICN) to predict artwork attributes, then feeds both retrieved Wikipedia fragments and predictions into Qwen2.5-VL-32B for open-ended reasoning. Built on Qdrant vector search over 5M+ multimodal Wikipedia fragments and requires ~250 GB disk storage plus significant compute (A100-class GPU) for inference and indexing pipelines.
Stars
10
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/cilabuniba/artseek"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AnswerDotAI/byaldi
Use late-interaction multi-modal models such as ColPali in just a few lines of code.
illuin-tech/colpali
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
jolibrain/colette
Multimodal RAG to search and interact locally with technical documents of any kind
nannib/nbmultirag
Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG,...
OpenBMB/VisRAG
Parsing-free RAG supported by VLMs