- Published on
Quick, practical notes to run the Vidore benchmark smoothly on a single 32GB GPU: dtype, batch size, and common OOM fixes.
Latest
A blog about everything, everywhere, all at once. 'Pun intended'
- Published on
An end-to-end, page-level Vision RAG template with ColPali-style embeddings, optional Next.js frontend, Qdrant multivector retrieval (with optional binary quantization), and MinIO-backed storage — dockerized, API-first, and optionally UI-powered.- Published on
A little-script to create a FastAPI server for ColQwen2.5- Published on
An audio RAG system that processes video URLs and answers questions about their content using ColQwen2.5-Omni and OpenAI audio- Published on
Introducing the first project in my little-scripts monorepo - A simple, yet beautiful RAG implementation using Colnomic, Qdrant and Nomic