Published on3 December 2025Implementing Spatially-Grounded Document Retrieval via Patch-to-Region Propagationragretrieval-augmented-generationvisionmultimodalcolpalidocument-retrievalcomputer-visionembeddingsvector-search'A deep dive into my recent research on spatially-grounded document retrieval using ColPali models and OCR bounding boxes, enabling precise region-level retrieval during inference time and without additional training.'
Published on28 October 2025Snappy: Your Vision Retrieval Buddy!ragretrieval-augmented-generationvisionmultimodalcolpaliqdrantminiofastapipythonvector-searchnextjsfrontenddocument-retrievalHow Snappy evolved from the nextjs-fastapi-colpali template into a vision-first document retrieval system
Published on22 August 2025You too can run the Vidore Benchmark with less than 32GB of GPU VRAMvidorebenchmarkcolpaliraggpu-poorpytorchmtebQuick, practical notes to run the Vidore benchmark smoothly on a single 32GB GPU: dtype, batch size, and common OOM fixes.
Published on15 August 2025The Most Beautiful RAG: Starring ColPali, Qdrant, Minio and Friendsragretrieval-augmented-generationvisionmultimodalcolpaliqdrantminiofastapipythonvector-searchnextjsfrontendbinary-quantizationAn end-to-end, page-level Vision RAG template with ColPali-style embeddings, Qdrant multivector retrieval (with optional binary quantization), and MinIO-backed storage — dockerized and API-first.
Published on12 August 2025ColQwen2.5 FastAPI Integrationfastapiembeddingsqdrantcoplpalicolqwenapi-developmentlittle-scriptsA little-script to create a FastAPI server for ColQwen2.5