🚀 New short course with Qdrant: Multi-vector Image Retrieval. Taught by Kacper Łukawski, Senior Developer Advocate at Qdrant, the course shows how multi-vector techniques outperform single-vector methods by matching text tokens to image patches directly. You’ll implement ColBERT to understand multi-vector search, apply ColPali for patch-level image retrieval, reduce memory with quantization and pooling, and use MUVERA to enable fast HNSW search. The course concludes with a full multi-modal RAG

31K views · 306 reactions | Creating a visual analogy system requires understanding deep image retrieval. In this on-demand webinar, researcher Mark Hamilton shows how mapping a query image into deep feature space and using conditional nearest neighbors uncovers exciting artwork pairs. Watch now: https://aka.ms/AA96b95 | Microsoft Research | Facebook