Tag
Educational article explaining FAISS, a library for billion-scale similarity search, covering vector embeddings, nearest neighbor search, and techniques like IVF and Product Quantization for efficient retrieval.
A developer built a multimodal semantic search over 68k artworks from the National Gallery of Art using Qwen3-VL-Embedding, FAISS, Modal, and Cloudflare R2. The system achieves warm response times of ~1.3s and cold starts of ~44s, supporting both text-to-image and image-to-image queries.
Benchmarks vector search libraries (Faiss, Scann, Usearch) for speed, memory, and accuracy across dataset sizes from 500 to 1 million samples, with results and code available.