Vector search without breaking the bank: Quantization and Adaptive Retrieval скачать в хорошем качестве

Vector search without breaking the bank: Quantization and Adaptive Retrieval

Install NLP Libraries https://www.johnsnowlabs.com/install/ Watch all NLP Summit 2024 sessions: https://www.nlpsummit.org/nlp-summit-... This session shows how you use the open-source Weaviate vector database to perform real-time billion-scale vector searches – on your laptop! This includes covering different quantization techniques, including product, binary, scalar, and matryoshka quantization that can be used to compress vectors trading off memory requirements for accuracy. I’ll also introduce the concept of adaptive retrieval where you first perform a cheap hardware-optimized low-accuracy search to identify retrieval candidates using compressed vectors followed by a slower, higher-accuracy search to rescore and correct. These quantization techniques when used with well-thought-out adaptive retrieval can lead to a 32x reduction in memory cost requirements at the cost of ~ 5% loss in retrieval recall in your RAG stack. This session was presented by Zain Hasan, Senior Developer Advocate at Weaviate Connect with us: Our website: https://www.johnsnowlabs.com/ LinkedIn:   / johnsnowlabs   Facebook:   / johnsnowlabsinc   Twitter: @johnsnowlabs