To make LLM faster we need faster retrieval system. Here comes Embedding Quantization. Embedding quantization is great technique to save cost on Vector DB, significantly faster retrieval while preserving retrieval performance.
Unofficial Implementation of Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval and Evaluation of RAG system using "SEMALEX" evaluation metric .
Add a description, image, and links to the embedding-quantization topic page so that developers can more easily learn about it.
To associate your repository with the embedding-quantization topic, visit your repo's landing page and select "manage topics."