You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Star0 (0)You must be signed in to star a repository
About
This project focuses on developing a scalable vector database system optimized for dense passage retrieval, leveraging the MS-MARCO v2 dataset containing 8.84 million passages. Using advanced big data technologies and vector indexing algorithms, the system addresses challenges of retrieval latency and accuracy in large-scale datasets.
This project focuses on developing a scalable vector database system optimized for dense passage retrieval, leveraging the MS-MARCO v2 dataset containing 8.84 million passages. Using advanced big data technologies and vector indexing algorithms, the system addresses challenges of retrieval latency and accuracy in large-scale datasets.
