Amir Ingber

Accurate and Efficient Metadata Filtering in Pinecone’s Serverless Vector Database

Results of the Big ANN: NeurIPS'23 competition

Bridging Dense and Sparse Maximum Inner Product Search

RAG makes LLMs better and equal

Pinecone algorithms set new records for BigANN

An Approximate Algorithm for Maximum Inner Product Search over Streaming Sparse Vectors

An Analysis of Fusion Functions for Hybrid Retrieval

SDR: Efficient Neural Re-ranking using Succinct Document Representation