Unlocking 70% Faster Response Times Through Token Pooling
The magic of hierarchical clustering token pooling
Dec 2, 20248 min read
Command Palette
Search for a command to run...
Latest articles
From Cosine to Dot: Benchmarking Similarity Methods for Speed and Precision
An experiment on vision models and RAG
Nov 20, 202411 min read
Optimizing Vector Storage with halfvecs
RAG (Retrieval Augmented Generation) is a powerful technique that allows us to enhance large language models (LLMs) output with private documents and proprietary knowledge that is not available elsewhere. For example, a company's internal documents o...
Nov 14, 20248 min readColiVara: a state of the art retrieval API with a delightful developer experience.
ColiVara stores, searches, and retrieves documents based on their visual embedding.
Nov 11, 20245 min read