JAJonathan Adlyinblog.colivara.com·Dec 2, 2024 · 8 min readUnlocking 70% Faster Response Times Through Token PoolingTLDRThis post examines improvements made to ColiVara, our ColPali-based retrieval API. We focus on hybrid search and hierarchical clustering token pooling. By benchmarking these two approaches, we aim to evaluate their impact on latency and performan...00
JAJonathan Adlyinblog.colivara.com·Nov 20, 2024 · 11 min readFrom Cosine to Dot: Benchmarking Similarity Methods for Speed and PrecisionBackground Retrieval Augmented Generation (RAG) empowers large language models (LLMs) by integrating private documents and proprietary knowledge, unlocking their potential for nuanced and informed responses. However, efficiently extracting informatio...00
JAJonathan Adlyinblog.colivara.com·Nov 14, 2024 · 8 min readOptimizing Vector Storage with halfvecsRAG (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...00
JAJonathan Adlyinjonathanadly.com·Nov 13, 2024 · 6 min readIs async django ready for prime time?We have traditionally used Django in all our products. We believe it is one of the most underrated, beautifully designed, rock solid framework out there. https://x.com/Jonathan_Adly_/status/1855357440034009362 However, if we are to be honest, the h...00
JAJonathan Adlyinblog.colivara.com·Nov 11, 2024 · 5 min readColiVara: a state of the art retrieval API with a delightful developer experience.We are launching ColiVara today! ColiVara is a state of the art retrieval API that stores, searches, and retrieves documents based on their visual embedding. End to end it uses vision models instead of chunking and text-processing for documents. In s...00
