New Lance v0.16.1 Release, Random Access I/O, Hybrid Search+Reranking Report 🔥New release of Lance v0.16.1🔥 Lance v0.16.1 brings new features to help manage versions and Lance file format editions, a new
Training a Variational AutoEncoder from scratch with Lance file format Autoencoders encode an input into a latent space and decode the latent representation into an output. The output is often referred to as the reconstruction,
Multi document agentic RAG: A walkthrough 💡This is a community post by Vipul Maheshwari Agentic RAG (Retrieval-Augmented Generation) brings a notable improvement in how information is managed. While traditional RAG systems
Lance v0.16.1 Feature Roundup In Lance v0.16.1 we introduced several new features, implemented by a combination of LanceDB engineers and community contributors. Lance is an OSS project
Improve (almost) every retriever with LanceDB hybrid search and Reranking Retrieval is a key component of any type of recommender system, including RAG. The quality of responses generated by chatbot can only be as good
GraphRAG: Hierarchical approach to Retrieval Augmented Generation 💡This is a community blog by Akash Desai What is RAG? Retrieval-Augmented Generation (RAG) is an architecture that combines traditional information retrieval systems with large
The case for random access I/O One of the reasons we started the Lance file format and have been investigating new encodings is because we wanted a format with better support
My summer internship experience at LanceDB I'm Raunak, a master's student at the University of Illinois, Urbana-Champaign. This summer, I had the opportunity to intern as a
GraphRAG, Full-Text Search, LanceDB+Character.AI 🔥LanceDB as the Local Vector Database of Choice of GraphRAG🔥 Microsoft Research open sourced their GraphRAG project last week, and we are excited that the
Lance v0.15.0 Lance 0.15.0 introduces several experimental features, marking major milestones on important projects in our library. It exposes the first public APIs for full-text
Cambrian-1: Vision-Centric Search Cambrian-1 is a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can boost multimodal capabilities, the design choices for
Streamlining Our SDKs In the fast-evolving landscape of software development, maintaining multiple SDKs in various languages can be a challenging endeavor, especially for a small startup! Each bespoke
Zero shot image classification with vector search 💡This is community post by Vipul Maheshwari This post covers the concept of zero-shot image classification with an example. It is the process where a
