Python Package to convert image datasets to lance type 💡This is community post by Vipul Maheshwari A few months ago, I wrote two articles on how the Lance format can supercharge your machine-learning workflows.
LLMs powering Computer Vision tasks 💡This is a community post by Prashant Kumar Computer vision turns visual data into valuable insights, making it exciting. Now, with Large Language Models (LLMs)
An attempt to build cursor's @codebase feature - RAG on codebases - part 2/2 💡This is a community post by Sankalp Shubham What this looks like: Quick recap I recommend reading Part1 before you read Part 2. Part 1
An attempt to build cursor's @codebase feature - RAG on codebases - part 1/2 💡This is a community post by Sankalp Shubham The project will look something like this: Introduction If you have used the Cursor code editor'
Customer support bot with OpenAI's Swarm Agent 💡This is a community blog by Prashant Kumar Difference between an assistant and a Swarm Agent- an assistant is a simple sequential program without function
Practical introduction to Late Chunking or Chunked Pooling 💡This is a community blog by Mahesh Deshwal Improved Contextual Retrieval over large Documents for RAG applications The pronoun is the King (or Queen), and
Advanced RAG with context enrichment window .... and some advanced filtering and re-ranking technique We all know what's Vanilla RAG, how it works, and how to use it but sometimes
Implement contextual retrieval and prompt caching with LanceDB Decrease chunk retrieval failure rate by 35% to 50% Have you ever worked on a task where your users search in one language and the
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
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
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
