Optimizing LLMs: A Step-by-Step Guide to Fine-Tuning with PEFT and QLoRA A Practical Guide to Fine-Tuning LLM using QLora Conducting inference with large language models (LLMs) demands significant GPU power and memory resources, which can be
Serverless Multi-Modal search engine application by Ayush Chaurasia In this writeup, you’ll learn the process of building a multi-modal search engine using roboflow’s CLIP inference API and LanceDB,
Context-aware chatbot using Llama 2 & lanceDB serverless vector database Building a real chatbot using RAG method – by Akash A. Desai Introduction: Many people know about OpenAI’s cool AI models like GPT-3.5 and
LLMs, RAG, & the missing storage layer for AI by Ayush Chaurasia In the rapidly evolving landscape of artificial intelligence, Generative AI, especially Language Model Machines (LLMs) have emerged as the veritable backbone of
Improving LLM-based web applications with easy-to-use and free serverless vector database LanceDB by Tevin Wang I believe that there are currently two major challenges using LLMs. (1) outdated information (ChatGPT has limited knowledge of the world and
S3 Backed Full-Text Search with Tantivy (Part 1) by Rob Meng Tantivy is a highly performant full text search library written in Rust. The python version of tantivy powers the full-text search (FTS)
Maximizing Developer Workflows using Lance and Claude 2 by Leon Yee Introduction Just a few days ago, I went to Anthropic’s Hackathon, where hackers utilized their Claude 2 APIs to build some
Reduce Hallucinations from LLM-powered Agents using Long-Term Memory Introduction to Critique-Based Contexting with OpenAI, LangChain, and LanceDB
Scalable Computer Vision with LanceDB & Voxel51 Importance of dataset analysis in CV Dataset analysis is an essential step in any computer vision project. It allows us to understand the data that
You can now delete rows in Lance and LanceDB! by Will Jones Starting in Lance 0.5.0, you can delete rows in Lance datasets. Up until now, we’ve only supported adding new
Demystifying LLM Apps with Lance There’s a lot of justifiable excitement around using LLMs as the basis for building a new generation of smart apps. While tools like LangChain
