Multi-Lingual Search With Cohere and LanceDB by Kaushal Choudhary Overview Cohere provides a Multi-Lingual Embedding model which promises to cross the language barriers in language models which were predominantly based on
Advanced RAG: Precise Zero-Shot Dense Retrieval with HyDE In the world of search engines, the quest to find the most relevant information is a constant challenge. Researchers are always on the lookout for
Multi-Modal AI made easy with LanceDB & CLIP by Kaushal Choudhary One of the most exciting areas of research in deep learning currently is multi-modality and its applications. Kick-started by open sourcing of
Simplest Method to improve RAG pipeline: Re-Ranking by Mahesh Deshwal Problem Statement: In a typical RAG pipeline, LLM Context window is limited so for a hypothetical 10000 pages document, we need to
Sentiment Analysis powered by semantic search using LanceDB Sentiment Analysis also known as Opinion Mining is a NLP technique that is used to analyze texts for polarity, from positive to negative. It helps
Better RAG with Active Retrieval Augmented Generation FLARE by Akash A. Desai Welcome to our deep dive into Forward-Looking Active Retrieval Augmented Generation (FLARE), an innovative approach enhancing the accuracy and reliability of
Multitask Embedding with LanceDB By Kaushal Choudhary In this blog, we’ll cover InstructOR embedding model and how it can be used with LanceBD. LanceDB embedding API already supports
NER-powered Semantic Search using LanceDB NER stands for Named Entity Recognition, a form of natural language processing (NLP) that involves extracting and identifying essential information from text. The information that
GPU-accelerated Indexing in LanceDB Vector databases are extremely useful for RAG, RecSys, computer vision, and a whole host of other ML/AI applications. Because of the rise of LLMs,
A Primer on Text Chunking and its Types Text chunking is a technique in natural language processing that divides text into smaller segments, usually based on the parts of speech and grammatical meanings
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,
