RAG But Better: Rerankers with Cohere AI - Improving Retrieval Pipelines
Offered By: James Briggs via YouTube
Course Description
Overview
Learn about rerankers and their role in optimizing retrieval pipelines for improved accuracy in Retrieval Augmented Generation (RAG) systems. Explore the differences between embedding retrieval and reranking, and discover how to implement retrieval pipelines with reranking using Cohere AI's reranking model and OpenAI's text-embedding-ada-002 model with Pinecone Vector Database. Gain insights into the problems of retrieval-only approaches, understand how embedding models and rerankers work, and follow along with a Python implementation. Compare retrieval results with and without reranking, and learn valuable tips for effectively utilizing rerankers in your AI projects.
Syllabus
Code :
RAG and Rerankers
Problems of Retrieval Only
How Embedding Models Work
How Rerankers Work
Implementing Reranking in Python
Testing Retrieval without Reranking
Retrieval with Cohere Reranking
Tips for Reranking
Taught by
James Briggs
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Natural Language Processing
Columbia University via Coursera Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent