How does RAG REALLY work?

angelo Leave a Comment

Event Timeslots (1)

Track 3 – 2024
Presenter: Jeff Maruschek

Abstract: "How many manuals are you expected to know cover to cover? How many different manuals are needed to be referenced for the same situation? You might be interested in RAG. Retrieval-Augmented Generation (RAG) is the process of optimizing the output of a large language model, so it references an authoritative knowledge base outside of its training data sources before generating a response. Large Language Models (LLMs) are trained on vast volumes of data and use billions of parameters to generate original output for tasks like answering questions, translating languages, and completing sentences. RAG extends the already powerful capabilities of LLMs to specific domains or an organization's internal knowledge base, all without the need to retrain the model. It is a cost-effective approach to improving LLM output so it remains relevant, accurate, and useful in various contexts. In this Session, Jeff Maruschek (AWS Sr. Solution Architect) will provide an overview of RAG, Context, Embeddings, and demonstrate both a fully built RAG chatbot application and AWS’s fully managed RAG offering, Knowledge Bases for Amazon Bedrock."

AWS Services: Bedrock, Lambda, Cloudfront, S3, and more

Audience: Beginner

angelo angelo

Leave a Reply

Your email address will not be published. Required fields are marked *