Build a RAG pipeline in LlamaIndex (simple)

Discover how to create powerful Retrieval Augmented Generation (RAG) systems using LlamaIndex. This tutorial covers everything from basic RAG pipelines and an advanced techniques called Router Queries. Learn how to enhance your AI applications with accurate, context-aware responses by leveraging your organization's proprietary data. Perfect for developers looking to build enterprise-grade, knowledge-intensive AI solutions.

Resources:
🛠️ GitHub repo: github.com/aws-samples/amazon-bedrock-samples/blob… and github.com/aws-samples/amazon-bedrock-samples/blob…
🌐 LlamaIndex: www.llamaindex.ai/
🌐 Amazon Bedrock: aws.amazon.com/bedrock/
📚 LlamaIndex Documentation: docs.llamaindex.ai/en/stable/

Follow AWS Developers!
📺 Instagram: www.instagram.com/awsdevelopers/?hl=en
🆇 X: x.com/awsdevelopers
💼 LinkedIn: www.linkedin.com/showcase/aws-developers/
👾 Twitch: twitch.tv/aws

Follow Stuart!
💻 GitHub: bigevilbeard.github.io/
🆇 X: x.com/bigevilbeard
💼 LinkedIn: www.linkedin.com/in/stuarteclark

00:00 - 00:14 Hook/Intro
00:14 - 00:29 Introduction to RAG
00:29 - 03:05 RAG Workflow
03:05 - 04:52 LlamaIndex Implementation
04:52 - 07:23 Advanced RAG Techniques - Router Query
07:23 - 09:07 Benefits of Advanced RAG Techniques
09:07 - 09:39 Call to Action/Close

#AmazonBedrock #LlamaIndex #RAG