Vector Embeddings and RAG Demystified
summary
Shows how text is converted into vectors with Amazon Titan embeddings and a live Boto3 Bedrock client code sample that initializes a session, calls get_embedding, and returns embedding vectors. Explains using Amazon Bedrock knowledge bases to wire embeddings into a RAG flow with a retrieve and generate API for prompt augmentation. Demonstration runs end to end but presents no latency, accuracy, or scaling numbers and no retraining—just the integration and APIs.
AI-written summary · about
chapters (8)
- 0:00Introduction and Session Overview
- 0:46Understanding Vector Databases
- 2:23Large Language Models Explained
- 3:35Numerical Representation of Words
- 7:34Creating Embeddings with AWS
- 9:00Retrieval Augmented Generation (RAG)
- 11:57Amazon Bedrock Knowledge Bases
- 13:28Conclusion and Further Learning
related talks
48mUnderstanding Embedding Vectors and the RAG Pattern in AI Solutions
38mGenerative AI - Architectures and applications in depth
23mNo RAGrets
44mBuild RAG from Scratch
28mImproving responses in generative AI applications
44mEnhance Your Generative AI Applications with RAG
53mBuild RAG from Scratch
30mRAG: Tricks from the trenches.