Machine Learning for Advanced AI Search
summary
Claims that embeddings come from Amazon Bedrock and get stored in either Amazon OpenSearch or PostgreSQL with PGVector and demonstrated a small product‑catalog prototype with 4 sample embeddings inserted then queried by Euclidean distance, returning the top 2 results as expected. The example shows native vector columns, three similarity metrics (Euclidean, cosine, inner product), hybrid SQL + vector filtering, and a working nearest‑neighbor query on Aurora/RDS without a separate vector database.
AI-written summary · about
chapters (13)
- 0:00Introduction to Machine Learning for Advanced AI Search
- 0:32Understanding Generative AI
- 1:47Foundation Models Explained
- 3:13Inputs and Outputs of Foundation Models
- 5:15Customizing Foundation Models
- 8:57Introduction to Vectors in Machine Learning
- 10:04Vector Embeddings and Their Importance
- 11:23Vector Stores and Databases
- 12:59Exploring AWS Vector Data Stores
- 16:10PostgreSQL and PG Vector for Vector Databases
- 19:01PG Vector: Features and Use Cases
- 20:18Querying with PG Vector
- 25:07Summary and Conclusion
related talks
33mVector Databases for GenAI applications
59mContextual search with vector search: exploring your options with open source tools
22mVector Search Made Simple: Getting Started With OpenSearch for AI Applications
27mUnified AI & Relational Power: Scalable Distributed Vector Search with
27mUse AI Vector Search to Build GenAI Apps with Enterprise Data
30mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
33mBringing Vector Search to OLTP
57mEnter The Brave New World of GenAI with Vector Search