Vector Databases for GenAI applications
summary
Vectors encode text, images, audio and video into numeric embeddings and semantic search returns the top-N most relevant chunks; demo uses Amazon OpenSearch + pgvector-style stores, LangChain and a Streamlit UI to query a chunked Amazon shareholder PDF and shows embeddings of size 1536. Retrieval Augmented Generation is implemented by querying the vector store (top 10 results), concatenating those chunks into a prompt and calling an LLM; demos run end-to-end and produce sourced answers via retrieval augmented generation and Amazon Bedrock knowledge bases.
AI-written summary · about
chapters (7)
- 0:00Introduction and context
- 2:40LLM limitations and RAG
- 7:17Vector databases explained
- 13:17Semantic search demo
- 21:06Implementing RAG
- 24:20Managed RAG platforms
- 26:44Bedrock demo and wrap-up
related talks
57mEnter The Brave New World of GenAI with Vector Search
33mEnter the Brave New World of GenAI with Vector Search
48mEnter the Brave New World of GenAI with Vector Search
41mGetting Started With Vector Databases
01h 03mWhat comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?
36mUnleashing the Power of Vector Databases for AI-Driven Applications
31mRetrieval Augmented Generation
45mA gentle introduction to Vector Databases