What Comes After ChatGPT? Vector Databases - the Simple & Powerful Future of ML?
summary
Claims that vector databases (Weaviate, Pinecone, Chroma) store model embeddings to enable true semantic search, demonstrated with a hands‑on Weaviate Java client demo. Shows embeddings for text, images, audio and code, explains HNSW indexing and approximate nearest‑neighbor search for millisecond lookups even at trillions of embeddings, and outlines concrete uses: deduplication, RAG to feed ChatGPT relevant document chunks, anomaly detection, recommendations, and how distance thresholds return empty results when nothing is similar.
AI-written summary · about
chapters (17)
- 0:00Introduction to vector databases
- 1:27What is vector similarity search
- 5:22Why vector databases matter now
- 6:48Unstructured data explained
- 10:19How embeddings work
- 12:51Vector space and semantic context
- 14:37Visualizing word embeddings
- 17:09Semantic search with vectors
- 21:43How vector databases work
- 25:18Speed and performance of vector DBs
- 27:30Approximate nearest neighbor search
- 29:56Popular vector databases overview
- 33:06How to use a vector database
- 34:52Endless use cases for vector DBs
- 36:37Face similarity and intrusion detection
- 37:00RAG with vector databases and ChatGPT
- 40:39Q&A session
related talks
01h 03mWhat comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?
36mUnleashing the Power of Vector Databases for AI-Driven Applications
45mA gentle introduction to Vector Databases
48mEnter the Brave New World of GenAI with Vector Search
50mA fun and absurd introduction to Vector Databases
33mVector Databases for GenAI applications
33mEnter the Brave New World of GenAI with Vector Search
12mVector Databases: Why QA professionals Needs to Care About them in the Age of AI?