What comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?
summary
Vector databases store model-generated embeddings for images, text, code and more, index trillions of vectors and answer similarity queries in milliseconds; demo uses open source tooling to build embeddings, store metadata, and run RAG with chunked docs so a few dozen chunks (not an entire corpus) fit ChatGPT token limits. Examples include Weaviate free tier 10,000 vectors for local or hosted testing and Pinecone $700M Series B as a cloud-only provider; use cases: semantic search, recommendations, anomaly detection and retrieval-augmented generation.
AI-written summary · about
chapters (8)
- 0:00Vector databases introduction
- 3:18ChatGPT limitations
- 7:33Vector databases trend
- 10:42Unstructured data & embeddings
- 25:11Semantic search with vectors
- 32:20Popular vector databases
- 39:53Vector DB use cases
- 57:29Q&A
related talks
50mWhat Comes After ChatGPT? Vector Databases - the Simple & Powerful Future of ML?
33mVector Databases for GenAI applications
58mDemystifying GenAI: Build a ChatGPT App with Vector Store
36mUnleashing the Power of Vector Databases for AI-Driven Applications
48mEnter the Brave New World of GenAI with Vector Search
45mA gentle introduction to Vector Databases
34mEnter the Brave New World of GenAI with Vector Search
17mThe keys to success with Generative AI and Vector Databases