Getting Started With Vector Databases
summary
Explains that vector databases store vectors alongside originals so semantic similarity returns meaning not keywords and scales to billions of documents; demos use we8 and a Verba demo to build a book recommender, a supplement/health search, and a multimodal demo using ImageBind that actually returns matching images audio and video; shows retrieval‑augmented generation that supplies context to LLMs to cut hallucinations and demonstrates a generative feedback loop that persists and deletes memories in the vector store.
AI-written summary · about
chapters (11)
- 0:00Vector databases introduction
- 2:09Keyword search problems
- 4:55Semantic search with vectors
- 10:57Vector search applications
- 14:51Multimodal embeddings
- 20:55LLMs and vector databases
- 26:22Contrasting vector databases and large language models
- 29:31Demo of retrieval augmented generation
- 32:40Why RAG matters
- 37:14Memory feedback loops
- 40:21Closing
related talks
45mA gentle introduction to Vector Databases
57mUsing Vector Databases for Multimodal Embeddings and Search
01h 23mVector Databases Demystified: Discover how they work
48mA fun and absurd introduction to Vector Databases
33mVector Databases for GenAI applications
39mWhat's in a Vector Database?
50mA fun and absurd introduction to Vector Databases
48mA Fun & Absurd Introduction to Vector Databases