Enter the Brave New World of GenAI with Vector Search
summary
Overview of generative AI plus practical vector search fundamentals: explains that text and multimedia become numeric vector embeddings stored as arrays of floats, that similarity uses approximate nearest neighbor (ANN) indexes, and that OpenAI embeddings are 1,536 dimensions (newer models approach 16k). Mentions frameworks and runtimes: LangChain, LlamaIndex, Hugging Face, JLama, JVector, LangChain4J, and vector DBs like Pinecone, Weaviate, PgVector, Milvus. Promised demo isn’t run live here but slides and Twitch/YouTube demos are available; warns about hallucinations and RAG for fresh data.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 0:56Agenda
- 2:12Who is Mary
- 2:51Background of AI
- 6:34GenAI
- 10:16New Players
- 16:13GenAI Terminology
- 18:11NLP
- 19:01Large Language Models
- 22:53Vector Database
- 29:38Challenges
- 31:57Resources
related talks
48mEnter the Brave New World of GenAI with Vector Search
57mEnter the Brave New World of GenAI with Vector Search
34mEnter the Brave New World of GenAI with Vector Search
57mEnter The Brave New World of GenAI with Vector Search
49mEnter the Brave New World of GenAI with Vector Search
33mEnter the Brave New World of GenAI with Vector Search
33mVector Databases for GenAI applications
01h 46mVector Databases (for GenAI & beyond)