Enter the Brave New World of GenAI with Vector Search
summary
45-minute primer that explains why GenAI needs vector embeddings for similarity search, shows the RAG (retrieval-augmented generation) pattern combining a retrieval index with an LLM, and names tools you can use today: LangChain4J, LlamaIndex, Semantic Kernel, Hugging Face and vector stores like PGVector, Milvus, Chroma, Weaviate and FAISS. Covers embeddings as multi-dimensional float arrays, ANN nearest-neighbor searches, the 1 billion users in five days milestone for ChatGPT, common hallucination risks, and promises a hands-on workshop/demo the next day.
AI-written summary · about
chapters (10)
- 0:00Introduction to GenAI
- 3:54AI Background and Basics
- 12:05Generative AI Explained
- 15:59Generative AI Models Overview
- 20:14AI Applications and Ethics
- 24:45Key Terminologies in GenAI
- 30:29Working with LLMs
- 35:05RAG Architecture
- 38:57Vector Databases
- 45:41GenAI Benefits and Challenges
related talks
33mEnter the Brave New World of GenAI with Vector Search
57mEnter 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
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
50mWhat Comes After ChatGPT? Vector Databases - the Simple & Powerful Future of ML?