Vector Search Made Simple: Getting Started with OpenSearch for AI Applications
summary
This talk explains how OpenSearch has evolved into a vector database for AI applications, supporting embeddings from text, images and audio. It covers the basics of vector databases (storing meaning as mathematical vectors) and similarity search techniques such as k-nearest neighbors, and shows concrete use cases enabled by this approach: semantic search, recommendation engines and visual search.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 1:53What is OpenSearch
- 3:43Search types explained
- 6:56Lexical search
- 13:04Lexical search limits
- 14:07Semantic search intro
- 15:33Dense vector search
- 22:36Vector search workflow
- 25:48LLMs with OpenSearch
- 26:29Hybrid search benefits
- 30:03Neural sparse search
- 34:25AI apps and frameworks
- 36:57Summary
- 39:26Resources
related talks
30mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
48mUnlocking Next-gen Semantic Search With OpenSearch 3.x
27mMachine Learning for Advanced AI Search
43mOpenSearch and the Path to a Trillion-scale Vector Database
59mContextual search with vector search: exploring your options with open source tools
22mThe Capabilities of Semantic Search
30mThe Unlimited Potential of Neural Search to Unlock the New Way of Data Comprehension
26mOpenSearch and the Path to a Trillion-s...