Redefining Search: Vector Search with OpenAI and MongoDB
summary
Shows how to implement vector search using OpenAI embeddings together with MongoDB to enable semantic search, retrieval-augmented generation (RAG) and LLM-backed search. Covers why vector search powers semantic search and practical steps to set it up using OpenAI and MongoDB technologies.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 1:04Traditional vs vector search
- 4:18Vector theory and embeddings
- 10:00OpenAI vector generation
- 13:34MongoDB Atlas setup
- 18:57Practical implementation
- 23:57Summary and resources
related talks
30mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
28mUse OpenSearch as Your Vector Search Database To Optimize GenAI Accuracy!
47mBoosting AI With OpenSearch: Vector Stores, Similarity Search, and Retrieval-Augme...
26mBuilding generative AI–enriched applications with AWS & MongoDB Atlas
55mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
22mVector Search Made Simple: Getting Started With OpenSearch for AI Applications
50mHow to design and build AI applications with vector search using Azure OpenAI & Azure Cosmos DB
06mWhat makes vector databases essential for RAG and AI apps?