Armchair Architects: LLMs & Vector Databases (Part 1)

Estimated read time 2 min read

Post Content

​ Vector databases are designed to store, manage, and index massive quantities of high-dimensional vector data efficiently that can help different types of queries, such as nearest neighbor. In this episode of the #AzureEnblementShow, Uli, Eric and David discuss how vector databases convert data to integers, cover some of the use cases of vector databases, and the benefits of embedding. This is part one of a two-part series.

Resources
• Vector search in Azure AI Search https://learn.microsoft.com/en-us/azure/search/vector-search-overview
• Geospatial data processing and analytics https://learn.microsoft.com/en-us/azure/architecture/example-scenario/data/geospatial-data-processing-analytics-azure
• Microsoft Azure AI Fundamentals: Natural Language Processing https://learn.microsoft.com/en-us/training/paths/explore-natural-language-processing/
• Azure Database for PostgreSQL https://learn.microsoft.com/en-us/training/paths/introduction-to-azure-postgres/
• Vector DB Lookup tool for flows in Azure AI Studio https://learn.microsoft.com/en-us/azure/ai-studio/how-to/prompt-flow-tools/vector-db-lookup-tool

Related episodes
• Watch more episodes in the Armchair Architects Series
https://aka.ms/azenable/ArmchairArchitects
• Watch more episodes in the Well-Architected Series
https://aka.ms/azenable/yt/wa-playlist

Chapters
0:00 Introduction
0:38 Data stored as integers
1:30 Text converted to numerical data
2:29 Vectors are not new
3:47 Use cases
5:02 Benefits of Embedding
7:40 Vectorizing semantic concepts
8:38 Teaser for Part 2   Read More Microsoft Developer 

You May Also Like

More From Author

+ There are no comments

Add yours