Generative AI using Azure AI Integrated Search Vector Embeddings
In this video, we'll walk through how to use Azure AI Search integrated vector embeddings to index documents for Retrieval Augmented Generation. We'll create a new Azure AI Vector index, populate it with PDF data, and build a Streamlit Python application to interact with an OpenAI LLM using Azure AI Search as the data source.
Description
This video demonstrates how Azure AI Search integrated vector embeddings are used to index documents for Retrieval Augmented Generation (RAG) when using a large language model for generative AI Q&A solutions.
The video creates a new Azure AI Vector index, populates it with PDF data, and creates a Streamlit Python application to interact with an OpenAI LLM using Azure AI Search as RAG data source.
This video has an associated blog post with additional discussion and information here:
https://robkerr.ai/azure-ai-search-integrated-vector-embeddings/
Quick Links:
0:00 Introduction
0:41 Create Search Service
1:48 Create Index
4:42 Populate Index
5:47 Explore Vector Index
7:55 Streamlist App Demo
10:30 Summary