RAG (Retrieval Augmented Generation) is the most common approach used to get LLMs to answer questions grounded in a particular domain's data. Learn how to build a RAG app using vCore-based Azure Cosmos DB for MongoDB and its new vector search capabilities. We'll walk through a Python web app that uses the LangChain package to orchestrate a RAG flow in order to answer questions about a restaurant's data.
Presented by Khelan Modi, Product Manager on Azure Cosmos DB team, and John Aziz, Software Developer and Microsoft MVP
** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **
📌 Check out the RAGHack 2024 series here! https://aka.ms/RAGHack2024
#MicrosoftReactor #RAGHack #AzureCosmosDB
Docs and more links:
Azure Cosmos DB for MongoDB vCore Free tier - https://aka.ms/tryvcore
Demo code - https://aka.ms/vcorelangchain
Additional samples, docs and more - https://aka.ms/CosmosAISamples
Try Azure Cosmos DB for Free, no credit card required - https://aka.ms/trycosmosdb
[eventID:23329]