From the course: Azure for Developers: Retrieval-Augmented Generation (RAG) with Azure AI

Unlock this course with a free trial

Join today to access over 24,600 courses taught by industry experts.

Creating a RAG solution with Azure AI Foundry

Creating a RAG solution with Azure AI Foundry - Azure AI Services Tutorial

From the course: Azure for Developers: Retrieval-Augmented Generation (RAG) with Azure AI

Start my 1-month free trial Buy for my team

Creating a RAG solution with Azure AI Foundry

“

- [Instructor] This course is focused on creating a RAG solution in Azure using the Python SDKs. However, I would like to demonstrate that you can also create one using Azure AI Foundry. We start by going to ai.azure.com and create a project. - The user interface that you see right now may look different by the time you see this recording, but the concepts will always remain the same. You need to create an Azure AI search service to set up your data source. Project creation provisions a lot of new Azure resources, so it will take a while. Once the project is created, you then need to deploy two models. We need to take note of the token limit assigned. The chat completion model would be gpt-4 Omni to contain our data and embeddings. We will create a new index, we will then upload our documents, which are PDF files that contain our product data. We then assign an appropriate name for our index. We also need to make sure that vector search is enabled. The index creation will take a…

Contents