From the course: Enterprise AI Development with GitHub Models and Azure
Join today to access over 24,900 courses taught by industry experts.
Validating the solution with the Azure resources
From the course: Enterprise AI Development with GitHub Models and Azure
Validating the solution with the Azure resources
- [Instructor] Now that we have configured our Azure setup, we can have a look at how to use the model and the Azure OpenAI search together and convert the local script to use these new resources. We started with having our data source inside of a GitHub repository and then uploading it to an Azure storage account. Then, we configured an Azure AI Search resource to ingest the data from the storage account and then index the data using embeddings and storing this information as a vector index. We then used Azure OpenAI to ask a large language model questions and instructed it to ground the completions on the information stored in our vector index. We can now set up a solution that communicates with our Azure OpenAI resource and tell it to use the Azure AI Search to complete our prompt. I'll show this new script from inside of a GitHub codespace. I want to show the new setup with the Azure OpenAI SDK and send them prompts in the same way as the Azure AI Studio does. To get us started…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.