Create an Azure AI Foundry Resource and Project
1. Login to the Azure portal.
2. Search for “AI Foundry” in the search bar and open the service.
3. Under "Use with AI Foundry", select "AI Foundry".
4. Click on "Create".
5. Basics section:
-> Select the Subscription.
-> Select an existing Resource group from the dropdown, or create a new one.
-> Enter a Foundry Name. (no spaces, must be globally unique)
-> Select the Region.
-> Enter a Project Name.
Click ‘Next’.
6. Network section – Select preferred inbound access:
-> All networks – Any network, including the internet, can access this resource.
-> Selected networks – Configure network security for your Azure AI Foundry resource.
-> Disabled – No networks can access this resource, only private endpoint connections can be used.
Click ‘Next’.
7. Identity section – Choose the identity type:
-> System-assigned.
-> User-assigned.
Click ‘Next’.
8. Encryption section – If required, enable "Encrypt data using a customer-managed key".
Click ‘Next’.
9. Tags – (Optional) Add tags to organize and manage your resource.
Click ‘Next’.
10. Review + Create – Review all configuration details
Click "Create".
If the deployment is completed, then we can see that the creation got completed:
Deploying Model:
- Open the Foundry that we have created.
2. Click on the ‘Go to Azure AI Foundry Portal’
3. In Left side menu, click on ‘Models + endpoints’ in My assets section:
4. Click on ‘Deploy model’ -> ‘Deploy base model’
5. Select the model to get deployed:
6. Click on ‘Confirm’:
7. Click on ‘Deploy’:
8. Once it got deployed, we can see the Deployment info like below:
Configure App Registration to the AI Foundry:
1. Open the AI Foundry that we have created (TestResourceFoundry)
Click on ‘Access control (IAM)’
2. Click on ‘Add-> Add role assignment’
3. Select ‘Azure AI User’ and click on Next
4. Click on ‘+ Select members ‘
5. Select the App Registration that we have created and click on ‘Select’
6. Click on Next and Review + assign – Review all configuration details
Architecture:
Agents:
File Upload:
Uploading the files to the AI Foundry Project Knowledge Base.
Vector Store:
Vector Store will be saved in the AI Foundry Project, we can see in My Assets -> Data + indexes -> Vector Stores
Prerequisites:
- Active Azure subscription.
- Choose region.
- Existing resource group or create new one.
- Networking and encryption.