Azure OpenAI
Last updated
Last updated
The Azure OpenAI integration feature in Datasaur's LLM Labs allows you to seamlessly integrate your own Large Language Models (LLMs) into the platform. This functionality provides three key benefits:
Integrating your own LLMs: This feature enables you to bring your own models into LLM Labs. Datasaur will retrieve all available Azure OpenAI models based on your credentials. Once connected, these models will be accessible to all workspace members.
Protect your data: By using your own LLMs, you can ensure better security compliance, providing you with complete control and privacy over your data.
Streamlined workflow: Access your preferred models directly within Datasaur's user-friendly interface, simplifying your LLM workflows to allows you to gain insights about your model's performance by comparing it to other models, both within and outside of Azure.
Navigate to the Models page under LLM Labs menu.
Open My models tab, and click the Manage providers button.
Choose Azure OpenAI as the provider, and insert your Tenant ID, Subscription ID, Resource group name, and Account name.
If this is your first time integrating Azure Open AI with Datasaur, click the Add Datasaur to your Azure Tenant button to grant consent for Datasaur's App Registration to your tenant. If you have previously done this, you can skip this step.
You must have at least the Privileged Role Administrator role to grant consent to App Registrations for delegated access. Continue the process on a new tab and authorize the Datasaur app. Note that you need Admin permission to complete this action.
Grant role assignments to Datasaur's Service Principal
Still in the Azure OpenAI Account, find Access Control (IAM) on the sidebar.
Click on Add > Add role assignment.
Select Cognitive Services OpenAI Contributor, then click Next.
In Assign access to, click on User, group, or service principal, then click select members.
Search for Datasaur Azure AI Integrator (you cannot see the service principals from the list, you must search for them), then add it. This step will not be available if you haven't added Datasaur to your Azure tenant as described above.
Proceed by clicking "Next" and then click "Next" once more when you reach the Conditions section.
Click on Review + assign.
Getting the Tenant ID:
Go to your Microsoft Entra ID from the Azure portal. To learn more about Microsoft Entra ID, please visit this link.
Under the Overview tab, copy the Tenant ID attribute under the Basic information section.
Getting the Subscription ID, Resource Group Name, and Account Name:
Go to the Azure OpenAI page from the Azure portal.
Create or select an Azure OpenAI Account.
From the sidebar, click on Overview menu.
You should find these fields under the Essentials section Subscription ID should be available as “Subscription ID” Resource Group Name should be available as “Resource group” Account Name is the name of the selected Azure OpenAI Account.
Once you have connected your Azure OpenAI Models to LLM Labs, you will see a list of available LLM Models that you have already deployed in Azure OpenAI. You can immediately use these models within LLM Labs.
Every new model that you deploy in Azure OpenAI will be synced to Datasaur, and you can use it right away in Datasaur. If the models you just deployed haven't appeared on Datasaur, you can click Sync models.
Datasaur supports a wide range of models available in Azure OpenAI. You can find the list of supported models here: Azure OpenAI Models.
Currently, Datasaur only provides support for text generation Large Language Models.
Additionally, you can bring your own fine-tuned models from Azure OpenAI into Datasaur, allowing for greater customization and performance tailored to your specific use cases.
This section provides a step-by-step guide to integrate Azure Open AI with Datasaur's LLM Labs using a certificate for secure authentication. Follow the instructions below to generate credentials, upload the certificate to Azure, and connect Azure Open AI to LLM Labs.
If you are connecting to Azure OpenAI using a certificate, note that only the deployment name that matches the format modelName-modelVersion will be integrated with LLM Labs.
To integrate Azure Open AI using a certificate, you need to generate a private key, extract the public key, and combine them into a single PEM file.
Generate a private key
If you don’t have a private key, generate one using the following command:
openssl genpkey -algorithm RSA -out private.pem -aes256
Extract the public key from the private key
Use the private key to generate a public key in .pem format:
openssl rsa -in private.pem -pubout -out public.pem
Combine keys into one PEM file
Combine the private and public keys into a single .pem file:
cat private.pem public.pem > fullkeys.pem
Access Azure Portal: Log in to the Azure Portal.
Navigate to App Registrations
Go to Azure Active Directory > App registrations.
Select your application.
Upload the certificate
In the left menu, go to Certificates & secrets.
Under the Certificates section, click Upload certificate.
Choose your .pem (public key) file and upload it.
Retrieve Tenant ID and Client ID
On your application page, go to the Overview section.
Copy the Tenant ID and Client ID. These will be required to connect Azure Open AI to LLM Labs.
Ensure your application has access to the Azure Open AI service you want to connect to.
Navigate to the Models catalog in your Datasaur workspace, and click the Manage providers button.
Choose Azure OpenAI as the provider, and select Azure tenant application certificate.
Enter your Tenant ID, Client ID, and Azure OpenAI endpoint.
Upload the .pem file containing both the private and public keys (created in Step 1).
To disconnect Azure OpenAI from Datasaur, follow these steps:
Go to the Models page under the LLM Labs menu.
Open My models tab and select Manage providers.
Click See details next to the Azure OpenAI provider.
Click Disconnect and confirm the action.
The model will be accessible to all workspace members for use in their projects. Additionally, only the Admin can remove the Azure OpenAI provider from the workspace.
Integrating your own Azure OpenAI models with Datasaur not only enhances functionality but also ensures that your data remains secure and compliant with your organization's policies. By leveraging your own LLMs, you gain greater control, customization, and security for your AI applications.
For further assistance or to get started, please reach out to our support team at support@datasaur.ai.
