Skip to main content

Azure GPT

For your own Azure OpenAI deployment, you need an existing Azure enterprise account that you have access to. If your company already has a normal Azure account, you can simply use it for this guide.

This guide will do following steps:

  • In your Azure account create Azure OpenAI, for which currently there is a waiting list.
  • In Azure OpenAI add models for gpt-35-turbo, gpt-4, gpt-4o, gpt-4o-mini and text-embedding-ada-002.
  • For these models request an increased rate limit so you can handle more requests per second.

Step 1: Start Creating Azure OpenAI​

  • In Azure type OpenAI into Azure search and select Azure OpenAI
  • The screen should show No Azure OpenAI to display and a button Create Azure OpenAI. Click this button.
  • The screen Create Azure OpenAI with tabs Basics, Network, Tags, Review + submit should show up.

Create Azure OpenAI

  • A red message box might show

Azure OpenAI Service is currently available to customers via an application form. The selected subscription has not been enabled for use of the service and does not have quota for any pricing tiers. Click here to request access to Azure OpenAI service

  • Click onto the red message box so that form Request Access to Azure OpenAI Service opens. If there is no such red message box, go to step 3 of this guide.

Step 2: Fill out form "Request Access to Azure OpenAI Service".​

Request Access

  • Enter first name, last name
  • Enter Azure subscription ID. You can find the Azure subscription ID by search for Subscription or Abonnements in Azure search.
  • Enter company email address, company name, company street address, company city, company state (e.g. NRW), company zip code, company country, company website, company phone number
  • Enter at Is your organization an ISV, SI, or MSP value None, if your company is none of the listed values
  • Enter company size, company category, company industry
  • Microsoft contact details if available
  • Confirm Please confirm this application is for your own company and you are not applying on behalf of your customer.
  • Select West Europe if your company is in Europe for data protection reasons.

Question 21

  • Select Text and code models

Question 22

  • Select use cases Chat and conversation interaction, Question-answering and Summarization
  • Attest Azure Legal Terms
  • Attest Data Processing details
  • Click Send and following text will show up

Thank you for your application for Azure OpenAI Service. If you submitted an experimentation or production review for Azure OpenAI’s text or code models, we will review your application within approximately 10 business days. If you expressed interest in the invite-only preview of DALL-E, we thank you for your interest. We may reach out in the future but are unable to offer information about timelines or guarantee onboarding.

  • Wait 10 days until you are informed via email about the decision.
  • If you have a key account manager at Microsoft, this person might be able to speed up the decision for you.

Step 3: Complete Creating Azure OpenAI​

  • In Azure type OpenAI into Azure search and select Azure OpenAI
  • Click button Azure OpenAI
  • The screen Create Azure OpenAI should show up, now without the red message box.

Create Azure OpenAI Basics

  • In Azure OpenAI > Basics
    • Select a subscription and if necessary at Resource group click Create new with arbitrary name such as openai
    • In Region select one of Sweden Central, Switzerland North, France Central, in name enter e.g. companyname-openai and as pricing select Standard S0.
    • The available regions differ with respect to model avalailability and latency. Currently, for Europe Sweden Central has the newest and most models.
    • Click Next
  • In Azure OpenAI > Network keep the preselected value All networks, including the internet, can access this resource. and click Next
  • In Azure OpenAI > Tags click Next
  • In Azure OpenAI > Review + submit click Create

Create Azure OpenAI Submit

  • Deployment is in progress will show up. Then Your deployment is complete will show up.
  • Click Go to resource to open the deployment.

Create Azure OpenAI Deployment

  • Under menu item Keys and Endpoint you find access keys and an endpoint URL. Copy this data to send it to LoyJoy support team later.

Step 4: Deploy Models​

To use Azure OpenAI, now models have to be deployed.

  • In Azure OpenAI click Model deployments to open Azure OpenAI Service Studio.
  • Azure OpenAI Service Studio should open, optionally with a sign in screen. You might need to select your Azure subscription to proceed.
  • In Azure OpenAI Service Studio open menu item Deployments.

Deploy Models

Create following models:

  • text-embedding-ada-002:
    • Click Create new deployment. Select text-embedding-ada-002 in version 2 and enter a name such as companyname-text-embedding-ada-002.
  • gpt-4o-mini:
    • Click Create new deployment. Select gpt-4o-mini in version Standard and enter a name such as companyname-gpt-4o-mini.
    • As filter select Standard instead of DefaultV2, as DefaultV2 seems to be too strict.
  • gpt-4o:
    • Click Create new deployment. Select gpt-4o in version Standard and enter a name such as companyname-gpt-4o.
    • As filter select Standard instead of DefaultV2, as DefaultV2 seems to be too strict.
  • gpt-4:
    • Click Create new deployment. Select gpt-4 in version Standard and enter a name such as companyname-gpt-4.
    • As filter select Standard instead of DefaultV2, as DefaultV2 seems to be too strict.
  • gpt-35-turbo:
    • Click Create new deployment. Select gpt-35-turbo in version Standard and enter a name such as companyname-gpt-35-turbo.
    • As filter select Standard instead of DefaultV2, as DefaultV2 seems to be too strict.

Step 5: Configuration in LoyJoy​

To use the deployment in LoyJoy please select an Azure model and enter the following details:

  • From step 3 one of the keys and the endpoint URL
  • The model deployment names, in this example companyname-text-embedding-ada-002 and companyname-gpt-35-turbo and companyname-gpt-4 and companyname-gpt-4o and companyname-gpt-4o-mini.
  • Please note that all deployment names for GPT-4/GPT-4o/GPT-4o-Mini and GPT-3.5 should be entered. This enables using advanced knowledge retrieval strategies in LoyJoy such as reranking, as reranking uses multiple models in parallel.

LoyJoy Azure GPT settings

Step 6: Fill out form "Modified Content Filters and Abuse Monitoring"​

Optionally, you can request that Microsoft internally should turn off human abuse monitoring based on Microsoft internal staff. To request this fill out this form.