co-op-translator

Set Up Azure AI for Co-op Translator (Azure OpneAI & Azure AI Vision)

Dis guide go show you how you fit set up Azure OpenAI for language translation and Azure Computer Vision for image content analysis (wey fit help for image-based translation) inside Azure AI Foundry.

Prerequisites:

You go need Azure account wey get active subscription.
You go need permission wey go allow you create resources and deployments for your Azure subscription.

Create Azure AI Project

You go first create Azure AI Project, wey go act like central place to manage your AI resources.

Go https://ai.azure.com and sign in with your Azure account.
Select +Create to create new project.
Do dis steps:
- Put Project name (e.g., CoopTranslator-Project).
- Select AI hub (e.g., CoopTranslator-Hub) (Create new one if e no dey).
Click “Review and Create” to set up your project. Dem go carry you go your project overview page.

Set up Azure OpenAI for Language Translation

Inside your project, you go deploy Azure OpenAI model wey go work as backend for text translation.

Navigate to Your Project

If you no dey there already, open the new project wey you create (e.g., CoopTranslator-Project) inside Azure AI Foundry.

Deploy OpenAI Model

From your project left-hand menu, under “My assets”, select “Models + endpoints”.
Select + Deploy model.
Select Deploy Base Model.
Dem go show you list of available models. Use filter or search find better GPT model. We recommend gpt-4o.
Select the model wey you want and click Confirm.
Select Deploy.

Azure OpenAI configuration

After you don deploy am, you fit select the deployment from “Models + endpoints” page to see REST endpoint URL, Key, Deployment name, Model name and API version. You go need all dis ones to connect the translation model to your application.

[!NOTE] You fit select API versions from API version deprecation page based on wetin you need. Make sure say you sabi say API version dey different from Model version wey dey show for Models + endpoints page inside Azure AI Foundry.

Set up Azure Computer Vision for Image Translation

To make am possible to translate text wey dey inside images, you go need find Azure AI Service API Key and Endpoint.

Go your Azure AI Project (e.g., CoopTranslator-Project). Make sure say you dey for project overview page.

Azure AI Service configuration

Find the API Key and Endpoint from Azure AI Service.

Go your Azure AI Project (e.g., CoopTranslator-Project). Make sure say you dey for project overview page.
Find API Key and Endpoint from Azure AI Service tab.

Dis connection go make the features of the linked Azure AI Services resource (including image analysis) dey available for your AI Foundry project. You fit use dis connection for your notebooks or applications to extract text from images, wey you fit later send go Azure OpenAI model for translation.

Consolidating Your Credentials

By now, you suppose don gather dis ones:

For Azure OpenAI (Text Translation):

Azure OpenAI Endpoint
Azure OpenAI API Key
Azure OpenAI Model Name (e.g., gpt-4o)
Azure OpenAI Deployment Name (e.g., cooptranslator-gpt4o)
Azure OpenAI API Version

For Azure AI Services (Image Text Extraction via Vision):

Azure AI Service Endpoint
Azure AI Service API Key

Example: Environment Variable Configuration (Preview)

Later, when you dey build your application, you go likely configure am using dis credentials wey you gather. For example, you fit set dem as environment variables like dis:

# Azure AI Service Credentials (Required for image translation)
AZURE_AI_SERVICE_API_KEY="your_azure_ai_service_api_key" # e.g., 21xasd...
AZURE_AI_SERVICE_ENDPOINT="https://your_azure_ai_service_endpoint.cognitiveservices.azure.com/"

# Azure OpenAI Credentials (Required for text translation)
AZURE_OPENAI_API_KEY="your_azure_openai_api_key" # e.g., 21xasd...
AZURE_OPENAI_ENDPOINT="https://your_azure_openai_endpoint.openai.azure.com/"
AZURE_OPENAI_MODEL_NAME="your_model_name" # e.g., gpt-4o
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="your_deployment_name" # e.g., cooptranslator-gpt4o
AZURE_OPENAI_API_VERSION="your_api_version" # e.g., 2024-12-01-preview