Skip to main content

Azure AI Studio

Azure AI Studio is Microsoft's comprehensive platform for building, deploying, and managing AI applications, providing access to advanced language models, machine learning tools, and AI services for enterprise-grade artificial intelligence solutions.

Azure AI Studio icon

Power end-to-end data operations for your Azure AI Studio API with Nexla. Our bi-directional Azure AI Studio connector is purpose-built for Azure AI Studio, making it simple to ingest data, sync it across systems, and deliver it anywhere — all with no coding required. Nexla turns API-sourced data into ready-to-use, reusable data products and makes it easy to send data to Azure AI Studio or any other destination. With comprehensive monitoring, lineage tracking, and access controls, Nexla keeps your Azure AI Studio workflows fast, secure, and fully governed.

Features

Type: API

SourceDestination

  • Seamless API Integration: Connect to any endpoint as source or destination without coding, with automatic data product creation
  • Visual Composition & Chaining: Build complex integrations using visual templates, chain API calls, and compose workflows with data validation and filtering
  • API Proxy: Expose curated slices of your data securely with a secure and customizable API proxy that validates and transforms data on the fly
  • Request optimization with intelligent batching, retry, and caching to minimize API calls and costs

Prerequisites​

Before creating an Azure AI Studio credential in Nexla, you need to create an Azure AI Studio deployment and obtain an API key. Azure AI Studio uses API Key authentication with Bearer token authentication for secure access to language models.

Azure AI Studio Deployment Setup​

Azure AI Studio provides access to language models through Azure deployments. You need to create a deployment in Azure AI Studio and obtain the necessary credentials to access the models.

  1. Access Azure AI Studio: Sign in to your Azure AI Studio portal or access it through the Azure Portal.

  2. Create or Select a Deployment: Create a new deployment or select an existing deployment of a language model (e.g., GPT-4, GPT-3.5, or other available models). The deployment provides access to the model through a dedicated endpoint.

  3. Obtain API Key: Navigate to your deployment settings or the Azure AI Studio resource settings to obtain your API key. The API key is used to authenticate requests to your Azure AI Studio deployment.

  4. Identify Deployment Details: Note the following information about your deployment:

    • Model Name: The name of the model deployment (e.g., gpt-4o, gpt-35-turbo)
    • Region: The Azure region where your deployment is located (e.g., eastus2, westeurope, asia)
    • Model Version: The API version for the model (e.g., 2023-03-15-preview, 2024-02-15-preview)
    • Base URL: The full endpoint URL for your deployment, typically in the format https://{model_name}.{region}.models.ai.azure.com

  5. Review Model Access: Ensure your Azure subscription and deployment have the necessary permissions and quotas to access the language models you want to use.

For detailed information about creating deployments and managing Azure AI Studio resources, see the Azure AI Studio documentation.

Authenticate​

Credentials required​

FieldRequiredSecretDescription
Model NameYesNoThe name of the model you want to use (Ex.: gpt-4o).
API Key ValueYesYesYour API KEY for this model
Model VersionYesNoThe version of the api related to the model (Ex.: 2023-03-15-preview).
RegionYesNoRegion of your Azure instance (Ex.: eastus2, westeurope, asia, etc.)
Base Url for the LLM CallYesNoProvide the full endpoint to the LLM call on Azure (Format: https://<MODEL_NAME>.<PROVIDER_REGION>.models.ai.azure.com)

Create a credential in Nexla​

  1. After selecting the data source/destination type, click the Add Credential tile to open the Add New Credential overlay.

New Credential Overlay – Azure AI Studio

AzureAIStudioCred.png

  1. Enter a name for the credential in the Credential Name field and a short, meaningful description in the Credential Description field.

  2. Enter the name of the model you want to use in the Model Name field. This should be the name of your Azure AI Studio model deployment (e.g., gpt-4o, gpt-35-turbo, gpt-4). The model name is used to construct the API endpoint URL for your deployment.

  3. Enter your Azure AI Studio API key in the API Key Value field. This should be the API key obtained from your Azure AI Studio deployment or resource settings. The API key is used for Bearer token authentication in the Authorization header for all API requests.

    The API key provides secure access to your Azure AI Studio deployment. Keep your API key secure and do not share it publicly or commit it to version control systems. The API key is sent in the Authorization: Bearer {api_key} header for all API requests. If you suspect your API key has been compromised, regenerate it immediately in your Azure AI Studio resource settings. For detailed information about Azure AI Studio authentication, see the Azure AI Studio documentation.

  4. Enter the API version for the model in the Model Version field. This should be the API version associated with your model deployment (e.g., 2023-03-15-preview, 2024-02-15-preview, 2024-06-01). The API version determines which features and response formats are available.

  5. Enter the Azure region where your deployment is located in the Region field. This should be the Azure region identifier (e.g., eastus2, westeurope, asia, southeastasia). The region is used to construct the API endpoint URL. The default value is eastus2 if not specified.

  6. Enter the complete base URL for your Azure AI Studio deployment in the Base Url for the LLM Call field. This should be the full endpoint URL in the format https://{model_name}.{region}.models.ai.azure.com (e.g., https://gpt-4o.eastus2.models.ai.azure.com). The base URL is used as the endpoint for API calls to your deployment.

    The base URL must match your Azure AI Studio deployment endpoint. Ensure the URL format is correct and includes the model name and region. The base URL is combined with the API path (e.g., /chat/completions) and API version query parameter to form the complete endpoint URL for API requests.

  7. Click the Save button at the bottom of the overlay. The newly added credential will now appear in a tile on the Authenticate screen during data source/destination creation.

Use as a data source​

To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Select the Azure AI Studio connector tile, then select the credential that will be used to connect to the Azure AI Studio instance, and click Next; or, create a new Azure AI Studio credential for use in this flow.

Endpoint templates​

Nexla provides pre-built templates that can be used to rapidly configure data sources to ingest data from common Azure AI Studio endpoints. Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below. Click on an endpoint to see more information about it and how to configure your data source for this endpoint.

Chat Completion

This endpoint sends a chat message to your Azure AI Studio language model and retrieves the model's response. Use this endpoint when you need to interact with language models for text generation, question answering, summarization, or other natural language processing tasks.

  • Enter the message or query you want to send to the language model in the Message field. This is the user message that will be sent to the model for processing. The message can be a question, prompt, instruction, or any text you want the model to respond to.
  • The endpoint uses POST requests to the Azure AI Studio Chat Completions API endpoint. The endpoint URL is automatically constructed based on your credential configuration as https://{model_name}.{region}.models.ai.azure.com/chat/completions?api-version={model_version}.
  • The endpoint sends the message in the request body as JSON with the format {"messages":[{"role":"user","content":"{your_message}"}]}. The request body follows the Azure OpenAI API specification for chat completions.
  • The endpoint will return the model's response to your message. The response data is returned at the root level of the JSON response ($), containing the model's completion, usage statistics, and other response metadata.
  • The endpoint does not use pagination and returns a single response for each request. Each message sent to the endpoint will generate one response from the model.

This endpoint requires a valid message to send to the language model. The endpoint uses POST requests with JSON request bodies following the Azure OpenAI Chat Completions API specification. The endpoint requires API Key authentication with Bearer token, which is handled automatically by your credential configuration. The Authorization: Bearer {api_key} header is automatically included in requests. The endpoint does not use pagination (isPaginated: false) and returns a single response per request. For detailed information about the Chat Completions API, including request formats, response structures, and available parameters, see the Azure AI Studio documentation and Azure OpenAI Service documentation.

Once the selected endpoint template has been configured, click the Test button to the right of the endpoint selection menu to retrieve a sample of the data that will be fetched. Sample data will be displayed in the Endpoint Test Result panel on the right, allowing you to verify that the source is configured correctly before saving.

Manual configuration​

Azure AI Studio data sources can also be manually configured to ingest data from any valid Azure AI Studio API endpoint, including endpoints not covered by the pre-built templates, chained API calls, or custom request parameters. Select the Advanced tab at the top of the configuration screen, and follow the instructions in Connect to Any API to configure the API method, endpoint URL, date/time and lookup macros, path to data, metadata, and request headers.

Azure AI Studio primarily uses POST requests, and its API endpoints follow the pattern https://{model_name}.{region}.models.ai.azure.com/{api_path}?api-version={version}. The Authorization: Bearer {api_key} header is included automatically based on your credential configuration. When extracting a subset of the response, JSON paths use dot notation — for example, $.choices[*] accesses the array of model response choices.

Once all of the relevant settings have been configured, click the Create button in the upper right corner of the screen to save and create the new Azure AI Studio data source. Nexla will now begin ingesting data from the configured endpoint and will organize any data that it finds into one or more Nexsets.