Azure ChatCompletion

Azure ChatCompletion

Certified

Generate chat completions using an Azure AI Foundry model deployment

Sends a list of chat messages to a model deployment in Azure AI Foundry and returns the model response. Currently supports 'system' and 'user' message roles; multi-turn conversations with prior 'assistant' turns are not yet supported.

yaml
type: io.kestra.plugin.azure.aifoundry.ChatCompletion

Chat completion with a deployed model

yaml
    id: azure_ai_chat_completion
    namespace: company.team
    inputs:
      - id: prompt
        type: STRING
        defaults: "Summarize the quarterly report."
    tasks:
      - id: chat
        type: io.kestra.plugin.azure.aifoundry.ChatCompletion
        endpoint: "{{ secret('AZURE_AI_FOUNDRY_ENDPOINT') }}"
        apiKey: "{{ secret('AZURE_AI_FOUNDRY_API_KEY') }}"
        deploymentName: gpt-4o
        messages:
          - role: user
            content: "{{ inputs.prompt }}"
Properties

The name of the deployment to use

Azure AI Foundry endpoint

The Azure AI Foundry project or model endpoint URL.

The messages to generate chat completions for

Definitions
content*Requiredstring

The contents of the message

role*Requiredstring

The role of the author of this message

Supported values: 'user' or 'system'

Azure AI Foundry API key

API key for API-key authentication. When omitted, DefaultAzureCredential (Entra ID) is used instead.

Azure client ID

Client ID of the Azure app registration used with tenantId and clientSecret.

Azure client secret

Client secret of the Azure app registration used with tenantId and clientId.

Reference (ref) of the pluginDefaults to apply to this task.

Azure tenant ID

Azure Entra tenant ID used with clientId and clientSecret for service principal authentication.

The generated chat completion content