Skip to main content
Technical Preview

Overview

A client-mode connector for a curated slice of Azure OpenAI / Azure AI Foundry focused on IIoT / edge alarm text into Azure-hosted LLMs (OpenAI-compatible bodies, deployment-based paths): Default BASE_ADDRESS placeholder is https://YOUR_RESOURCE.openai.azure.com (no trailing slash) — replace with your real resource host. Default api-version in docs/examples: 2024-10-21. Topics use ai/azure-openai/<object>/<verb>. See the base guide: REST API Connectors.
Auth: api-key: &lt;Azure OpenAI resource key&gt; on every request (template default). Prefer Hub secrets (GET SECRET "AZURE_OPENAI_API_KEY" or AZURE_OPENAI_KEY) mapped into MQTT api_token. Entra ID alternative: Authorization: Bearer &lt;token&gt; with scope https://cognitiveservices.azure.com/.default. Never commit real keys.
Factory live smoke is blocked until a resource endpoint + API key + deployment name are supplied. Set BASE_ADDRESS to your https://{resource}.openai.azure.com host before production use.

Basic Syntax

Full deployable file: AzureOpenaiAndAzureAiFoundryRestApi.lot in the factory package (no ADD METADATA).

Topics

Configuration

  1. Set BASE_ADDRESS to https://{your-resource}.openai.azure.com (no trailing slash).
  2. Store the Azure OpenAI API key in Hub secrets (AZURE_OPENAI_API_KEY or AZURE_OPENAI_KEY); map into MQTT api_token.
  3. Pass deployment (deployment name) and api_version (e.g. 2024-10-21) on inference MQTT JSON.
  4. For alarm classification: publish to ai/azure-openai/chat/completions/post with an OpenAI-compatible messages body (optional response_format).
  5. For semantic search / similarity: publish to ai/azure-openai/embeddings/post with a tiny input string against an embeddings deployment.
  6. Use GetModels as a cheap auth smoke before production workloads.

References

Last modified on October 21, 2026