AzureAIFoundryConnector Transformer Documentation

The AzureAIFoundryConnector is a custom FME transformer that enables integration with Azure OpenAI's Responses API. This transformer allows you to send prompts to large language models deployed in Azure AI Foundry and receive responses directly within an FME workspace. This transformer also supports a variety of tasks: text, reasoning (only available for some models), image (Vision), and file search.

Purpose

This transformer is designed for content generation, structured information extraction, summarization, reasoning, and other AI-driven tasks using Microsoft Azure’s hosted OpenAI services. It supports advanced reasoning models and file-based document processing via Azure AI's Files API.

Example Use Case

Imagine you have a dataset with a column of customer support inquiries, and you'd like to auto-generate a response or classify the sentiment. You can:

Use AttributeCreator to build a dynamic prompt string.

Pass that prompt to AzureAIFoundryConnector and choose the best model for your task.

Capture the model's response as a new attribute for downstream use.

Output Attributes

Attribute Name

Description

_response_body

The raw text response from the Azure AI Foundry model.

Response

A formatted text response from the Azure AI Foundry model

Notes

This transformer uses the Azure OpenAI Responses API (/v1/responses). It is not compatible with the chat endpoint (/v1/chat/completions) unless explicitly adapted. For Chat Completions, consider using the OpenAIChatGPTConnector instead.

Related Resources

Azure OpenAI Responses API

Azure AI Services Files API

OpenAI Tokenizer Tool