foundry_llm_resource: Describe a bring-your-own Azure OpenAI resource for...

In foundryR: Data Frame Workflows for 'Microsoft Foundry'

Describe a bring-your-own Azure OpenAI resource for groundedness

Description

Build the llm_resource argument for foundry_groundedness(). Reasoning and correction both rely on an Azure OpenAI deployment (typically a provisioned GPT-4o) that Content Safety calls on your behalf.

Usage

foundry_llm_resource(endpoint, deployment_name, resource_type = "AzureOpenAI")

Arguments

endpoint	Character. The Azure OpenAI resource endpoint, for example "https://your-openai.openai.azure.com".
deployment_name	Character. The Azure OpenAI deployment name to use.
resource_type	Character. The resource type. Only "AzureOpenAI" is currently supported.

Value

A named list matching the Content Safety LLMResource schema.

Examples

foundry_llm_resource(
  endpoint = "https://your-openai.openai.azure.com",
  deployment_name = "gpt-5-nano"
)

foundryR documentation built on Sept. 25, 2026, 1:10 a.m.