foundry_moderate_image: Moderate image content

In foundryR: Data Frame Workflows for 'Microsoft Foundry'

Moderate image content

Description

Analyze an image for harmful content with Azure AI Content Safety. image can be a local file path or an HTTPS Azure Blob Storage URL.

Usage

foundry_moderate_image(
  image,
  categories = c("Hate", "Sexual", "SelfHarm", "Violence"),
  output_type = c("FourSeverityLevels", "EightSeverityLevels"),
  endpoint = NULL,
  api_key = NULL,
  api_version = "2024-09-01"
)

Arguments

image	Character. Local image path or HTTPS Azure Blob Storage URL.
categories	Character vector of harm categories.
output_type	Character. Severity level granularity.
endpoint	Character. Optional Content Safety endpoint.
api_key	Character. Optional Content Safety key.
api_version	Character. API version. Defaults to "2024-09-01".

Value

A tibble with one row per category and raw response payloads.

Examples

## Not run: 
# Requires a configured Azure Content Safety endpoint and credentials,
# base64enc, and your own local image.png input file.
foundry_moderate_image("image.png")

## End(Not run)

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