Skip to content

Multi-Modal Models

Image models are not currently the primary use case expected to be protected by AIDR; however, we offer the option in multi-modal models to block image input if required.

Environment KeyRequiredExample ValueDescription
HL_LLM_BLOCK_IMAGES_UPLOADFalseFalseFlag to block uploading images.

Models Supported

Model Provider / Cloud Model ServiceSupport Status
AnthropicSupported
Azure OpenAIUnsupported
GeminiSupported
Hugging Face TGI OpenAIUnsupported
OpenAISupported
AzureMLPartial
AWSPartial