SimpleDirectoryLoader
to get the image document(s)?image_document
image_documents
and send the array returned from llamaindex's directory loader (it should handle whatever type their API is looking for)image_documents = SimpleDirectoryReader("./your_img_directory/").load_data() response = azure_openai_mm_llm.complete( prompt="Describe the images as an alternative text", image_documents=image_documents )