In these examples, you can see how to generate a textual analysis or description of the contents of a given image.

Here, you supply an image along with a text question as the prompt (for example, "What is this image about?" or "How many birds are there in this image?"). The LLM responds with a textual answer or description based on the specified task in the prompt, which can then be used for image classification, object detection, or similarity search.

• Describe Images Using Public REST Providers
  Perform an image-to-text transformation by supplying an image along with a text question as the prompt, using publicly hosted third-party LLMs by Google AI, Hugging Face, OpenAI, or Vertex AI.
• Describe Images Using the Local REST Provider Ollama
  Perform an image-to-text transformation by supplying an image along with a text question as the prompt by accessing open LLMs, using the local host REST endpoint provider Ollama.