Usage body for LLaVA model

[sanujenLLM]

What is the request body for the LLaVA model which needs to handle image inputs along with text?

This is the sample provided in the repo for the llama2 model.

import ollama
response = ollama.chat(model='llama2', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
])
print(response['message']['content'])

[mxyng]

llava is a multimodal model. There's an example here