Suggestion: Use models to encapsulate request/responses

[sachinsachdeva]

consider using models to properly encapsulate request/responses

for example

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

would become something like

import ollama
from ollama.models import ChatMessageRequest, ChatMessageResponse

messages: [ChatMessageRequest] =  [ChatMessageRequest('user' , 'Why is the sky blue?')]
response: ChatMessageResponse = ollama.chat(model='llama2', messages=messages)

print(response.content)

[adriens]

:heavy_plus_sign: :one: