Suggestion: Use models to encapsulate request/responses #12

New Issue

2026-02-15T16:27:26-05:00

yindo commented

2026-02-15 16:27:26 -05:00

Originally created by @sachinsachdeva on GitHub (Jan 27, 2024).

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)

Originally created by @sachinsachdeva on GitHub (Jan 27, 2024). consider using models to properly encapsulate request/responses for example ```python import ollama response = ollama.chat(model='llama2', messages=[ { 'role': 'user', 'content': 'Why is the sky blue?', }, ]) print(response['message']['content']) ``` would become something like ```python 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) ```

yindo closed this issue

2026-02-15 16:27:26 -05:00

yindo commented

2026-02-15 16:27:27 -05:00

@adriens commented on GitHub (Jan 31, 2024):

➕ 1️⃣

@adriens commented on GitHub (Jan 31, 2024): :heavy_plus_sign: :one:

yindo commented

2026-02-15 16:27:27 -05:00

@ParthSareen commented on GitHub (Feb 13, 2025):

😄 supported now!

@ParthSareen commented on GitHub (Feb 13, 2025): 😄 supported now!

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: ollama/ollama-python#12