app2.py

from PIL import Image
import requests
import torch
import os
# Set the cache directory
cache_dir = "F:\\huggingface_cache"

# Set environment variables for good measure
# os.environ["TRANSFORMERS_CACHE"] = cache_dir
# os.environ["HF_HOME"] = cache_dir
# os.environ["HUGGINGFACE_HUB_CACHE"] = cache_dir

# Model ID
model_id = "google/gemma-3-4b-it"

from ollama import chat
from ollama import ChatResponse

response: ChatResponse = chat(model='llama3.2', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
])
print(response['message']['content'])
# or access fields directly from the response object
print(response.message.content)