.github/workflows/tests.yml

# name: Testing output

# on:
#   push:
#     branches:
#       - main
#   pull_request:
#     branches:
#       - main

# jobs:
#   build:
#     runs-on: ubuntu-latest

#     steps:
#     - uses: actions/checkout@v3  # Update to v3
#     - name: Set up Python
#       uses: actions/setup-python@v3  # Update to v3
#       with:
#         python-version: '3.x'
#     - name: Install dependencies
#       run: |
#         python -m pip install --upgrade pip
#         pip install gradio huggingface_hub torch transformers accelerate
#     - name: Run tests
#       run: |
#         python -c """
#         import time
#         from app import respond, base_message

#         def test_api():
#             message = 'What is the meaning of life?'
#             history = []
#             system_message_val = base_message
#             temperature = 0.7
#             practicality = 0.8
#             max_tokens = 256
#             use_local_model = False  # Set to False to use the API-based model

#             start_time = time.time()

#             result_generator = respond(
#                 message=message,
#                 history=history,
#                 system_message_val=system_message_val,
#                 temperature=temperature,
#                 practicality=practicality,
#                 max_tokens=max_tokens,
#                 use_local_model=use_local_model
#             )

#             for result in result_generator:
#                 final_history, final_system_message = result

#             end_time = time.time()
#             runtime = end_time - start_time

#             print('API Runtime: ', runtime)
#             print('API Final conversation history:', final_history)
#             print('API Final system message:', final_system_message)

#         def test_local():
#             message = 'What is the meaning of life?'
#             history = []
#             system_message_val = base_message
#             temperature = 0.7
#             practicality = 0.8
#             max_tokens = 256
#             use_local_model = True

#             start_time = time.time()

#             result = list(respond(
#                 message=message,
#                 history=history,
#                 system_message_val=system_message_val,
#                 temperature=temperature,
#                 practicality=practicality,
#                 max_tokens=max_tokens,
#                 use_local_model=use_local_model
#             ))

#             end_time = time.time()
#             runtime = end_time - start_time

#             final_history, final_system_message = result[-1]
#             print('Local Runtime: ', runtime)
#             print('Local Final conversation history:', final_history)
#             print('Local Final system message:', final_system_message)

#         if __name__ == '__main__':
#             test_api()
#             test_local()
#                 """