import asyncio
import os
 
from semantic_kernel.connectors.ai.onnx import OnnxGenAIChatCompletion, OnnxGenAIPromptExecutionSettings
from semantic_kernel.contents.chat_history import ChatHistory
from semantic_kernel.kernel import Kernel

kernel = Kernel()
 
service_id = "phi3"
streaming = True
 
model_path = os.path.join(
        os.path.dirname(__file__),
        "models", "Phi-4-mini-instruct-onnx", "cpu_and_mobile", "cpu-int4-rtn-block-32-acc-level-4"
    )
 
chat_completion = OnnxGenAIChatCompletion(ai_model_path=model_path,ai_model_id=service_id, template="phi3")
chat_completion.enable_multi_modality = False
 
settings = OnnxGenAIPromptExecutionSettings()
 
system_message = """You are a helpful assistant."""
chat_history = ChatHistory(system_message=system_message)
 
async def chat() -> bool:
    try:
        user_input = input("User:> ")
    except KeyboardInterrupt:
        print("\n\nExiting chat...")
        return False
    except EOFError:
        print("\n\nExiting chat...")
        return False
 
    if user_input == "exit":
        print("\n\nExiting chat...")
        return False
    chat_history.add_user_message(user_input)
    if streaming:
        print("Mosscap:> ", end="")
        message = ""
        async for chunk in chat_completion.get_streaming_chat_message_content(
            chat_history=chat_history, settings=settings, kernel=kernel
        ):
            if chunk:
                print(str(chunk), end="")
                message += str(chunk)
        chat_history.add_assistant_message(message)
        print("")
    else:
        answer = await chat_completion.get_chat_message_content(
            chat_history=chat_history, settings=settings, kernel=kernel
        )
        print(f"Mosscap:> {answer}")
        chat_history.add_message(answer)
    return True
 
 
async def main() -> None:
    chatting = True
    while chatting:
        chatting = await chat()
 
 
if __name__ == "__main__":
    asyncio.run(main())