Semantic kernel using google gemini and API key

If you're thinking about using Google Gemini as your model in semantic kernel, then you come to the right place. This is how you can setup 

Run the following command to setup and install the required dependencies

uv add semantic-kernel[google]

Then you all you need is your Gemini API key

import asyncio

from semantic_kernel import Kernel

from semantic_kernel.utils.logging import setup_logging

from semantic_kernel.functions import kernel_function

from semantic_kernel.connectors.ai.google.google_ai import GoogleAIChatCompletion

from semantic_kernel.connectors.ai.function_choice_behavior import FunctionChoiceBehavior

from semantic_kernel.connectors.ai.chat_completion_client_base import ChatCompletionClientBase

from semantic_kernel.contents.chat_history import ChatHistory

from semantic_kernel.functions.kernel_arguments import KernelArguments

from semantic_kernel.connectors.ai.open_ai.prompt_execution_settings.azure_chat_prompt_execution_settings import (

    AzureChatPromptExecutionSettings,

)

async def main():

    # Initialize the kernel

    # Add Azure OpenAI chat completion

    chat_completion = GoogleAIChatCompletion(

        gemini_model_id="gemini-2.5-flash-lite",

        api_key="YOUR-API-KEY",

        service_id="my-service-id", # Optional; for targeting specific services within Semantic Kernel

    )

    from semantic_kernel import Kernel

    # Initialize the kernel

    kernel = Kernel()

    kernel.add_service(chat_completion)

    # Enable planning

    # execution_settings = AzureChatPromptExecutionSettings()

    # execution_settings.function_choice_behavior = FunctionChoiceBehavior.Auto()

    # Create a history of the conversation

    from semantic_kernel.connectors.ai.chat_completion_client_base import ChatCompletionClientBase

    # Retrieve the chat completion service by type

    chat_completion_service = kernel.get_service(type=ChatCompletionClientBase)

    # Retrieve the chat completion service by id

    chat_completion_service = kernel.get_service(service_id="my-service-id")

    # Retrieve the default inference settings

    execution_settings = kernel.get_prompt_execution_settings_from_service_id("my-service-id")

    from semantic_kernel.connectors.ai.google.google_ai import GoogleAIChatPromptExecutionSettings

    execution_settings = GoogleAIChatPromptExecutionSettings()

    # chat_history = ChatHistory()

    # chat_history.add_user_message("Hello, how are you?")

    # response = await chat_completion_service.get_chat_message_content(

    #     chat_history=history,

    #     settings=execution_settings,

    # )

    # print(response)

    chat_history = ChatHistory()

    chat_history.add_user_message("Hello, how are you?")

    response = chat_completion_service.get_streaming_chat_message_content(

        chat_history=chat_history,

        settings=execution_settings,

    )

    async for chunk in response:

        print(chunk, end="")

if __name__ == "__main__":

    asyncio.run(main())