{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "jWESX0tpdrE-"
},
"source": [
"##### Copyright 2025 Google LLC."
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"cellView": "form",
"id": "YQvTrJpxzRlJ"
},
"outputs": [],
"source": [
"#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"# you may not use this file except in compliance with the License.\n",
"# You may obtain a copy of the License at\n",
"#\n",
"# https://www.apache.org/licenses/LICENSE-2.0\n",
"#\n",
"# Unless required by applicable law or agreed to in writing, software\n",
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"# See the License for the specific language governing permissions and\n",
"# limitations under the License."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "3hp_P0cDzTWp"
},
"source": [
"# Gemini 2.0 - Multimodal live API: Tool use"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OLW8VU78zZOc"
},
"source": [
"![](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "y7f4kFby0E6j"
},
"source": [
"This notebook provides examples of how to use tools with the multimodal live API with [Gemini 2.0](https://ai.google.dev/gemini-api/docs/models/gemini-v2).\n",
"\n",
"The API provides Google Search, Code Execution and Function Calling tools. The earlier Gemini models supported versions of these tools. The biggest change with Gemini 2 (in the Live API) is that, basically, all the tools are handled by Code Execution. With that change, you can use **multiple tools** in a single API call, and the model can use multiple tools in a single code execution block. \n",
"\n",
"This tutorial assumes you are familiar with the Live API, as described in the [this tutorial](../quickstarts/Get_started_LiveAPI.ipynb)."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Mfk6YY3G5kqp"
},
"source": [
"## Setup"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "d5027929de8f"
},
"source": [
"### Install SDK\n",
"\n",
"The new **[Google Gen AI SDK](https://ai.google.dev/gemini-api/docs/sdks)** provides programmatic access to Gemini 2.0 (and previous models) using both the [Google AI for Developers](https://ai.google.dev/gemini-api/docs) and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/overview) APIs. With a few exceptions, code that runs on one platform will run on both. This means that you can prototype an application using the Developer API and then migrate the application to Vertex AI without rewriting your code.\n",
"\n",
"More details about this new SDK on the [documentation](https://ai.google.dev/gemini-api/docs/sdks) or in the [Getting started](../quickstarts/Get_started.ipynb) notebook."
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {
"id": "46zEFO2a9FFd"
},
"outputs": [],
"source": [
"%pip install -U -q google-genai"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CTIfnvCn9HvH"
},
"source": [
"### Setup your API key\n",
"\n",
"To run the following cell, your API key must be stored it in a Colab Secret named `GOOGLE_API_KEY`. If you don't already have an API key, or you're not sure how to create a Colab Secret, see [Authentication](../quickstarts/Authentication.ipynb) for an example."
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"id": "A1pkoyZb9Jm3"
},
"outputs": [],
"source": [
"from google.colab import userdata\n",
"import os\n",
"\n",
"os.environ['GOOGLE_API_KEY']=userdata.get('GOOGLE_API_KEY')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Y13XaCvLY136"
},
"source": [
"### Initialize SDK client\n",
"\n",
"The client will pickup your API key from the environment variable.\n",
"To use the live API you need to set the client version to `v1alpha`."
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"id": "HghvVpbU0Uap"
},
"outputs": [],
"source": [
"from google import genai\n",
"\n",
"client = genai.Client()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QOov6dpG99rY"
},
"source": [
"### Select a model\n",
"\n",
"Multimodal Live API are a new capability introduced with the [Gemini 2.0](https://ai.google.dev/gemini-api/docs/models/gemini-v2) model. It won't work with previous generation models."
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {
"id": "27Fikag0xSaB"
},
"outputs": [],
"source": [
"model_name = \"gemini-2.0-flash-live-001\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "pLU9brx6p5YS"
},
"source": [
"### Imports"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"id": "yMG4iLu5ZLgc"
},
"outputs": [],
"source": [
"import asyncio\n",
"import contextlib\n",
"import json\n",
"import wave\n",
"\n",
"from IPython import display\n",
"\n",
"from google import genai\n",
"from google.genai import types"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yrb4aX5KqKKX"
},
"source": [
"### Utilities"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rmfQ-NvFI7Ct"
},
"source": [
"You're going to use the Live API's audio output, the easiest way hear it in Colab is to write the `PCM` data out as a `WAV` file:"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"id": "p2aGpzlR-60Q"
},
"outputs": [],
"source": [
"@contextlib.contextmanager\n",
"def wave_file(filename, channels=1, rate=24000, sample_width=2):\n",
" with wave.open(filename, \"wb\") as wf:\n",
" wf.setnchannels(channels)\n",
" wf.setsampwidth(sample_width)\n",
" wf.setframerate(rate)\n",
" yield wf"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "KfdD9mVxqatm"
},
"source": [
"Use a logger so it's easier to switch on/off debugging messages."
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {
"id": "wgHJgpV9Zw4E"
},
"outputs": [],
"source": [
"import logging\n",
"logger = logging.getLogger('Live')\n",
"#logger.setLevel('DEBUG') # Switch between \"INFO\" and \"DEBUG\" to toggle debug messages.\n",
"logger.setLevel('INFO')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4hiaxgUCZSYJ"
},
"source": [
"## Get started"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "LQoca-W7ri0y"
},
"source": [
"Most of the Live API setup will be similar to the [starter tutorial](../quickstarts/Get_started_LiveAPI.ipynb). Since this tutorial doesn't focus on the realtime interactivity of the API, the code has been simplified: This code uses the Live API, but it only sends a single text prompt, and listens for a single turn of replies.\n",
"\n",
"You can set `modality=\"AUDIO\"` on any of the examples to get the spoken version of the output."
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {
"id": "lwLZrmW5zR_P"
},
"outputs": [],
"source": [
"n = 0\n",
"async def run(prompt, modality=\"TEXT\", tools=None):\n",
" global n\n",
" if tools is None:\n",
" tools=[]\n",
"\n",
" config = {\n",
" \"tools\": tools,\n",
" \"response_modalities\": [modality]\n",
" }\n",
"\n",
" async with client.aio.live.connect(model=model_name, config=config) as session:\n",
" display.display(display.Markdown(prompt))\n",
" display.display(display.Markdown('-------------------------------'))\n",
" await session.send_client_content(\n",
" turns={\"role\": \"user\", \"parts\": [{\"text\": prompt}]}, turn_complete=True\n",
" )\n",
"\n",
" audio = False\n",
" filename = f'audio_{n}.wav'\n",
" with wave_file(filename) as wf:\n",
" async for response in session.receive():\n",
" logger.debug(str(response))\n",
" if text:=response.text:\n",
" display.display(display.Markdown(text))\n",
" continue\n",
"\n",
" if data:=response.data:\n",
" print('.', end='')\n",
" wf.writeframes(data)\n",
" audio = True\n",
" continue\n",
"\n",
" server_content = response.server_content\n",
" if server_content is not None:\n",
" handle_server_content(wf, server_content)\n",
" continue\n",
"\n",
" tool_call = response.tool_call\n",
" if tool_call is not None:\n",
" await handle_tool_call(session, tool_call)\n",
"\n",
"\n",
" if audio:\n",
" display.display(display.Audio(filename, autoplay=True))\n",
" n = n+1"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ngrvxzrf0ERR"
},
"source": [
"Since this tutorial demonstrates several tools, you'll need more code to handle the different types of objects it returns.\n",
"\n",
"- The `code_execution` tool can return `executable_code` and `code_execution_result` parts.\n",
"- The `google_search` tool may attach a `grounding_metadata` object."
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {
"id": "CypjqSb-0C-Q"
},
"outputs": [],
"source": [
"def handle_server_content(wf, server_content):\n",
" model_turn = server_content.model_turn\n",
" if model_turn:\n",
" for part in model_turn.parts:\n",
" executable_code = part.executable_code\n",
" if executable_code is not None:\n",
" display.display(display.Markdown('-------------------------------'))\n",
" display.display(display.Markdown(f'``` python\\n{executable_code.code}\\n```'))\n",
" display.display(display.Markdown('-------------------------------'))\n",
"\n",
" code_execution_result = part.code_execution_result\n",
" if code_execution_result is not None:\n",
" display.display(display.Markdown('-------------------------------'))\n",
" display.display(display.Markdown(f'```\\n{code_execution_result.output}\\n```'))\n",
" display.display(display.Markdown('-------------------------------'))\n",
"\n",
" grounding_metadata = getattr(server_content, 'grounding_metadata', None)\n",
" if grounding_metadata is not None:\n",
" display.display(\n",
" display.HTML(grounding_metadata.search_entry_point.rendered_content))\n",
"\n",
" return"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dPnXSNZ5rydM"
},
"source": [
"- Finally, with the `function_declarations` tool, the API may return `tool_call` objects. To keep this code minimal, the `tool_call` handler just replies to every function call with a response of `\"ok\"`."
]
},
{
"cell_type": "code",
"execution_count": 46,
"metadata": {
"id": "EmTKF_DtrY4U"
},
"outputs": [],
"source": [
"async def handle_tool_call(session, tool_call):\n",
" function_responses = []\n",
" for fc in tool_call.function_calls:\n",
" function_response = types.FunctionResponse(\n",
" id=fc.id,\n",
" name=fc.name,\n",
" response={\"result\": \"ok\"},\n",
" )\n",
" function_responses.append(function_response)\n",
" print('\\n>>> ', function_responses)\n",
" await session.send_tool_response(function_responses=function_responses)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "TcNu3zUNsI_p"
},
"source": [
"Try running it for a first time:"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {
"id": "ss9I0MRdHbP2"
},
"outputs": [
{
"data": {
"text/markdown": "Hello?",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "Hello! How can",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " I help you today?\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"await run(prompt=\"Hello?\", tools=None, modality = \"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Z_BFBLLGp-Ye"
},
"source": [
"## Simple function call"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RMq795G6t2hA"
},
"source": [
"The function calling feature of the API Can handle a wide variety of functions. Support in the SDK is still under construction. So keep this simple just send a minimal function definition: Just the function's name.\n",
"\n",
"Note that in the live API function calls are independent of the chat turns. The conversation can continue while a function call is being processed."
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {
"id": "8Y00qqZZt5L-"
},
"outputs": [],
"source": [
"turn_on_the_lights = {'name': 'turn_on_the_lights'}\n",
"turn_off_the_lights = {'name': 'turn_off_the_lights'}"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {
"id": "8dCjPmz8nEbv"
},
"outputs": [
{
"data": {
"text/markdown": "Turn on the lights",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\nprint(default_api.turn_on_the_lights())\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
">>> [FunctionResponse(id='function-call-11156140644305791367', name='turn_on_the_lights', response={'result': 'ok'})]\n"
]
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "```\n{'result': 'ok'}\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "OK",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ". I've turned on the lights.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"prompt = \"Turn on the lights\"\n",
"\n",
"tools = [\n",
" {'function_declarations': [turn_on_the_lights, turn_off_the_lights]}\n",
"]\n",
"\n",
"await run(prompt, tools=tools, modality = \"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "eCnCiTbhqE8q"
},
"source": [
"## Code execution"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "P4ptRBNY4N8Q"
},
"source": [
"The `code_execution` lets the model write and run python code. Try it on a math problem the model can't solve from memory:"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {
"id": "k4dURhC-QoSw"
},
"outputs": [
{
"data": {
"text/markdown": "Can you compute the largest prime palindrome under 100000.",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "Okay",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ", I can help you with that. Here's my plan:\n\n1",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ". **Generate Palindromes:** Create a list of all palindromes under",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " 100000.\n2. **Check for Primality:** Iterate through the palindromes and check if each one is prime.\n3.",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " **Find the Largest:** Keep track of the largest prime palindrome found so far.\n\nHere's the Python code to achieve this:\n\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\ndef is_palindrome(n):\n \"\"\"Checks if a number is a palindrome.\"\"\"\n return str(n) == str(n)[::-1]\n\n\ndef is_prime(n):\n \"\"\"Checks if a number is prime.\"\"\"\n if n < 2:\n return False\n for i in range(2, int(n**0.5) + 1):\n if n % i == 0:\n return False\n return True\n\n\nlargest_prime_palindrome = 0\nfor i in range(100000):\n if is_palindrome(i):\n if is_prime(i):\n largest_prime_palindrome = i\n\nprint(f'{largest_prime_palindrome=}')\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "```\nlargest_prime_palindrome=98689\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "The largest prime palindrome",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " under 100000 is 98689.",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"prompt=\"Can you compute the largest prime palindrome under 100000.\"\n",
"\n",
"tools = [\n",
" {'code_execution': {}}\n",
"]\n",
"\n",
"await run(prompt, tools=tools, modality=\"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ueeerkpX5F-v"
},
"source": [
"## Compositional Function Calling\n",
"\n",
"Compositional function calling refers to the ability to combine user defined functions with the `code_execution` tool. The model will write them into larger blocks of code, and then pause execution while it waits for you to send back responses for each call.\n"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {
"id": "XzKyL_Rq5sG3"
},
"outputs": [
{
"data": {
"text/markdown": "Can you turn on the lights wait 10s and then turn them off?",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\nimport time\n\ndefault_api.turn_on_the_lights()\ntime.sleep(10)\ndefault_api.turn_off_the_lights()\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
">>> [FunctionResponse(id='function-call-18306446495930491005', name='turn_on_the_lights', response={'result': 'ok'})]\n",
"\n",
">>> [FunctionResponse(id='function-call-18412143381776491416', name='turn_off_the_lights', response={'result': 'ok'})]\n"
]
},
{
"data": {
"text/markdown": "Okay",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ", I've turned on the lights, waited for 10 seconds,",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " and then turned them off.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"prompt=\"Can you turn on the lights wait 10s and then turn them off?\"\n",
"\n",
"tools = [\n",
" {'code_execution': {}},\n",
" {'function_declarations': [turn_on_the_lights, turn_off_the_lights]}\n",
"]\n",
"\n",
"await run(prompt, tools=tools, modality=\"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "G78sxDEcqHyO"
},
"source": [
"## Google search"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "FW10vRPN6UNp"
},
"source": [
"The `google_search` tool lets the model conduct google searches. For example, try asking it about events that are too recent to be in the training data.\n",
"\n",
"The search will still execute in `AUDIO` mode, but you won't see the detailed results:"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {
"id": "QKvWzROJic60"
},
"outputs": [
{
"data": {
"text/markdown": "When the latest Brazil vs. Argentina soccer match happened and what was the final score?",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\nprint(google_search.search(queries=[\"latest Brazil vs Argentina soccer match date and final score\", \"Brazil vs Argentina soccer match results 2024 2025\"]))\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "```\nLooking up information on Google Search.\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "The latest match",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " between Brazil and Argentina took place on **March 25, 202",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "5**, as part of the 2026 FIFA World Cup qualifiers.",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " Argentina won the match with a final score of **4-1**.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"prompt=\"When the latest Brazil vs. Argentina soccer match happened and what was the final score?\"\n",
"\n",
"tools = [\n",
" {'google_search': {}}\n",
"]\n",
"\n",
"await run(prompt, tools=tools, modality=\"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HM9y5rwfqKfY"
},
"source": [
"## Multi-tool\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "qrxAQjYA6vQX"
},
"source": [
"The biggest difference with the new API however is that you're no longer limited to using 1-tool per request. Try combining those tasks from the previous sections:"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {
"id": "QmB_4XPOslyA"
},
"outputs": [
{
"data": {
"text/markdown": " Hey, I need you to do three things for me.\n\n 1. Then compute the largest prime plaindrome under 100000.\n 2. Then use google search to lookup unformation about the largest earthquake in california the week of Dec 5 2024?\n 3. Turn on the lights\n\n Thanks!\n ",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "Okay",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ", I'll do those three things for you. Here's the plan",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": ":\n\n1. Compute the largest prime palindrome under 1000",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "00 using Python.\n2. Use Google Search to find information about the largest earthquake in California the week of December 5, 2024.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "3. Turn on the lights using the `default_api`.\n\nHere we go:\n\nFirst, I will find the largest prime palindrome under 10",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "0000.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\ndef is_palindrome(n):\n return str(n) == str(n)[::-1]\n\ndef is_prime(n):\n if n < 2:\n return False\n for i in range(2, int(n**0.5) + 1):\n if n % i == 0:\n return False\n return True\n\nlargest_prime_palindrome = 0\nfor i in range(99999, 1, -1):\n if is_palindrome(i) and is_prime(i):\n largest_prime_palindrome = i\n break\n\nprint(largest_prime_palindrome)\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "```\n98689\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "Okay, the largest",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " prime palindrome under 100000 is 9868",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "9.\n\nNow, I will use Google Search to find information about the largest",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " earthquake in California the week of December 5, 2024.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\nconcise_search(\"largest earthquake california week of December 5 2024\", max_num_results=5)\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "```\nLooking up information on Google Search.\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "Based on the search",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " results, the largest earthquake in California during the week of December 5, ",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "2024, was a magnitude 7.0 earthquake that struck offshore",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " of Cape Mendocino on December 5, 2024, at 10:44 a.m. local time. A tsunami warning was briefly",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": " issued.\n\nFinally, I will turn on the lights.\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "``` python\ndefault_api.turn_on_the_lights()\n\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/markdown": "-------------------------------",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
">>> [FunctionResponse(id='function-call-661398979255934381', name='turn_on_the_lights', response={'result': 'ok'})]\n"
]
},
{
"data": {
"text/markdown": "```tool_outputs\n{}\n```",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"prompt = \"\"\"\\\n",
" Hey, I need you to do three things for me.\n",
"\n",
" 1. Then compute the largest prime plaindrome under 100000.\n",
" 2. Then use google search to lookup unformation about the largest earthquake in california the week of Dec 5 2024?\n",
" 3. Turn on the lights\n",
"\n",
" Thanks!\n",
" \"\"\"\n",
"\n",
"tools = [\n",
" {'google_search': {}},\n",
" {'code_execution': {}},\n",
" {'function_declarations': [turn_on_the_lights, turn_off_the_lights]}\n",
"]\n",
"\n",
"await run(prompt, tools=tools, modality=\"TEXT\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Y0OhM95KkMzl"
},
"source": [
"## Next Steps\n",
"\n",
"- For more information about the SDK see the [SDK docs](https://googleapis.github.io/python-genai/)\n",
"- This tutorial uses the high level SDK, if you're interested in the lower-level details, try the [Websocket version of this tutorial](../quickstarts/quickstarts/websockets/Get_started_LiveAPI_tools.ipynb)\n",
"- This tutorial only covers _basic_ usage of these tools for deeper (and more fun) example see the [Search tool tutorial](./Search_Grounding.ipynb)\n",
"\n",
"Or check the other Gemini 2.0 capabilities from the [Cookbook](../gemini-2/), in particular this other [multi-tool](../examples/LiveAPI_plotting_and_mapping.ipynb) example and the one about Gemini [spatial capabilities](../quickstarts/Spatial_understanding.ipynb)."
]
}
],
"metadata": {
"colab": {
"name": "Get_started_LiveAPI_tools.ipynb",
"toc_visible": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 0
}