1. Objective of this lab
In this hands-on lab you will install, authenticate Gemini CLI and try out some basic use cases.
What you'll learn
- Understand the basics of Gemini CLI.
- Learn how to perform basic tasks with Gemini CLI.
2. Before you begin
- If you already do not have a project that you can use, you will need to create a new project in the GCP console.
- In this lab, we will use GCP Cloud Shell to perform the steps below. Open the Cloud Shell and set the project using Cloud Shell.
- Open the GCP Cloud Shell Editor by pressing the Cloud Shell Editor Button. If you see the "Authorize Shell" popup, click to authorize the Cloud Shell Editor.
- You can check if the project is already authenticated using the following command.
gcloud auth list
- Run the following command in Cloud Shell to confirm your project
gcloud config list project
- If your project is not set, use the following command to set it
gcloud config set project <YOUR_PROJECT_ID>
- We need to enable some services to run this lab. Run the following command in Cloud Shell.
gcloud services enable aiplatform.googleapis.com
3. Installation and Authentication
Installation
Gemini CLI comes preinstalled in GCP Cloud Shell Editor . If you want to use that you can get started right away.
You can also install Gemini CLI in your local environment.
In order to install Gemini CLI in your local environment you need Nodejs 20+. You can execute the following command to install Gemini CLI.
npm install -g @google/gemini-cli
To upgrade to the latest , use following command
npm update -g @google/gemini-cli
Run Gemini by executing the following command at your terminal.
gemini
Authentication
If you are using GCP Cloud Shell Editor you should already be authenticated if you accepted to authenticate the shell while running it.
If you are running locally and you have not authenticated yet, you will see a screen like below.
You can also type /auth to bring the screen below.
Figure 1: Gemini CLI will give you 3 methods to Authenticate.
First exit Gemini CLI with /quit command.
Authenticate with Google：Running /auth in the console will bring up authentication options. Select ‘Login with Google' from the options. The Google authentication screen will then appear in your browser. Once you complete the login there, the console will also be authenticated. Although authentication is complete, to actually use the Gemini CLI, you need to specify a Google Cloud project. Go back to the console screen and run the following command to specify the project (it's also possible to specify it in a .env file).
export GOOGLE_CLOUD_PROJECT=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Authenticate with API Key：To authenticate with an API key, you will need an API Key. You can generate an API Key from aistudio.google.com . Once the API Key is issued, set it in the console as follows:
export GEMINI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Authenticate with Vertex AI：In order to use the Gemini API via Vertex AI, follow the following steps.
First, use the command below to authenticate into Google Cloud.
gcloud auth application-default login
Execute the following commands after that in your terminal
export GOOGLE_GENAI_USE_VERTEXAI=true export GOOGLE_CLOUD_PROJECT=Your GCP Project Name export GOOGLE_CLOUD_LOCATION=us-central1
4. Try Gemini CLI
Now you are ready to try Gemini CLI. Try the following use cases.
First create a project folder, my_cli_project.
mkdir my_cli_project cd my_cli_project
Running Gemini from a project folder allows you to run Gemini CLI securely within the boundaries of that folder.
- Run a simple prompt:
What is the weather today in Tokyo
This should give you the weather in Tokyo. Notice that running this automatically uses
GoogleSearch Tool!
- Confirm the installed Tools: Run the following command. You should be able to see the list of tools installed.
/tools
Figure 2: List of tools displayed
- Get news from local news site: (eg. https://mainichi.jp, change it to your local news site).
Get me the news summary from https://mainichi.jp/
You should get a news summary from the local news site. Notice that the agent automatically uses the WebFetch tool to download the content from the news site and creates the summary.
- Run a Multi step task(please change it to your local site): Get me the news from https://mainichi.jp/ and filter in only the sports news and summarize that for me.
Get me the news from https://mainichi.jp/ and filter in only the sports news and summarize that for me.
- Run System Commands : In order to run system commands press ! and type the commands. To revert back to the normal mode, type ! again.
Type ! and Enter key. This starts the command mode. ls pwd Type ! to go back to normal mode.
- Create a Tic-Tac-Toe Game Enter the following prompt (English Version).
Please develop a Tic-Tac-Toe game that meets the following requirements. The solution should be split into separate HTML, CSS, and JavaScript files, with the JavaScript file handling the majority of the game logic independently.
1. General Requirements
The game format should be a match between one human player and one computer player.
When the game ends (a win/loss is determined, or a draw occurs), display "GAME OVER" on the screen along with the winner's name ("X wins!," "O wins!," or "Draw!").
Provide a "Reset" button to start a new game.
2. HTML (index.html)
Create the basic page structure.
The game board should consist of nine squares (cells). Each cell should be clickable and display the player's mark (X or O).
Provide an element to display the game status (e.g., current player's turn, game result).
Place the reset button for starting a new game.
Link the CSS and JavaScript files appropriately.
3. CSS (style.css)
Style the game board and cells so they are visually clear and easy to understand.
Add borders to the cells to indicate they are clickable areas.
Set appropriate font size and color for the X and O marks to ensure good visibility.
Style the game status display and the "GAME OVER" message to make them stand out.
Consider responsive design to ensure appropriate display on various screen sizes.
4. JavaScript (script.js)
It is strongly requested that the JavaScript file handle all the game logic.
4.1. Game State Management
Define an array or object to manage the game board state (e.g., ['', '', '', '', '', '', '', '', '']).
Define a variable to track the current player (X or O). The initial value should be X.
Define a boolean value to track whether the game has ended (win/loss or draw).
4.2. Game Initialization
Create a function to initialize the game board upon page load.
Clear all cells.
Set the current player to X.
Reset the game end flag.
Clear the game result display.
4.3. Player Interaction
Set up event listeners for cell clicks.
Only place the current player's mark and update the board state if the clicked cell is empty.
After placing the mark, execute the following:
Call the win/draw check function.
If a winner is not yet determined, switch the player (X to O, O to X).
4.4. Computer AI Logic
Create a function that is called when it is the computer's (O) turn.
Implement a simple logic where the computer randomly selects an empty cell to place its mark. (While difficulty can be increased in the future, random selection is sufficient initially.)
After the computer places its mark, perform the win/draw check, and if the game is not over, switch the turn back to the human player.
4.5. Win/Draw Determination
Create a function that determines the win/draw status based on the current board state.
Check the following winning conditions:
Three rows
Three columns
Two diagonals
If a player meets a winning condition, declare that player the winner.
If all cells are filled and no player meets a winning condition, declare a draw.
If a win or draw is determined, set the game end flag to true and display the "GAME OVER" message and the result.
4.6. Game End Handling
When the game ends (win/loss or draw), prevent further clicks on the cells.
Display the text "GAME OVER" followed by the message "X wins!," "O wins!," or "Draw!" underneath it.
4.7. Reset Functionality
When the "Reset" button is clicked, call the function to return the game to its initial state.
Enter the following prompt (Japanese Version)
以下の要件を満たす三目並べ（Tic-Tac-Toe）ゲームを開発してください。HTML、CSS、JavaScriptの各ファイルに分割し、JavaScriptはゲームロジックの大部分を単独で処理するようにしてください。
1. 全体要件
プレイヤーは人間1人、コンピューター1人の対戦形式とする。
ゲーム終了時（勝敗が決まった場合、または引き分けの場合）は、画面上に「GAME OVER」と表示し、勝者の名前（「Xの勝利！」「Oの勝利！」または「引き分け！」）も併記すること。
新しいゲームを開始するための「リセット」ボタンを設けること。
2. HTML (index.html)
基本的なページ構造を作成してください。
ゲームボードは、9つのマス目（セル）で構成されるようにしてください。各セルはクリック可能で、プレイヤーのマーク（XまたはO）が表示されるようにします。
ゲームの状態（現在のプレイヤーのターン、ゲーム結果など）を表示する要素を設けてください。
ゲームをリセットするためのボタンを配置してください。
CSSファイルとJavaScriptファイルを適切にリンクしてください。
3. CSS (style.css)
ゲームボードとマス目が視覚的に分かりやすいようにスタイルを設定してください。
マス目には枠線をつけ、クリック可能な領域であることがわかるようにする。
XとOの表示は、見やすいように適切なフォントサイズと色を設定する。
ゲームの状態表示、および「GAME OVER」メッセージが目立つようにスタイルを設定してください。
レスポンシブデザインを考慮し、様々な画面サイズで適切に表示されるようにしてください。
4. JavaScript (script.js)
JavaScriptファイルがゲームロジックの全てを処理することを強く要請します。
4.1. ゲームの状態管理
ゲームボードの状態を管理する配列またはオブジェクト（例: ['', '', '', '', '', '', '', '', '']）を定義してください。
現在のプレイヤー（XまたはO）を追跡する変数を定義してください。初期値はXとする。
ゲームが終了したかどうか（勝敗が決まったか、引き分けか）を追跡するブール値を定義してください。
4.2. ゲームの初期化
ページ読み込み時にゲームボードを初期化する関数を作成してください。
全てのマス目を空にする。
現在のプレイヤーをXに設定する。
ゲーム終了フラグをリセットする。
ゲーム結果表示をクリアする。
4.3. プレイヤーの操作
マス目をクリックした際のイベントリスナーを設定してください。
クリックされたマス目が空の場合のみ、現在のプレイヤーのマークを配置し、ボードの状態を更新する。
マークを配置した後、以下の処理を実行する。
勝敗判定関数を呼び出す。
勝敗が決まっていない場合、プレイヤーを交代する（XからO、OからXへ）。
4.4. コンピューターの思考ロジック
コンピューター（O）が手番の時に呼び出される関数を作成してください。
コンピューターは、空いているマス目の中からランダムに選択してマークを配置するシンプルなロジックを実装してください。（将来的に難易度を上げることも考慮できるが、最初はランダムで十分です）
コンピューターがマークを配置した後、勝敗判定を行い、勝敗が決まっていない場合はプレイヤーを人間に戻す。
4.5. 勝敗判定
現在のボードの状態に基づいて勝敗を判定する関数を作成してください。
以下の勝利条件をチェックする。
3つの行
3つの列
2つの対角線
勝利条件を満たすプレイヤーがいる場合、そのプレイヤーの勝利とする。
全てのマス目が埋まり、かつ勝利条件を満たすプレイヤーがいない場合、引き分けとする。
勝敗または引き分けが決まった場合、ゲーム終了フラグをtrueに設定し、「GAME OVER」メッセージと結果を表示する。
4.6. ゲーム終了時の処理
ゲームが終了した場合（勝敗が決まったか、引き分けか）は、それ以上マス目をクリックできないようにする。
「GAME OVER」というテキストと、その下に「Xの勝利！」「Oの勝利！」または「引き分け！」というメッセージを表示する。
4.7. リセット機能
「リセット」ボタンがクリックされた際に、ゲームを初期状態に戻す関数を呼び出す。
Start a terminal in the same folder and start a http server,
python3 -m http.server 8080
In the browser open (CTRL+click if you are in Cloud Shell):
http://localhost:8080
5. Run Gemini CLI Extensions
Gemini CLI provides some very useful extensions that can be installed and run easily. These extensions enable you to connect to various services and use them. https://geminicli.com/extensions/ a list of available extensions and it's growing each day. To learn more about Gemini CLI Extensions refer to this page, https://medium.com/google-cloud/gemini-cli-tutorial-series-part-11-gemini-cli-extensions-69a6f2abb659
Lets install a Gemini Nanobanana extension and run it.
To install the extension run the following command.
gemini extensions install https://github.com/gemini-cli-extensions/nanobanana
Once the extension is installed, restart Gemini CLI and you will be able to run the following nanobanana commands from gemini cli.
/generate- Single or multiple image generation with style/variation options/edit- Image editing/restore- Image restoration/icon- Generate app icons, favicons, and UI elements in multiple sizes/pattern- Generate seamless patterns and textures for backgrounds/story- Generate sequential images that tell a visual story or process/diagram- Generate technical diagrams, flowcharts, and architectural mockups/nanobanana- Natural language interface
Let's run a few commands
Before you run Nanobanana, you must get a Gemini API key from aistudio.google.com and set it here,
export NANOBANANA_GEMINI_API_KEY=YOUR_API_KEY
English version
# Single image /generate "a watercolor painting of a fox in a snowy forest" # Multiple variations with preview /generate "sunset over mountains" --count=3 --preview # Style variations /generate "mountain landscape" --styles="watercolor,oil-painting" --count=4 # Specific variations with auto-preview /generate "coffee shop interior" --variations="lighting,mood" --preview
Japanese Version
# Single image /generate "雪の森のキツネの水彩画" # Multiple variations with preview /generate "山にかかる夕焼け" --count=3 --preview # Style variations /generate "山岳風景" --styles="watercolor,oil-painting" --count=4 # Specific variations with auto-preview /generate "コーヒーショップのインテリア" --variations="lighting,mood" --preview
Edit images
Change the name of the file to your local file name.
/edit my_photo.png "change the color of fox to blue"
6. Complete
And you are done! Well done! For more please check out the following resources.