API Reference

Complete API documentation for Gemini CLI with detailed method descriptions, parameters, and practical examples.

API Sections

Navigate to different API categories

Core API

Main API for interacting with Gemini models and managing conversations

Plugin API

API for developing custom plugins and extensions

Configuration API

API for managing CLI configuration and settings

Tools API

API for managing and executing built-in tools

Core API

Main API for interacting with Gemini models and managing conversations

chat()

Start an interactive chat session with Gemini

Signature:

chat(options?: ChatOptions): Promise<ChatSession>

Example:

import { GeminiCLI } from '@google/generative-ai-cli';

const cli = new GeminiCLI();
const session = await cli.chat({
  model: 'gemini-pro',
  temperature: 0.7
});

ask()

Send a single prompt and get a response

Signature:

ask(prompt: string, options?: AskOptions): Promise<string>

Example:

const response = await cli.ask("What is machine learning?", {
  maxTokens: 1000,
  temperature: 0.5
});

analyze()

Analyze files or code with AI assistance

Signature:

analyze(files: string[], options?: AnalyzeOptions): Promise<AnalysisResult>

Example:

const analysis = await cli.analyze(['src/main.js'], {
  type: 'code-review',
  includeMetrics: true
});

Plugin API

API for developing custom plugins and extensions

registerPlugin()

Register a new plugin with the CLI

Signature:

registerPlugin(plugin: Plugin): void

Example:

const myPlugin = {
  name: 'my-custom-plugin',
  version: '1.0.0',
  commands: {
    'custom-command': async (args) => {
      // Plugin logic here
      return 'Plugin executed successfully';
    }
  }
};

cli.registerPlugin(myPlugin);

createTool()

Create a custom tool for AI to use

Signature:

createTool(definition: ToolDefinition): Tool

Example:

const weatherTool = cli.createTool({
  name: 'get_weather',
  description: 'Get current weather for a location',
  parameters: {
    location: { type: 'string', required: true }
  },
  execute: async ({ location }) => {
    // Fetch weather data
    return `Weather in ${location}: Sunny, 25°C`;
  }
});

Configuration API

API for managing CLI configuration and settings

getConfig()

Get current configuration values

Signature:

getConfig(key?: string): any

Example:

// Get all config
const config = cli.getConfig();

// Get specific config value
const model = cli.getConfig('model');

setConfig()

Set configuration values

Signature:

setConfig(key: string, value: any): void

Example:

// Set model
cli.setConfig('model', 'gemini-pro');

// Set multiple values
cli.setConfig('temperature', 0.8);
cli.setConfig('maxTokens', 2000);

resetConfig()

Reset configuration to defaults

Signature:

resetConfig(key?: string): void

Example:

// Reset all config
cli.resetConfig();

// Reset specific key
cli.resetConfig('temperature');

Tools API

API for managing and executing built-in tools

listTools()

Get list of available tools

Signature:

listTools(): Tool[]

Example:

const tools = cli.listTools();
console.log(tools.map(t => t.name));
// ['read_file', 'write_file', 'run_shell_command', ...]

executeTool()

Execute a specific tool

Signature:

executeTool(name: string, args: any): Promise<any>

Example:

// Read a file
const content = await cli.executeTool('read_file', {
  path: './package.json'
});

// Run shell command
const result = await cli.executeTool('run_shell_command', {
  command: 'ls -la'
});

Common Types

TypeScript interfaces and types used across the API

ChatOptions

Options for starting a chat session

model
string

Model to use (e.g., "gemini-pro")

temperature
number

Creativity level (0-1)

maxTokens
number

Maximum response length

systemPrompt
string

System instructions

ToolDefinition

Definition for creating custom tools

name
string

Unique tool name

description
string

Tool description for AI

parameters
object

Parameter schema

execute
function

Tool execution function

Additional Resources

Explore more documentation and examples

View ExamplesBack to Docs