Quick Start

Get started with Genkit in under a minute across JavaScript, Go, or Python

Quick Start

Get up and running with Genkit in under a minute. Choose your preferred language and follow the steps below.

JavaScript/TypeScript

Prerequisites

• Node.js 20 or higher
• npm or yarn

Installation

1. Install Genkit and Google AI plugin

   npm install genkit @genkit-ai/google-genai
   
2. Install the Genkit CLI

   npm install -g genkit-cli
   
3. Get an API key

   Get a Google AI API key from Google AI Studio.

   Set it as an environment variable:

   export GOOGLE_GENAI_API_KEY="your-api-key"
   

Your First Genkit App

Create a file called index.ts (or index.js):

index.ts

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/google-genai';

const ai = genkit({ plugins: [googleAI()] });

const { text } = await ai.generate({
    model: googleAI.model('gemini-2.5-flash'),
    prompt: 'Why is Firebase awesome?'
});

console.log(text);

Run Your App

TypeScript (tsx)

npx tsx index.ts

You should see the AI-generated response printed to your console!

Launch the Developer UI

The Genkit Developer UI helps you test and debug your AI flows:

genkit start -- npx tsx index.ts

Open your browser to the URL shown in the terminal (usually http://localhost:4000) to access the Developer UI.

Next Steps

Build Your First Flow

Learn how to create deployable AI workflows

Add Tool Calling

Enable your AI to use external functions and APIs

Structured Output

Generate type-safe JSON responses

Deploy to Production

Ship your AI features to Cloud Run, Firebase, or anywhere

Go

Prerequisites

• Go 1.23 or higher

Installation

1. Initialize your Go module

   mkdir genkit-app
   cd genkit-app
   go mod init example/genkit-app
   
2. Install Genkit for Go

   go get github.com/firebase/genkit/go
   
3. Install the Genkit CLI

   curl -sL cli.genkit.dev | bash
   
4. Get an API key

   Get a Google AI API key from Google AI Studio.

   Set it as an environment variable:

   export GEMINI_API_KEY="your-api-key"
   

Your First Genkit App

Create a file called main.go:

main.go

package main

import (
    "context"
    "fmt"

    "github.com/firebase/genkit/go/ai"
    "github.com/firebase/genkit/go/genkit"
    "github.com/firebase/genkit/go/plugins/googlegenai"
)

func main() {
    ctx := context.Background()
    g := genkit.Init(ctx, genkit.WithPlugins(&googlegenai.GoogleAI{}))

    answer, err := genkit.GenerateText(ctx, g,
        ai.WithModelName("googleai/gemini-2.5-flash"),
        ai.WithPrompt("Why is Go a great language for AI applications?"),
    )
    if err != nil {
        fmt.Println("could not generate: %s", err)
    }
    fmt.Println(answer)
}

Run Your App

export GEMINI_API_KEY="your-api-key"
go run main.go

You should see the AI-generated response printed to your console!

Launch the Developer UI

The Genkit Developer UI helps you test and debug your AI flows:

genkit start -- go run main.go

Open your browser to the URL shown in the terminal (usually http://localhost:4000) to access the Developer UI.

Next Steps

Define Flows

Create deployable AI workflows with tracing

Add Tools

Give your AI the ability to call functions

Structured Data

Generate type-safe Go structs from AI models

HTTP Endpoints

Expose flows as HTTP endpoints

Python

The Python SDK is currently in Alpha. APIs may change, and some features are still under development.

Prerequisites

• Python 3.10 or higher
• uv package manager (recommended)

Installation

1. Install uv package manager

   curl -LsSf https://astral.sh/uv/install.sh | sh
   
2. Create a new project

   mkdir genkit-app
   cd genkit-app
   uv init
   
3. Install Genkit and Google GenAI plugin

   uv add genkit genkit-google-genai
   
4. Get an API key

   Get a Google AI API key from Google AI Studio.

   Set it as an environment variable:

   export GOOGLE_GENAI_API_KEY="your-api-key"
   

Your First Genkit App

Create a file called main.py:

main.py

from genkit import Genkit
from genkit.plugins.google_genai import GoogleGenAI, gemini_2_0_flash

ai = Genkit(
    plugins=[GoogleGenAI()],
    model=gemini_2_0_flash,
)

response = await ai.generate(prompt="Tell me a joke")
print(response.text)

Run Your App

export GOOGLE_GENAI_API_KEY="your-api-key"
uv run python main.py

You should see the AI-generated response printed to your console!

Launch the Developer UI

The Genkit Developer UI helps you test and debug your AI flows:

genkit start -- uv run python main.py

Install the Genkit CLI first: curl -sL cli.genkit.dev | bash

Open your browser to the URL shown in the terminal (usually http://localhost:4000) to access the Developer UI.

Next Steps

Define Flows

Create deployable AI workflows with full tracing

Tool Calling

Build agents that can call external functions

Structured Output

Generate Pydantic models from AI responses

Deploy with Flask

Expose flows as HTTP endpoints

Common Next Steps

Regardless of which language you chose, here are some common next steps:

Explore Model Providers

Connect to OpenAI, Anthropic, Ollama, and more

Learn Core Concepts

Understand flows, tools, prompts, and the Genkit architecture

Try Examples

Explore interactive examples and sample applications

Join the Community

Get help and share ideas with other developers

Need Help?

If you run into any issues:

• Search existing GitHub issues
• Ask in our Discord community
• Review the API documentation
• Check out the Community resources