Genkit

Genkit is an open-source framework for building full-stack AI-powered applications, built and used in production by Google's Firebase.

Verified

Core facts

Read by a script from the official API, not rewritten by a model.

License
Apache-2.0
Languages
TypeScript
Maintainer
genkit-ai
Verified

What it is

Genkit is an open-source framework for building full-stack AI-powered applications, built and used in production by Google's Firebase. Genkit provides SDKs for multiple programming languages with varying levels of stability. Genkit offers a unified interface for integrating AI models from providers like Google, OpenAI, Anthropic, Ollama, and more. Genkit is built by Google with contributions from the Open Source Community.

Main features

  1. Genkit offers text and image generation.

  2. Genkit offers type-safe, structured data generation.

  3. Genkit offers tool calling and prompt templating.

  4. Genkit offers persisted chat interfaces and AI workflows.

  5. Genkit offers AI-powered data retrieval (RAG).

  6. The Genkit developer UI is a local interface for testing, debugging, and iterating on an AI application, and its Run feature executes and experiments with Genkit flows, prompts, queries, and more in dedicated playgrounds.

  7. The developer UI Inspect feature analyzes detailed traces of past executions, including step-by-step breakdowns of complex flows, and its Evaluate feature reviews results of evaluations run against flows, including performance metrics and links to relevant traces.

Getting started

  1. The reader selects the Genkit SDK for a preferred language: JavaScript/TypeScript, Go, Python (Beta), or Dart (Preview).

  2. The reader installs the Genkit SDK, a model-provider package of choice, and the Genkit CLI.

  3. The Genkit and provider packages are imported, and Genkit is initialized with the provider API key.

  4. The Genkit SDK is used to build AI features, from basic text generation to complex multi-step workflows and agents.

  5. The Genkit CLI includes commands for running and evaluating Genkit functions (flows) and collecting telemetry and logs.

  6. AI features are integrated into an app and monitored in production in the Firebase console.

From the README · 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-flash-latest'),
    prompt: 'What is the meaning of life?'
});

Who it is for

The project describes the Python (Beta) SDK as having wide feature support approaching production-readiness. The Dart (Preview) SDK is described as early development with core functionality. Genkit is designed for server-side deployment in multiple language environments and provides client-side integration through dedicated helpers and client SDKs.

Genkit lists a JavaScript/TypeScript quickstart. Genkit lists a Go quickstart. Genkit lists a Python quickstart, marked Beta.

Genkit lists a Dart quickstart, marked Preview.

Sources

This page is written from the official sources below. Open them to check the original text.

Verified ·

This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.