OpenAI Plugin

The genkit-plugin-compat-oai package includes a pre-configured plugin for official OpenAI models.

Installation

pip install genkit-plugin-compat-oai

Configuration

To use this plugin, import OpenAI and openai_model and specify it when you initialize Genkit:

from genkit.ai import Genkit
from genkit.plugins.compat_oai import OpenAI, openai_model

ai = Genkit(plugins=[OpenAI()], model=openai_model('gpt-4o'))

The plugin requires an API key for the OpenAI API. You can get one from the OpenAI Platform.

Configure the plugin to use your API key by doing one of the following:

Set the OPENAI_API_KEY environment variable to your API key.
Specify the API key when you initialize the plugin:
```
OpenAI(api_key=your_key)
```
However, don’t embed your API key directly in code!

Usage

The plugin provides helpers to reference supported models.

Chat Models

You can reference chat models like gpt-4o and gpt-4-turbo using the openai_model() helper.

import structlog
from pydantic import BaseModel, Field

from genkit.ai import Genkit
from genkit.plugins.compat_oai import OpenAI, openai_model

logger = structlog.get_logger(__name__)

ai = Genkit(plugins=[OpenAI()])


@ai.flow()
async def say_hi(name: str) -> str:
    """Say hi to a name.

    Args:
        name: The name to say hi to.

    Returns:
        The response from the OpenAI API.
    """
    response = await ai.generate(
        model=openai_model('gpt-4'),
        prompt=f'hi {name}',
    )
    return response.message.content[0].root.text

You can also pass model-specific configuration:

response = await ai.generate(
    model=openai_model('gpt-4'),
    config={'temperature': 1},
    prompt=f'hi {name}',
)

Tool Calling

You can define and use tools with OpenAI models.

import httpx
from decimal import Decimal
from pydantic import BaseModel

from genkit.ai import Genkit
from genkit.plugins.compat_oai import OpenAI, openai_model

ai = Genkit(plugins=[OpenAI()])

class WeatherRequest(BaseModel):
    """Weather request."""

    latitude: Decimal
    longitude: Decimal

@ai.tool(description='Get current temperature for provided coordinates in celsius')
def get_weather_tool(coordinates: WeatherRequest) -> float:
    """Get the current temperature for provided coordinates in celsius.

    Args:
        coordinates: The coordinates to get the weather for.

    Returns:
        The current temperature for the provided coordinates.
    """
    url = (
        f'https://api.open-meteo.com/v1/forecast?'
        f'latitude={coordinates.latitude}&longitude={coordinates.longitude}'
        f'&current=temperature_2m'
    )
    with httpx.Client() as client:
        response = client.get(url)
        data = response.json()
        return float(data['current']['temperature_2m'])

@ai.flow()
async def get_weather_flow(location: str) -> str:
    """Get the weather for a location.

    Args:
        location: The location to get the weather for.

    Returns:
        The weather for the location.
    """
    response = await ai.generate(
        model=openai_model('gpt-4o-mini'),
        prompt=f"What's the weather like in {location} today?",
        tools=['get_weather_tool'],
    )
    # The response will contain the tool output if the model decided to call it.
    return response.message.content[0].root.text

Streaming

The plugin supports streaming responses.

@ai.flow()
async def say_hi_stream(name: str) -> str:
    """Say hi to a name and stream the response.

    Args:
        name: The name to say hi to.

    Returns:
        The response from the OpenAI API.
    """
    stream, _ = ai.generate_stream(
        model=openai_model('gpt-4'),
        prompt=f'hi {name}',
    )
    result = ''
    async for data in stream:
        for part in data.content:
            result += part.root.text
    return result

The @genkit-ai/compat-oai package includes a pre-configured plugin for official OpenAI models.

Installation

npm install @genkit-ai/compat-oai

Configuration

To use this plugin, import openAI and specify it when you initialize Genkit:

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

export const ai = genkit({
  plugins: [openAI()],
});

The plugin requires an API key for the OpenAI API. You can get one from the OpenAI Platform.

Configure the plugin to use your API key by doing one of the following:

Set the OPENAI_API_KEY environment variable to your API key.
Specify the API key when you initialize the plugin:
```
openAI({ apiKey: yourKey });
```
However, don’t embed your API key directly in code! Use this feature only in conjunction with a service like Google Cloud Secret Manager or similar.

Usage

The plugin provides helpers to reference supported models and embedders.

Chat Models

You can reference chat models like gpt-4o and gpt-4-turbo using the openAI.model() helper.

import { genkit, z } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

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

export const jokeFlow = ai.defineFlow(
  {
    name: 'jokeFlow',
    inputSchema: z.object({ subject: z.string() }),
    outputSchema: z.object({ joke: z.string() }),
  },
  async ({ subject }) => {
    const llmResponse = await ai.generate({
      prompt: `tell me a joke about ${subject}`,
      model: openAI.model('gpt-4o'),
    });
    return { joke: llmResponse.text };
  },
);

You can also pass model-specific configuration:

const llmResponse = await ai.generate({
  prompt: `tell me a joke about ${subject}`,
  model: openAI.model('gpt-4o'),
  config: {
    temperature: 0.7,
  },
});

Image Generation Models

The plugin supports image generation models like DALL-E 3.

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

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

// Reference an image generation model
const dalle3 = openAI.model('dall-e-3');

// Use it to generate an image
const imageResponse = await ai.generate({
  model: dalle3,
  prompt: 'A photorealistic image of a cat programming a computer.',
  config: {
    size: '1024x1024',
    style: 'vivid',
  },
});

const imageUrl = imageResponse.media()?.url;

Text Embedding Models

You can use text embedding models to create vector embeddings from text.

import { genkit, z } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

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

export const embedFlow = ai.defineFlow(
  {
    name: 'embedFlow',
    inputSchema: z.object({ text: z.string() }),
    outputSchema: z.object({ embedding: z.string() }),
  },
  async ({ text }) => {
    const embedding = await ai.embed({
      embedder: openAI.embedder('text-embedding-ada-002'),
      content: text,
    });

    return { embedding: JSON.stringify(embedding) };
  },
);

Audio Transcription and Speech Models

The OpenAI plugin also supports audio models for transcription (speech-to-text) and speech generation (text-to-speech).

Transcription (Speech-to-Text)

Use models like whisper-1 to transcribe audio files.

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';
import * as fs from 'fs';

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

const whisper = openAI.model('whisper-1');
const audioFile = fs.readFileSync('path/to/your/audio.mp3');

const transcription = await ai.generate({
  model: whisper,
  prompt: [
    {
      media: {
        contentType: 'audio/mp3',
        url: `data:audio/mp3;base64,${audioFile.toString('base64')}`,
      },
    },
  ],
});

console.log(transcription.text());

Speech Generation (Text-to-Speech)

Use models like tts-1 to generate speech from text.

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';
import * as fs from 'fs';

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

const tts = openAI.model('tts-1');
const speechResponse = await ai.generate({
  model: tts,
  prompt: 'Hello, world! This is a test of text-to-speech.',
  config: {
    voice: 'alloy',
  },
});

const audioData = speechResponse.media();
if (audioData) {
  fs.writeFileSync('output.mp3', Buffer.from(audioData.url.split(',')[1], 'base64'));
}

Advanced usage

Passthrough configuration

You can pass configuration options that are not defined in the plugin’s custom configuration schema. This permits you to access new models and features without having to update your Genkit version.

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

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

const llmResponse = await ai.generate({
  prompt: `Tell me a cool story`,
  model: openAI.model('gpt-4-new'), // hypothetical new model
  config: {
    seed: 123,
    new_feature_parameter: ... // hypothetical config needed for new model
  },
});

Genkit passes this config as-is to the OpenAI API giving you access to the new model features. Note that the field name and types are not validated by Genkit and should match the OpenAI API specification to work.

Web-search built-in tool

Some OpenAI models support web search. You can enable it in the config block:

import { genkit } from 'genkit';
import { openAI } from '@genkit-ai/compat-oai/openai';

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

const llmResponse = await ai.generate({
  prompt: `What was a positive news story from today?`,
  model: openAI.model('gpt-4o-search-preview'),
  config: {
    web_search_options: {},
  },
});

The OpenAI plugin provides access to OpenAI models.

Configuration

import "github.com/firebase/genkit/go/plugins/compat_oai/openai"

g := genkit.Init(context.Background(), genkit.WithPlugins(&openai.OpenAI{
    APIKey: "YOUR_OPENAI_API_KEY", // or set OPENAI_API_KEY env var
}))

Supported Models

Latest Models

gpt-4.1 - Latest GPT-4.1 with multimodal support
gpt-4.1-mini - Faster, cost-effective GPT-4.1 variant
gpt-4.1-nano - Ultra-efficient GPT-4.1 variant
gpt-4.5-preview - Preview of GPT-4.5 with advanced capabilities

Production Models

gpt-4o - Advanced GPT-4 with vision and tool support
gpt-4o-mini - Fast and cost-effective GPT-4o variant
gpt-4-turbo - High-performance GPT-4 with large context window

Reasoning Models

o3-mini - Latest compact reasoning model
o1 - Advanced reasoning model for complex problems
o1-mini - Compact reasoning model
o1-preview - Preview reasoning model

Legacy Models

gpt-4 - Original GPT-4 model
gpt-3.5-turbo - Fast and efficient language model

Embedding Models

text-embedding-3-large - Most capable embedding model
text-embedding-3-small - Fast and efficient embedding model
text-embedding-ada-002 - Legacy embedding model

Usage Example

import (
    "github.com/firebase/genkit/go/plugins/compat_oai/openai"
    "github.com/firebase/genkit/go/plugins/compat_oai"
)

// Initialize Genkit with the OpenAI plugin
g := genkit.Init(ctx, genkit.WithPlugins(&openai.OpenAI{APIKey: "YOUR_API_KEY"}))

// Use GPT-4o for general tasks
model := oai.Model(g, "gpt-4o")
resp, err := genkit.Generate(ctx, g,
    ai.WithModel(model),
    ai.WithPrompt("Explain quantum computing."),
)

// Use embeddings
embedder := oai.Embedder(g, "text-embedding-3-large")
embeds, err := ai.Embed(ctx, embedder, ai.WithDocs("Hello, world!"))

Advanced Features

Tool Calling

OpenAI models support tool calling:

// Define a tool
weatherTool := genkit.DefineTool(g, "get_weather", "Get current weather",
    func(ctx *ai.ToolContext, input struct{City string}) (string, error) {
        return fmt.Sprintf("It's sunny in %s", input.City), nil
    })

// Use with GPT models
model := oai.Model(g, "gpt-4o")
resp, err := genkit.Generate(ctx, g,
    ai.WithModel(model),
    ai.WithPrompt("What's the weather like in San Francisco?"),
    ai.WithTools(weatherTool),
)

Multimodal Support

OpenAI models support vision capabilities:

// Works with GPT-4o models
resp, err := genkit.Generate(ctx, g,
    ai.WithModel(model),
    ai.WithMessages(
        ai.NewUserMessage(
            ai.NewTextPart("What do you see in this image?"),
            ai.NewMediaPart("image/jpeg", imageData),
        ),
    ),
)

Streaming

OpenAI models support streaming responses:

resp, err := genkit.Generate(ctx, g,
    ai.WithModel(model),
    ai.WithPrompt("Write a long explanation."),
    ai.WithStreaming(func(ctx context.Context, chunk *ai.ModelResponseChunk) error {
        for _, content := range chunk.Content {
            fmt.Print(content.Text)
        }
        return nil
    }),
)