Firebase Genkit <> AWS Bedrock Plugin

AWS Bedrock Community Plugin for Google Firebase Genkit

genkitx-aws-bedrock is a community plugin for using AWS Bedrock APIs with Firebase Genkit. Built by Xavier Portilla Edo.

This Genkit plugin allows to use AWS Bedrock through their official APIs.

Installation

Install the plugin in your project with your favorite package manager:

• npm install genkitx-aws-bedrock
• pnpm add genkitx-aws-bedrock

Versions

if you are using Genkit version <v0.9.0, please use the plugin version v1.9.0. If you are using Genkit >=v0.9.0, please use the plugin version >=v1.10.0.

Usage

Configuration

To use the plugin, you need to configure it with your AWS credentials. There are several approaches depending on your environment.

Standard Initialization

You can configure the plugin by calling the genkit function with your AWS region and model:

import { genkit, z } from 'genkit';
import { awsBedrock, amazonNovaProV1 } from "genkitx-aws-bedrock";

const ai = genkit({
  plugins: [
    awsBedrock({ region: "<my-region>" }),
  ],
   model: amazonNovaProV1,
});

If you have set the AWS_ environment variables, you can initialize it like this:

import { genkit, z } from 'genkit';
import { awsBedrock, amazonNovaProV1 } from "genkitx-aws-bedrock";

const ai = genkit({
  plugins: [
    awsBedrock(),
  ],
   model: amazonNovaProV1,
});

Production Environment Authentication

In production environments, it is often necessary to install an additional library to handle authentication. One approach is to use the @aws-sdk/credential-providers package:

import { fromEnv } from "@aws-sdk/credential-providers";
const ai = genkit({
  plugins: [
    awsBedrock({
      region: "us-east-1",
      credentials: fromEnv(),
    }),
  ],
});

Ensure you have a .env file with the necessary AWS credentials. Remember that the .env file must be added to your .gitignore to prevent sensitive credentials from being exposed.

AWS_ACCESS_KEY_ID = 
AWS_SECRET_ACCESS_KEY =

Local Environment Authentication

For local development, you can directly supply the credentials:

const ai = genkit({
  plugins: [
    awsBedrock({
      region: "us-east-1",
      credentials: {
        accessKeyId: awsAccessKeyId.value(),
        secretAccessKey: awsSecretAccessKey.value(),
      },
    }),
  ],
});

Each approach allows you to manage authentication effectively based on your environment needs.

Configuration with Inference Endpoint

If you want to use a model that uses Cross-region Inference Endpoints, you can specify the region in the model configuration. Cross-region inference uses inference profiles to increase throughput and improve resiliency by routing your requests across multiple AWS Regions during peak utilization bursts:

import { genkit, z } from 'genkit';
import {awsBedrock, amazonNovaProV1, anthropicClaude35SonnetV2} from "genkitx-aws-bedrock";

const ai = genkit({
  plugins: [
    awsBedrock(),
  ],
   model: anthropicClaude35SonnetV2("us"),
});

You can check more information about the available models in the AWS Bedrock PLugin documentation.

Basic examples

The simplest way to call the text generation model is by using the helper function generate:

import { genkit, z } from 'genkit';
import {awsBedrock, amazonNovaProV1} from "genkitx-aws-bedrock";

// Basic usage of an LLM
const response = await ai.generate({
  prompt: 'Tell me a joke.',
});

console.log(await response.text);

Within a flow

// ...configure Genkit (as shown above)...

export const myFlow = ai.defineFlow(
  {
    name: 'menuSuggestionFlow',
    inputSchema: z.string(),
    outputSchema: z.string(),
  },
  async (subject) => {
    const llmResponse = await ai.generate({
      prompt: `Suggest an item for the menu of a ${subject} themed restaurant`,
    });

    return llmResponse.text;
  }
);

Tool use

// ...configure Genkit (as shown above)...

const specialToolInputSchema = z.object({ meal: z.enum(["breakfast", "lunch", "dinner"]) });
const specialTool = ai.defineTool(
  {
    name: "specialTool",
    description: "Retrieves today's special for the given meal",
    inputSchema: specialToolInputSchema,
    outputSchema: z.string(),
  },
  async ({ meal }): Promise<string> => {
    // Retrieve up-to-date information and return it. Here, we just return a
    // fixed value.
    return "Baked beans on toast";
  }
);

const result = ai.generate({
  tools: [specialTool],
  prompt: "What's for breakfast?",
});

console.log(result.then((res) => res.text));

For more detailed examples and the explanation of other functionalities, refer to the official Genkit documentation.

Supported models

This plugin supports all currently available Chat/Completion and Embeddings models from AWS Bedrock. This plugin supports image input and multimodal models.

API Reference

You can find the full API reference in the API Reference Documentation

Contributing

Want to contribute to the project? That's awesome! Head over to our Contribution Guidelines.

Need support?

[!NOTE]
This repository depends on Google's Firebase Genkit. For issues and questions related to Genkit, please refer to instructions available in Genkit's repository.

Reach out by opening a discussion on GitHub Discussions.

Credits

This plugin is proudly maintained by Xavier Portilla Edo Xavier Portilla Edo.

I got the inspiration, structure and patterns to create this plugin from the Genkit Community Plugins repository built by the Fire Compnay as well as the ollama plugin.

License

This project is licensed under the Apache 2.0 License.