![A developer's guide to Bedrock's new Converse API](https://assets.community.aws/a/2hVSmtwFxlFatStRI4iNqno9cH1/imag.webp)
A developer's guide to Bedrock's new Converse API
Learn how to send your first request to a generative AI model using Amazon Bedrock's Converse API and the AWS SDK for JavaScript.
Dennis Traub
Amazon Employee
Published May 30, 2024
Last Modified Jul 9, 2024
[ Open the Java edition | Jump directly to the code 💻 ]
The Converse API is a new addition to the Amazon Bedrock Runtime, designed to simplify the interaction with text-based generative AI models. It offers a cohesive set of functionality through a common and strongly-typed request format, regardless of the specific foundation model being used.
In this tutorial, we'll explore the Converse API and learn how to leverage its capabilities to build engaging and interactive applications. Whether you're new to AI or an experienced developer, this guide will walk you through the process of sending your first request to a generative AI model.
This edition of the tutorial uses JavaScript. I've also prepared a Java edition, and have uploaded many more examples in Python, C#, etc.
This series guides you through Amazon Bedrock's Converse API:
- In Part 1: Getting Started (this post), you will learn how to send your first request.
- In Part 2: Conversational AI, I'll show you how to implement conversational turns.
- In Part 3: Customizing AI Behavior, we'll configure the model with a system prompt and additional inference parameters.
Future posts will cover extracting invocation metrics and metadata, sending and receiving model-specific parameters and fields, processing model responses in real-time, the new tool-use feature, and more.
Let's dive in and start building! 💻
Throughout the following steps, you will learn how to use the Amazon Bedrock Runtime client for JavaScript to send a message to a foundation model and print the response.
Let's get started!
Before you begin, ensure all prerequisites are in place. You should have:
- An AWS account
- The AWS CLI installed and configured with your credentials
- The latest stable version of Node.js and npm installed
- Requested access to the model you want to use
First, install the Bedrock Runtime client from the AWS SDK for JavaScript v3:
In a new JavaScript file, import the required modules:
Create an instance of the
BedrockRuntimeClient
, specifying the AWS region where the model is available:Specify the ID of the model you want to use. In this example, we'll use Claude 3 Haiku:
You can find the complete list of models supporting the Converse API and a list of all available model IDs in the documentation.
Prepare the first user message and add it to a new conversation array:
The conversation array represents the conversation history, with each element containing a role (e.g., "user" or "assistant") and at least one content block with the message text.
Send the conversation to the model using a
ConverseCommand
:The ConverseCommand sends the conversation to the specified model and returns its response.
Print out the model's response:
With the code complete, let's run it and see the AI engage in a multi-turn conversation!
Here's the full code for reference:
To run it:
- Save the code in a file named
bedrock_first_message.js
- In your terminal, navigate to the directory containing
bedrock_first_message.js
- Run the following command:
If you encounter any errors, double check that you have:
- Configured your AWS credentials
- Requested access to the model you are using
- Installed the required dependencies
Congratulations on sending your first request to the Amazon Bedrock Converse API! With just a few lines of code, you've successfully interacted with a generative AI model.
Ready for more? Here are some ideas to keep exploring:
- Experiment with different models and compare their responses. Here's the list of all models supporting the Converse API.
- Challenge yourself to rewrite this program in another language. Here are examples in Python, Java, C#, and more.
- Dive deeper into the Converse API in the Amazon Bedrock User Guide.
In Part 2 of this series, we'll dive deeper into the Converse API and learn how to maintain a conversation history and handle multi-turn conversations.
I'd love to see what you build with Amazon Bedrock! Feel free to share your projects or ask questions in the comments.
Thanks for following along and happy building! 💻🤖
Any opinions in this post are those of the individual author and may not reflect the opinions of AWS.