Amazon Bedrock Connector 1.0

Anypoint Connector for Amazon Bedrock (Amazon Bedrock Connector) provides seamless access to Amazon Bedrock, a fully managed service offering high-performing foundation models (FMs) from leading AI providers. The connector enables customers to invoke, evaluate, and integrate Bedrock models and operations within Mule flows, supporting use cases such as prompt-based inference, Retrieval-Augmented Generation (RAG), and agent-driven, multi-step workflows over enterprise data. While each model provider exposes different APIs and capabilities, the connector abstracts these differences and offers a unified, consistent interface to interact with all supported Bedrock models through MuleSoft.

For information about compatibility and fixed issues, see the Amazon Bedrock Connector release notes.

Before You Begin

To use this connector, you must be familiar with:

Anypoint Connectors
Mule runtime engine (Mule)
Elements and global elements in a Mule flow
How to create a Mule app using Anypoint Code Builder or Anypoint Studio
Amazon Web Services (AWS) and Amazon Bedrock

Before creating an app, you must have:

Java 17 (required for compilation and runtime)
Apache Maven
An AWS account with access to Amazon Bedrock
Valid AWS credentials
Anypoint Platform
The latest versions of Anypoint Code Builder or Anypoint Studio

Supported Foundation Model Providers

Amazon Bedrock Connector provides access to all foundation models supported by Amazon Bedrock, including models from Amazon and third-party AI providers, through a single, unified MuleSoft interface. Custom models aren’t supported.

AI21 Labs J2
Amazon Nova
Amazon Titan
Anthropic Claude
Cohere
Meta Llama 2
Meta Llama 3
Mistral AI
Stability AI

Key Features

Amazon Bedrock Connector simplifies AI integration into Mule applications with:

Seamless Interaction with LLMs and Agents

Integrate and utilize foundation models and agents effortlessly. Amazon Bedrock offers a choice of leading foundation models through a single API, allowing you to experiment with and evaluate top models for your use case.
Optimized Performance in Mule Apps

Deliver high efficiency and performance in enterprise-grade Mule apps. Since Amazon Bedrock is serverless, you don’t have to manage any infrastructure, and you can securely integrate and deploy generative AI capabilities into your applications using AWS services.
Access to a Wide Variety of LLM Providers

Connect to your preferred LLM provider through a unification layer. Amazon Bedrock Connector provides the ability to connect to all supported LLMs, simplifying how you interact with different model providers.

Connector Capabilities

Amazon Bedrock Connector provides a variety of powerful features:

Language Models

Integrate language models to generate text, perform language analysis, and handle complex language tasks.
Embeddings

Utilize embedding models to transform text into numerical vectors for tasks like text similarity, clustering, and search functionalities.
Tools Integration

Incorporate APIs and other dynamic functionalities into MuleSoft, facilitating the use of external services and data processing tools.
Image Models

Work with image models for tasks such as image generation, recognition, and manipulation.
Streaming

Support real-time data processing and interaction with language models.

Amazon Bedrock Service Features

Amazon Bedrock offers advanced features that enhance generative AI application development:

Knowledge Bases

Give foundation models and agents contextual information from your company’s private data sources for Retrieval Augmented Generation (RAG) to deliver more relevant, accurate, and customized responses.
Agents

Enable generative AI applications to execute multistep tasks across company systems and data sources. Agents for Bedrock streamline workflows and automate repetitive tasks.
Memory Retention

Agents for Amazon Bedrock can retain memory across interactions, offering more personalized and seamless user experiences. This feature allows agents to remember historical interactions and improve the accuracy of multi-step tasks.
Guardrails

Implement safeguards customized to your application requirements and responsible AI policies. Guardrails for Amazon Bedrock evaluates user inputs and FM responses based on use case specific policies.
Security and Privacy

Maintain full control over the data you use to customize foundation models. Your data is encrypted in transit and at rest, and you can create, manage, and control encryption keys using AWS Key Management Service (AWS KMS). Your data is not shared with model providers and is not used to improve the base models.

Enhanced Capabilities via Anypoint Platform

You can leverage Anypoint Platform to provide enhanced capabilities, including:

End-to-End Lifecycle Management for AI Agents

Manages the complete lifecycle of AI agents, from design to deployment.
Centralized AI Agent Design

Streamlines design through Anypoint Design Center.
AI Agent Portal

Provides centralized management and access via Exchange and Anypoint Experience Hub.
Comprehensive Monitoring

Enables detailed monitoring and visualization with Anypoint Monitoring and Visualizer.
Low-Code Development Environment

Simplifies development with Anypoint Studio and Anypoint Code Builder.
Robust Unit-Testing Framework

Ensures thorough testing capabilities with MUnit, available in Anypoint Studio.

Additional Integrations

Amazon Bedrock integrates seamlessly with the MuleSoft ecosystem:

Dynamic Tooling through Configuration Files

Allows for flexible and customizable setups.
Extensive Tooling through Anypoint Exchange

Facilitates easy integration and management of various tools.

Next Step

After you complete the prerequisites, you are ready to create an app and configure the connector using Anypoint Studio or Anypoint Code Builder.