AWS re:Post Knowledge Center Spotlight: Amazon Bedrock

The AWS re:Post Knowledge Center is your one-stop-shop for authoritative, up-to-date guidance on using AWS services. This month, we're highlighting Amazon Bedrock, a fully managed service that offers a choice of high-performing foundation models (FM) from leading AI companies.

Amazon Bedrock offers the easiest way to build and scale generative AI applications with FMs. Whether you're new to Amazon Bedrock or an experienced user, the following Knowledge Center articles equip you with the skills and troubleshooting tips to get the most out of this powerful service.

Handling long-running requests in Amazon Bedrock

Large language models can sometimes take a while to generate responses, leading to potential read timeout errors. Learn how to configure your Amazon Bedrock applications to gracefully handle long-running requests and provide a smooth user experience.

How do I prevent read timeouts in Python when I use large models in Amazon Bedrock?

Managing Amazon Bedrock knowledge bases

Building and maintaining knowledge bases in Amazon Bedrock allows you to augment responses from Large Learning Models (LLMs). These articles dive into how to build and use knowledge bases.

How do I use the RetrieveAndGenerate API to reuse a knowledge base session in Amazon Bedrock?

How do I use the Amazon OpenSearch Serverless collection with a private network policy to create a knowledge base in Amazon Bedrock?

Optimizing prompt engineering

Creating effective prompts is key to eliciting high quality responses from your LLMs. Learn how to create effective prompts to get more consistent and reliable results in Amazon Bedrock.

How do I optimize prompts to achieve deterministic responses on Amazon Bedrock?

Using cross-account access in Amazon Bedrock

Cross-account access allows you to use the Amazon Bedrock API across accounts, bringing AI to other applications. The following articles explain how to turn on and use cross-account access.

How do I use a cross-account to invoke Amazon Bedrock in my account?

How do I use a cross-account to invoke Amazon Bedrock in my account?

Upgrading AI models in Amazon Bedrock

AI models provide the foundation for building generative AI applications with Amazon Bedrock. Learn how to upgrade the boto3 and botocore libraries.

How do I upgrade boto3 and botocore in AWS Lambda to access newer AI models?

Troubleshooting errors

Access errors can occur in Amazon Bedrock for a variety of reasons. The following articles help you troubleshoot permissions, eligibility, model usage, and validation errors.

How do I resolve validation exceptions in Amazon Bedrock?

How do I troubleshoot the InvokeModel API error in Amazon Bedrock?

How do I resolve the error "Unauthorized to perform action due to private marketplace eligibility"?

How do I troubleshoot the permission errors I get when I create a knowledge base in Amazon Bedrock?

Next steps

Have more questions about Amazon Bedrock? Check out the re:Post Amazon Bedrock knowledge base or ask your own question to get guidance from the AWS community.