Remove Lambda Remove Performance Remove Reference
article thumbnail

Multi-LLM routing strategies for generative AI applications on AWS

AWS Machine Learning - AI

Although an individual LLM can be highly capable, it might not optimally address a wide range of use cases or meet diverse performance requirements. In contrast, more complex questions might require the application to summarize a lengthy dissertation by performing deeper analysis, comparison, and evaluation of the research results.

article thumbnail

Automate Amazon Bedrock batch inference: Building a scalable and efficient pipeline

AWS Machine Learning - AI

Refer to Supported Regions and models for batch inference for current supporting AWS Regions and models. To address this consideration and enhance your use of batch inference, we’ve developed a scalable solution using AWS Lambda and Amazon DynamoDB. We walk you through our solution, detailing the core logic of the Lambda functions.

article thumbnail

Create a generative AI–powered custom Google Chat application using Amazon Bedrock

AWS Machine Learning - AI

Before processing the request, a Lambda authorizer function associated with the API Gateway authenticates the incoming message. After it’s authenticated, the request is forwarded to another Lambda function that contains our core application logic. This request contains the user’s message and relevant metadata.

article thumbnail

Enhance customer support with Amazon Bedrock Agents by integrating enterprise data APIs

AWS Machine Learning - AI

The agents also automatically call APIs to perform actions and access knowledge bases to provide additional information. The Lambda function runs the database query against the appropriate OpenSearch Service indexes, searching for exact matches or using fuzzy matching for partial information.

Lambda 127
article thumbnail

AWS Lambda Benchmarking

Xebia

In this blog post, we examine the relative costs of different language runtimes on AWS Lambda. Many languages can be used with AWS Lambda today, so we focus on four interesting ones. Rust just came to AWS Lambda in November 2023 , so probably a lot of folks are wondering whether to try it out.

Lambda 130
article thumbnail

Build a multi-tenant generative AI environment for your enterprise on AWS

AWS Machine Learning - AI

It also uses a number of other AWS services such as Amazon API Gateway , AWS Lambda , and Amazon SageMaker. Shared components refer to the functionality and features shared by all tenants. If it leads to better performance, your existing default prompt in the application is overridden with the new one.

article thumbnail

Transcribe, translate, and summarize live streams in your browser with AWS AI and generative AI services

AWS Machine Learning - AI

The solution also uses Amazon Cognito user pools and identity pools for managing authentication and authorization of users, Amazon API Gateway REST APIs, AWS Lambda functions, and an Amazon Simple Storage Service (Amazon S3) bucket. Authentication is performed against the Amazon Cognito user pool.