AWS Machine Learning

MARCH 6, 2023

In this post, we dive into tips and best practices for successful LLM training on Amazon SageMaker Training. The post covers all the phases of an LLM training workload and describes associated infrastructure features and best practices. Some of the best practices in this post refer specifically to ml.p4d.24xlarge

Best practices 105

Best practices APIs Transportation Scripts 105

AWS Machine Learning

NOVEMBER 1, 2024

In this post, we explore the best practices and lessons learned for fine-tuning Anthropic’s Claude 3 Haiku on Amazon Bedrock. We also provide insights on how to achieve optimal results for different dataset sizes and use cases, backed by experimental data and performance metrics.

Best practices 96

Best practices APIs Finance Engineering 96

AWS Machine Learning

JULY 7, 2022

You liked the overall experience and now want to deploy the bot in your production environment, but aren’t sure about best practices for Amazon Lex. In this post, we review the best practices for developing and deploying Amazon Lex bots, enabling you to streamline the end-to-end bot lifecycle and optimize your operations.

Best practices 98

Best practices Metrics APIs Accountability 98

AWS Machine Learning

JANUARY 10, 2023

This post describes the best practices for load testing a SageMaker endpoint to find the right configuration for the number of instances and size. This post assumes you are familiar with how to deploy a model. This can help us understand the minimum provisioned instance requirements to meet our latency and TPS requirements.

Best practices 100

Best practices Scripts APIs Metrics 100

AWS Machine Learning

OCTOBER 2, 2024

This two-part series explores best practices for building generative AI applications using Amazon Bedrock Agents. This data provides a benchmark for expected agent behavior, including the interaction with existing APIs, knowledge bases, and guardrails connected with the agent.

Best practices 97

Best practices APIs Metrics Accountability 97

AWS Machine Learning

JUNE 30, 2022

In part 1 of this series, we demonstrated how to resolve an Amazon SageMaker Studio presigned URL from a corporate network using Amazon private VPC endpoints without traversing the internet. The user invokes createStudioPresignedUrl API on API Gateway along with a token in the header. Deploy the solution. Deploy the solution.

APIs 98

APIs Enterprise Big data Accountability 98

AWS Machine Learning

NOVEMBER 14, 2024

Reactive governance is for finding resources that lack proper tags using tools such as the AWS Resource Groups tagging API, AWS Config rules, and custom scripts. AWS Resource Groups tagging API – The AWS Resource Groups Tagging API lets you tag or untag resources. You should take action when resources lack necessary tags.

Government 107

Government Best practices Accountability APIs 107

AWS Machine Learning

APRIL 9, 2024

In this post, we discuss two new features of Knowledge Bases for Amazon Bedrock specific to the RetrieveAndGenerate API: configuring the maximum number of results and creating custom prompts with a knowledge base prompt template. Adjust the prompt template to customize how you want to use the retrieved results and generate content.

APIs 133

APIs Engineering Healthcare Education 133

AWS Machine Learning

FEBRUARY 9, 2024

Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon via a single API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI.

SaaS 144

SaaS APIs Government Accountability 144

AWS Machine Learning

JANUARY 24, 2025

In this post, we show you an example of a generative AI assistant application and demonstrate how to assess its security posture using the OWASP Top 10 for Large Language Model Applications , as well as how to apply mitigations for common threats. These steps might involve both the use of an LLM and external data sources and APIs.

APIs 114

APIs Scripts Best practices Management 114

AWS Machine Learning

SEPTEMBER 18, 2024

Amazon Bedrock enables access to powerful generative AI models like Stable Diffusion through a user-friendly API. The user chooses Call API to invoke API Gateway to begin processing on the backend. The API invokes a Lambda function, which uses the Amazon Bedrock API to invoke the Stability AI SDXL 1.0

APIs 127

APIs Best practices Entertainment Advertising 127

AWS Machine Learning

NOVEMBER 7, 2024

It also uses a number of other AWS services such as Amazon API Gateway , AWS Lambda , and Amazon SageMaker. API Gateway is serverless and hence automatically scales with traffic. API Gateway also provides a WebSocket API. Incoming requests to the gateway go through this point.

Enterprise 112

Enterprise APIs Government Accountability 112

AWS Machine Learning

AUGUST 26, 2024

The GenASL web app invokes the backend services by sending the S3 object key in the payload to an API hosted on Amazon API Gateway. API Gateway instantiates an AWS Step Functions The state machine orchestrates the AI/ML services Amazon Transcribe and Amazon Bedrock and the NoSQL data store Amazon DynamoDB using AWS Lambda functions.

APIs 119

APIs Calibration Best practices Metrics 119

AWS Machine Learning

OCTOBER 30, 2023

It allows developers to build and scale generative AI applications using FMs through an API, without managing infrastructure. You can choose from various FMs from Amazon and leading AI startups such as AI21 Labs, Anthropic, Cohere, and Stability AI to find the model that’s best suited for your use case.

APIs 141

APIs Big data Accountability Enterprise 141

AWS Machine Learning

OCTOBER 2, 2024

In this post, we discuss how to address these challenges holistically. Because this is an emerging area, best practices, practical guidance, and design patterns are difficult to find in an easily consumable basis. To learn more, see Log Amazon Bedrock API calls using AWS CloudTrail.

Government 127

Government APIs Enterprise Best practices 127

TechSee

APRIL 22, 2024

In this post, we explore how to remove barriers to adoption, significantly amplifying the effectiveness of your CX strategies. Furthermore, TechSee’s technology can be integrated anywhere through APIs or SDKs. However, the true potential of investing in CX innovation often remains untapped due to barriers that hinder adoption.

APIs 109

APIs Scripts Best practices Technology 109

TechSee

APRIL 22, 2024

In this post, we explore how to remove barriers to adoption, significantly amplifying the effectiveness of your CX strategies. Furthermore, TechSee’s technology can be integrated anywhere through APIs or SDKs. However, the true potential of investing in CX innovation often remains untapped due to barriers that hinder adoption.

APIs 109

APIs Scripts Best practices Technology 109

aircall

MARCH 17, 2021

When you use best practices in sales planning, everyone involved benefits — marketing teams, sales managers, sales teams, and your customers. Best practices for sales planning begins with an overall comprehensive plan that serves as your roadmap for sales call planning. How to Identify Gaps in Your Sales Strategy Plan.

Best practices 62

Best practices Sales Contact center software Contact Center 62

AWS Machine Learning

NOVEMBER 15, 2024

In this post, we introduce the core dimensions of responsible AI and explore considerations and strategies on how to address these dimensions for Amazon Bedrock applications. This tool not only supports responsible AI practices, but also fosters trust and reliability in the use of AI-generated content.

APIs 110

APIs Government Best practices Metrics 110

AWS Machine Learning

NOVEMBER 2, 2023

Amazon Bedrock is a fully managed service that makes foundation models from leading AI startups and Amazon available via easy-to-use API interfaces. The solution also uses the grammatical error correction API and the paraphrase API from AI21 to recommend word and sentence corrections.

APIs 129

APIs Education Transportation Accountability 129

AWS Machine Learning

MAY 17, 2024

In this blog post, you will learn about prompt chaining, how to break a complex task into multiple tasks to use prompt chaining with an LLM in a specific order, and how to involve a human to review the response generated by the LLM. Repeat the toxicity detection through the Comprehend API for the LLM generated response.

APIs 135

APIs Construction Engineering Enterprise 135

Cincom

MAY 8, 2024

The key stages include: Initial Research: Early messaging should focus on educating prospects with thought leadership content detailing industry trends and best practices. Adoption: Share tips, how-to content, and community forums to aid customers in skill-building and integration post-purchase. This builds awareness and trust.

Best practices 52

Best practices Metrics Education CRM 52

AWS Machine Learning

MARCH 15, 2023

The best practice for migration is to refactor these legacy codes using the Amazon SageMaker API or the SageMaker Python SDK. Step Functions is a serverless workflow service that can control SageMaker APIs directly through the use of the Amazon States Language.

Scripts 144

Scripts APIs Engineering Construction 144

AWS Machine Learning

NOVEMBER 17, 2023

ReAct Prompting FMs determine how to solve user-requested tasks with a technique called ReAct. The thought is a reasoning step that helps demonstrate to the FM how to tackle the problem and identify an action to take. The action is an API that the model can invoke from an allowed set of APIs.

APIs 115

APIs Customer Service Construction Analytics 115

AWS Machine Learning

MAY 7, 2024

In this post, we demonstrate how to use enhanced video search capabilities by enabling semantic retrieval of videos based on text queries. Amazon Transcribe The transcription for the entire video is generated using the StartTranscriptionJob API. The metadata generated for each video by the APIs is processed and stored with timestamps.

APIs 135

APIs Advertising Entertainment Metrics 135

AWS Machine Learning

MARCH 26, 2024

In this post, we show how to automate the accounts payable process using Amazon Textract for data extraction. AnalyzeExpense is an API dedicated to processing invoice and receipts documents. It is available both as a synchronous or asynchronous API. Map State – A Lambda function that processes each chunk in parallel.

APIs 121

APIs Construction Analytics Enterprise 121

AWS Machine Learning

MAY 1, 2024

Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon through a single API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI.

Chatbots 129

Chatbots APIs Engineering Automotive 129

AWS Machine Learning

JULY 17, 2024

This post shows how to use AWS generative artificial intelligence (AI) services , like Amazon Q Business , with AWS Support cases, AWS Trusted Advisor , and AWS Health data to derive actionable insights based on common patterns, issues, and resolutions while using the AWS recommendations and best practices enabled by support data.

Scripts 124

Scripts APIs Enterprise Accountability 124

AWS Machine Learning

JANUARY 22, 2025

Amazon Bedrock Flows offers an intuitive visual builder and a set of APIs to seamlessly link foundation models (FMs), Amazon Bedrock features, and AWS services to build and automate user-defined generative AI workflows at scale. Test the flow Youre now ready to test the flow through the Amazon Bedrock console or API.

APIs 129

APIs Transportation Best practices Enterprise 129

AWS Machine Learning

JULY 30, 2024

Additionally, Q Business conversation APIs employ a layer of privacy protection by leveraging trusted identity propagation enabled by IAM Identity Center. Amazon Q Business comes with rich API support to perform administrative tasks or to build an AI-assistant with customized user experience for your enterprise.

APIs 131

APIs Enterprise Accountability Management 131

AWS Machine Learning

OCTOBER 19, 2023

In this post, we discuss how to use the Custom Moderation feature in Amazon Rekognition to enhance the accuracy of your pre-trained content moderation API. The unique ID of the trained adapter can be provided to the existing DetectModerationLabels API operation to process images using this adapter.

APIs 131

APIs Best practices Advertising Accountability 131

AWS Machine Learning

SEPTEMBER 12, 2024

Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon through a unified API, along with a broad set of capabilities to build generative AI applications with security, privacy, and responsible AI.

Healthcare 126

Healthcare APIs Accountability Enterprise 126

AWS Machine Learning

JANUARY 28, 2025

In this post, we show how to use FMEval and Amazon SageMaker to programmatically evaluate LLMs. It functions as a standalone HTTP server that provides various REST API endpoints for monitoring, recording, and visualizing experiment runs. The sample notebooks implement both approaches to help you decide which one fits best your needs.

Management 113

Management APIs Engineering Metrics 113

AWS Machine Learning

FEBRUARY 8, 2024

At the forefront of this evolution sits Amazon Bedrock , a fully managed service that makes high-performing foundation models (FMs) from Amazon and other leading AI companies available through an API. System integration – Agents make API calls to integrated company systems to run specific actions.

APIs 139

APIs Scripts Enterprise Management 139

AWS Machine Learning

FEBRUARY 9, 2023

In this post, we discuss the benefits of the AnalyzeDocument Signatures feature and how the AnalyzeDocument Signatures API helps detect signatures in documents. Lastly, we share some best practices for using this feature. When Amazon Textract processes documents, the results are returned in an array of Block objects.

APIs 103

APIs Best practices Banking Enterprise 103

AWS Machine Learning

JANUARY 10, 2024

The solution uses AWS Lambda , Amazon API Gateway , Amazon EventBridge , and SageMaker to automate the workflow with human approval intervention in the middle. The approver approves the model by following the link in the email to an API Gateway endpoint. API Gateway invokes a Lambda function to initiate model updates.

APIs 127

APIs Construction Engineering Analytics 127

aircall

MAY 24, 2021

Setting up the right digital transformation framework makes a huge difference in how well your call center runs. By following best practices for your digital transformation framework, you also get the benefit of flexibility so you can add and subtract digital tools as your company’s needs change. Improves training and retention.

Best practices 62

Best practices Call Center Technology Analytics 62