AWS Machine Learning

MARCH 14, 2025

Traditional automation approaches require custom API integrations for each application, creating significant development overhead. For example, your agent could take screenshots, create and edit text files, and run built-in Linux commands. The output is given back to the Amazon Bedrock agent for further processing.

APIs 134

APIs Engineering CRM Enterprise 134

AWS Machine Learning

JULY 31, 2024

The new ApplyGuardrail API enables you to assess any text using your preconfigured guardrails in Amazon Bedrock, without invoking the FMs. In this post, we demonstrate how to use the ApplyGuardrail API with long-context inputs and streaming outputs. For example, you can now use the API with models hosted on Amazon SageMaker.

APIs 130

APIs Banking Best practices Engineering 130

AWS Machine Learning

DECEMBER 18, 2024

Although were using admin privileges for the purpose of this post, its a security best practice to apply least privilege permissions and grant only the permissions required to perform a task. This involves creating an OAuth API endpoint in ServiceNow and using the web experience URL from Amazon Q Business as the callback URL.

APIs 97

APIs Enterprise Accountability Government 97

AWS Machine Learning

JANUARY 28, 2025

Using SageMaker with MLflow to track experiments The fully managed MLflow capability on SageMaker is built around three core components: MLflow tracking server This component can be quickly set up through the Amazon SageMaker Studio interface or using the API for more granular configurations.

Management 115

Management APIs Engineering Metrics 115

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 116

APIs Scripts Best practices Management 116

AWS Machine Learning

JANUARY 4, 2024

In this post, we provide an introduction to text to SQL (Text2SQL) and explore use cases, challenges, design patterns, and best practices. Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) via a single API, enabling to easily build and scale Gen AI applications.

Best practices 139

Best practices Enterprise Engineering APIs 139

AWS Machine Learning

MARCH 4, 2025

Solution overview The following code is an example metadata filter for Amazon Bedrock Knowledge Bases. We have provided example documents and metadata in the accompanying GitHub repo for you to upload. This example data contains user answers to an online questionnaire about travel preferences.

APIs 114

APIs Best practices Management Personalization 114

AWS Machine Learning

DECEMBER 2, 2024

We cover the key scenarios where scaling to zero is beneficial, provide best practices for optimizing scale-up time, and walk through the step-by-step process of implementing this functionality. We also discuss best practices for implementation and strategies to mitigate potential drawbacks.

APIs 108

APIs Best practices Metrics Engineering 108

AWS Machine Learning

MARCH 25, 2024

Amazon Transcribe can be used for transcription of customer care calls, multiparty conference calls, and voicemail messages, as well as subtitle generation for recorded and live videos, to name just a few examples. Applications must have valid credentials to sign API requests to AWS services.

Best practices 117

Best practices APIs Transportation Personalization 117

AWS Machine Learning

MARCH 19, 2025

This could be APIs, code functions, or schemas and structures required by your end application. In this post, we discuss tool use and the new tool choice feature, with example use cases. For example, if a user asks What is the weather in Seattle? For example, if a user asks What is the weather in Seattle?

APIs 103

APIs Engineering Chatbots Best practices 103

AWS Machine Learning

JANUARY 27, 2025

Solution overview To get started with Nova Canvas and Nova Reel, you can either use the Image/Video Playground on the Amazon Bedrock console or access the models through APIs. Example: A blue sports car parked in front of a grand villa. Example: Rendered in a cinematic style with vivid, high-contrast details.

Engineering 111

Engineering Best practices Entertainment APIs 111

AWS Machine Learning

NOVEMBER 14, 2024

Customers can use the SageMaker Studio UI or APIs to specify the SageMaker Model Registry model to be shared and grant access to specific AWS accounts or to everyone in the organization. It also helps achieve data, project, and team isolation while supporting software development lifecycle best practices.

Government 105

Government Management APIs Accountability 105

AWS Machine Learning

SEPTEMBER 13, 2024

Intricate workflows that require dynamic and complex API orchestration can often be complex to manage. In this post, we explore how chaining domain-specific agents using Amazon Bedrock Agents can transform a system of complex API interactions into streamlined, adaptive workflows, empowering your business to operate with agility and precision.

APIs 132

APIs Enterprise Best practices Accountability 132

AWS Machine Learning

APRIL 23, 2025

For example, the job identifies and redacts sensitive data entities like name, email, address, and other financial PII entities. For more information, see Redacting PII entities with asynchronous jobs (API). The query is then forwarded using a REST API call to an Amazon API Gateway endpoint along with the access tokens in the header.

APIs 96

APIs Healthcare Enterprise Accountability 96

AWS Machine Learning

MARCH 14, 2024

By the end, you will have solid guidelines and a helpful flow chart for determining the best method to develop your own FM-powered applications, grounded in real-life examples. The following screenshot shows an example of a zero-shot prompt with the Anthropic Claude 2.1 In these instructions, we didn’t provide any examples.

Best practices 135

Best practices Engineering Chatbots Enterprise 135

AWS Machine Learning

APRIL 24, 2025

For enterprise data, a major difficulty stems from the common case of database tables having embedded structures that require specific knowledge or highly nuanced processing (for example, an embedded XML formatted string). This work extends upon the post Generating value from enterprise data: Best practices for Text2SQL and generative AI.

Enterprise 109

Enterprise Construction Scripts APIs 109

AWS Machine Learning

AUGUST 2, 2024

adds new APIs to customize GraphStorm pipelines: you now only need 12 lines of code to implement a custom node classification training loop. To help you get started with the new API, we have published two Jupyter notebook examples: one for node classification, and one for a link prediction task. Specifically, GraphStorm 0.3

APIs 117

APIs Benchmark Construction Enterprise 117

AWS Machine Learning

FEBRUARY 12, 2025

Amazon Bedrock , a fully managed service offering high-performing foundation models from leading AI companies through a single API, has recently introduced two significant evaluation capabilities: LLM-as-a-judge under Amazon Bedrock Model Evaluation and RAG evaluation for Amazon Bedrock Knowledge Bases. keys()) & set(metrics2.keys())

Metrics 104

Metrics Engineering Benchmark APIs 104

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 106

Best practices APIs Transportation Scripts 106

AWS Machine Learning

SEPTEMBER 7, 2023

In this post, we provide some best practices to maximize the value of SageMaker Pipelines and make the development experience seamless. We also discuss some common design scenarios and patterns when building SageMaker Pipelines and provide examples for addressing them. 1", instance_type="ml.m5.xlarge", 1", instance_type="ml.m5.xlarge",

Best practices 125

Best practices Scripts Construction APIs 125

AWS Machine Learning

AUGUST 19, 2022

Because many data scientists may lack experience in the acceleration training process, in this post we show you the factors that matter for fast deep learning model training and the best practices of acceleration training for TensorFlow 1.x We discuss best practices in the following areas: Accelerate training on a single instance.

Best practices 102

Best practices APIs Scripts Advertising 102

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 98

Best practices APIs Metrics Accountability 98

AWS Machine Learning

APRIL 10, 2025

In this post, we seek to address this growing need by offering clear, actionable guidelines and best practices on when to use each approach, helping you make informed decisions that align with your unique requirements and objectives. The following diagram illustrates the solution architecture. Be as objective as possible.

APIs 124

APIs Metrics Best practices Construction 124

AWS Machine Learning

FEBRUARY 11, 2025

First we discuss end-to-end large-scale data integration with Amazon Q Business, covering data preprocessing, security guardrail implementation, and Amazon Q Business best practices. The following diagram illustrates an example architecture for ingesting data through an endpoint interfacing with a large corpus.

Enterprise 103

Enterprise Engineering APIs Best practices 103

AWS Machine Learning

MARCH 27, 2025

We also showcase a real-world example for predicting the root cause category for support cases. For the use case of labeling the support root cause categories, its often harder to source examples for categories such as Software Defect, Feature Request, and Documentation Improvement for labeling than it is for Customer Education.

Education 111

Education Engineering APIs Enterprise 111

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. Structured outputs – For example, when you have 10,000 labeled examples specific to your use case and need Anthropic’s Claude 3 Haiku to accurately identify them. Sonnet across various tasks.

Best practices 97

Best practices APIs Finance Metrics 97

AWS Machine Learning

NOVEMBER 19, 2024

Hear from customer speakers with real-world examples of how they’ve used data to support a variety of use cases, including generative AI, to create unique customer experiences. In this session, learn best practices for effectively adopting generative AI in your organization.

APIs 107

APIs Enterprise Best practices Government 107

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. The entire set of code for the example is available in the following GitHub repository. Overview of solution. MemoryUtilization , on the other hand, is in the range of 0–100%.

Best practices 100

Best practices Scripts APIs Metrics 100

Help Scout

JULY 29, 2021

The 18 FAQ examples below will give you a great basis of ideas to work from to make your knowledge base content exceptional. 18 great examples of effective FAQ pages and content We’ve found companies across multiple industries with FAQ examples that we find inspiring and super helpful. Below are our 18 favorites.

Self service 142

Self service Education Telecommunications APIs 142

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. Additionally, you can add custom instructions and examples tailored to your specific workflows.

APIs 135

APIs Engineering Healthcare Education 135

AWS Machine Learning

FEBRUARY 5, 2025

Through this practical example, well illustrate how startups can harness the power of LLMs to enhance customer experiences and the simplicity of Nemo Guardrails to guide the LLMs driven conversation toward the desired outcomes. model API exposed by SageMaker JumpStart properly. The Llama 3.1

Chatbots 111

Chatbots Construction Best practices APIs 111

AWS Machine Learning

NOVEMBER 21, 2024

For example, in speech generation, an unnatural pause might last only a fraction of a second, but its impact on perceived quality is significant. This setup follows AWS best practices for least-privilege access, making sure CloudFront can only access the specific UI files needed for the annotation interface. val(option).text(option));

APIs 102

APIs Feedback Telecommunications Management 102

AWS Machine Learning

NOVEMBER 15, 2024

For example, a technician could query the system about a specific machine part, receiving both textual maintenance history and annotated images showing wear patterns or common failure points, enhancing their ability to diagnose and resolve issues efficiently. In practice, the router module can be implemented with an initial LLM call.

APIs 117

APIs Engineering Chatbots Construction 117

AWS Machine Learning

FEBRUARY 7, 2025

The implementation uses Slacks event subscription API to process incoming messages and Slacks Web API to send responses. The following screenshot shows an example. The incoming event from Slack is sent to an endpoint in API Gateway, and Slack expects a response in less than 3 seconds, otherwise the request fails.

Entertainment 85

Entertainment APIs Technology Feedback 85

AWS Machine Learning

APRIL 30, 2025

For anonymous Amazon Q Business applications, weve implemented a simple consumption-based pricing model where youre charged based on the number of Chat or ChatSync API operations your anonymous Amazon Q Business applications make. For Application name , enter a name (for example, SupportDocs-Assistant ). Choose Add an index.

54

54

AWS Machine Learning

FEBRUARY 9, 2024

For example, they may need to track the usage of FMs across teams, chargeback costs and provide visibility to the relevant cost center in the LOB. For example, if only specific FMs may be approved for use. We use API keys to restrict and monitor API access for teams. Each team is assigned an API key for access to the FMs.

SaaS 144

SaaS APIs Government Accountability 144

AWS Machine Learning

SEPTEMBER 18, 2024

Amazon Bedrock enables access to powerful generative AI models like Stable Diffusion through a user-friendly API. For example, it can fill in a line drawing with colors, lighting, and a background that makes sense for the subject. The user chooses Call API to invoke API Gateway to begin processing on the backend.

APIs 129

APIs Entertainment Best practices Advertising 129