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. For our example, we chose Amazons Nova Lite model and set the temperature inference parameter to 0.1

APIs 127

APIs Transportation Best practices Enterprise 127

AWS Machine Learning

DECEMBER 18, 2024

Prerequisites Before proceeding, make sure that you have the necessary AWS account permissions and services enabled, along with access to a ServiceNow environment with the required privileges for configuration. AWS Have an AWS account with administrative access. For more information, see Setting up for Amazon Q Business. Choose Next.

APIs 86

APIs Enterprise Accountability Government 86

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 126

APIs Banking Best practices Engineering 126

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 131

APIs Enterprise Best practices Accountability 131

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 104

Management APIs Engineering Metrics 104

AWS Machine Learning

MARCH 25, 2025

Then we deep dive into the new rolling update feature for inference components and provide practical examples using DeepSeek distilled models to demonstrate this feature. Consider an example where a customer has 10 copies of an inference component spread across 5 ml.p4d.24xlarge You can find the example notebook in the GitHub repo.

APIs 85

APIs Engineering Accountability Metrics 85

AWS Machine Learning

OCTOBER 29, 2024

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

Best practices 110

Best practices Feedback Metrics APIs 110

AWS Machine Learning

MARCH 11, 2025

The following table provides example questions with their domain and question type. Amazon Bedrock APIs make it straightforward to use Amazon Titan Text Embeddings V2 for embedding data. The eight different question types are simple , simple_w_condition , comparison , aggregation , set , false_premise , post-processing , and multi-hop.

Benchmark 93

Benchmark APIs Enterprise Scripts 93

AWS Machine Learning

AUGUST 2, 2024

With GraphStorm, you can build solutions that directly take into account the structure of relationships or interactions between billions of entities, which are inherently embedded in most real-world data, including fraud detection scenarios, recommendations, community detection, and search/retrieval problems. Specifically, GraphStorm 0.3

APIs 115

APIs Benchmark Construction Enterprise 115

AWS Machine Learning

MARCH 19, 2025

The organizations that figure this out first will have a significant competitive advantageand were already seeing compelling examples of whats possible. The question is no longer whether to adopt generative AI, but how to move from promising pilots to production-ready systems that deliver real business value.

Healthcare 125

Healthcare Enterprise APIs Transportation 125

AWS Machine Learning

DECEMBER 11, 2024

The following screenshot shows an example of an interaction with Field Advisor. Weve seen our sales teams use this capability to do things like consolidate meeting notes from multiple team members, analyze business reports, and develop account strategies.

Sales 101

Sales Accountability APIs CRM 101

AWS Machine Learning

OCTOBER 30, 2024

Enabling Global Resiliency for an Amazon Lex bot is straightforward using the AWS Management Console , AWS Command Line Interface (AWS CLI), or APIs. For this example, we create a bot named BookHotel in the source Region ( us-east-1 ). If this option isn’t visible, the Global Resiliency feature may not be enabled for your account.

Chatbots 106

Chatbots Interactive Voice Response APIs Telecommunications 106

AWS Machine Learning

NOVEMBER 21, 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, Mistral AI, 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.

APIs 110

APIs Call Center Engineering Personalization 110

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 108

APIs Scripts Best practices Management 108

AWS Machine Learning

FEBRUARY 21, 2025

Whether youre new to AI development or an experienced practitioner, this post provides step-by-step guidance and code examples to help you build more reliable AI applications. Lets walkthrough an example of how this solution would handle a users question. For example, if the question was What hotels are near re:Invent?

Engineering 119

Engineering APIs Analytics Enterprise 119

AWS Machine Learning

MARCH 18, 2025

Beyond Amazon Bedrock models, the service offers the flexible ApplyGuardrails API that enables you to assess text using your pre-configured guardrails without invoking FMs, allowing you to implement safety controls across generative AI applicationswhether running on Amazon Bedrock or on other systemsat both input and output levels.

Government 83

Government APIs Enterprise Technology 83

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 91

Education Engineering APIs Enterprise 91

AWS Machine Learning

SEPTEMBER 20, 2024

Amazon Bedrock agents use LLMs to break down tasks, interact dynamically with users, run actions through API calls, and augment knowledge using Amazon Bedrock Knowledge Bases. In this post, we demonstrate how to use Amazon Bedrock Agents with a web search API to integrate dynamic web content in your generative AI application.

APIs 105

APIs Chatbots Construction Engineering 105

AWS Machine Learning

FEBRUARY 21, 2025

This serves as an example of how generative AI can streamline operations that involve diverse data types and formats. The solution uses the FMs tool use capabilities, accessed through the Amazon Bedrock Converse API. In this post, we focus on one such complex workflow: document processing. Access to the Anthropics Claude 3.5

APIs 85

APIs Healthcare Consulting Consulting 85

AWS Machine Learning

FEBRUARY 13, 2024

For example, in an application that recommends a music playlist, features could include song ratings, listening duration, and listener demographics. SageMaker Feature Store now makes it effortless to share, discover, and access feature groups across AWS accounts. Features are inputs to ML models used during training and inference.

Accountability 127

Accountability Government Engineering Scripts 127

AWS Machine Learning

NOVEMBER 20, 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, Mistral AI, 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.

Construction 115

Construction APIs Metrics Accountability 115

AWS Machine Learning

JANUARY 24, 2025

The workflow steps are as follows: The user submits an Amazon Bedrock fine-tuning job within their AWS account, using IAM for resource access. The fine-tuning job initiates a training job in the model deployment accounts. For Security group name , enter a name (for example, bedrock-kms-interface-sg ). For VPC , choose your VPC.

Best practices 112

Best practices Accountability industry standards Metrics 112

AWS Machine Learning

DECEMBER 9, 2024

For example, you can give users access permission to download popular packages and customize the development environment. Prerequisites You need an AWS account with an AWS Identity and Access Management (IAM) role with permissions to manage resources created as part of the solution. For details, see Creating an AWS account.

Metrics 95

Metrics APIs Engineering Accountability 95

AWS Machine Learning

JANUARY 14, 2025

See the following figure for an example. The following example illustrates the hybrid RAG high-level architecture. The embedding model, which is hosted on the same EC2 instance as the local LLM API inference server, converts the text chunks into vector representations.

APIs 97

APIs Chatbots Enterprise Healthcare 97

AWS Machine Learning

FEBRUARY 11, 2025

The following diagram illustrates an example architecture for ingesting data through an endpoint interfacing with a large corpus. Step Functions orchestrates AWS services like AWS Lambda and organization APIs like DataStore to ingest, process, and store data securely. The fetched data is put into an S3 data store bucket for processing.

Enterprise 91

Enterprise Engineering APIs Best practices 91

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

JULY 2, 2024

Amazon Bedrock is a fully managed service that makes a wide range of foundation models (FMs) available though an API without having to manage any infrastructure. Amazon API Gateway and AWS Lambda to create an API with an authentication layer and integrate with Amazon Bedrock. Refer to the Amazon Bedrock FAQs for further details.

APIs 136

APIs Scripts Enterprise Engineering 136

AWS Machine Learning

NOVEMBER 22, 2024

Cloud providers have recognized the need to offer model inference through an API call, significantly streamlining the implementation of AI within applications. Although a single API call can address simple use cases, more complex ones may necessitate the use of multiple calls and integrations with other services.

APIs 89

APIs Technology Management Enterprise 89

AWS Machine Learning

FEBRUARY 11, 2025

We use various AWS services to deploy a complete solution that you can use to interact with an API providing real-time weather information. We also use identity pool to provide temporary AWS credentials for the user while they interact with Amazon Bedrock API. In this solution, we use Amazon Bedrock Agents.

APIs 80

APIs Enterprise Accountability Management 80

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. Add team members using their email addresses—they will receive instructions to set up their accounts. On the SageMaker console, choose Labeling workforces.

APIs 95

APIs Feedback Telecommunications Management 95

AWS Machine Learning

MARCH 3, 2025

Designed for both image and document comprehension, Pixtral demonstrates advanced capabilities in vision-related tasks, including chart and figure interpretation, document question answering, multimodal reasoning, and instruction followingseveral of which are illustrated with examples later in this post. Lets explore an example.

Benchmark 88

Benchmark APIs Enterprise Construction 88

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. We give more details on that aspect later in this post.

APIs 117

APIs Engineering Chatbots Construction 117

AWS Machine Learning

NOVEMBER 13, 2024

For example, searching for a specific red leather handbag with a gold chain using text alone can be cumbersome and imprecise, often yielding results that don’t directly match the user’s intent. Amazon Titan FMs provide customers with a breadth of high-performing image, multimodal, and text model choices, through a fully managed API.

Engineering 114

Engineering Management APIs Healthcare 114

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.

Metrics 93

Metrics Engineering APIs Benchmark 93

AWS Machine Learning

FEBRUARY 12, 2025

Amazon Bedrock is a fully managed service that makes FMs from leading AI startups and Amazon available through an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case. Solution overview The solution comprises two main steps: Generate synthetic data using the Amazon Bedrock InvokeModel API.

APIs 74

APIs Management Benchmark Scripts 74

AWS Machine Learning

FEBRUARY 28, 2025

The following are examples of questions you can ask Amazon Q Business to gain actionable insights: Project status updates Get quick insights into project health Whats the status of the website redesign project? In this example, were using Smartsheet to track tasks for a software development project. A Smartsheet access token.

APIs 66

APIs Enterprise Accountability Management 66

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. For detailed setup instructions, including account requirements, model access, and necessary permissions, refer to Creative content generation with Amazon Nova.

Engineering 98

Engineering Best practices Entertainment APIs 98