APIs and Construction - Customer Contact Central

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

AWS Machine Learning

NOVEMBER 7, 2024

In this post, we guide you through integrating Amazon Bedrock Agents with enterprise data APIs to create more personalized and effective customer support experiences. An automotive retailer might use inventory management APIs to track stock levels and catalog APIs for vehicle compatibility and specifications.

APIs

APIs Enterprise Automotive Customer Support

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

AWS Machine Learning

OCTOBER 31, 2024

The custom Google Chat app, configured for HTTP integration, sends an HTTP request to an API Gateway endpoint. Before processing the request, a Lambda authorizer function associated with the API Gateway authenticates the incoming message. The following figure illustrates the high-level design of the solution.

APIs

APIs Scripts Accountability Construction

Streamline RAG applications with intelligent metadata filtering using Amazon Bedrock

AWS Machine Learning

NOVEMBER 20, 2024

In some use cases, particularly those involving complex user queries or a large number of metadata attributes, manually constructing metadata filters can become challenging and potentially error-prone. The extracted metadata is used to construct an appropriate metadata filter. it will extract “strategy” (genre) and “2023” (year).

Construction

Construction APIs Metrics Accountability

Centralize model governance with SageMaker Model Registry Resource Access Manager sharing

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. We will start by using the SageMaker Studio UI and then by using APIs.

Government

Government Management APIs Accountability

GraphStorm 0.3: Scalable, multi-task learning on graphs with user-friendly APIs

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. Based on customer feedback for the experimental APIs we released in GraphStorm 0.2, introduces refactored graph ML pipeline APIs. Specifically, GraphStorm 0.3 In addition, GraphStorm 0.3

APIs

APIs Benchmark Construction Enterprise

Track LLM model evaluation using Amazon SageMaker managed MLflow and FMEval

AWS Machine Learning

JANUARY 28, 2025

Thanks to this construct, you can evaluate any LLM by configuring the model runner according to your model. It functions as a standalone HTTP server that provides various REST API endpoints for monitoring, recording, and visualizing experiment runs. Model runner Composes input, and invokes and extracts output from your model.

Management

Management APIs Engineering Metrics

Speed up your time series forecasting by up to 50 percent with Amazon SageMaker Canvas UI and AutoML APIs

AWS Machine Learning

SEPTEMBER 28, 2023

In this post, we describe the enhancements to the forecasting capabilities of SageMaker Canvas and guide you on using its user interface (UI) and AutoML APIs for time-series forecasting. While the SageMaker Canvas UI offers a code-free visual interface, the APIs empower developers to interact with these features programmatically.

APIs

APIs Construction Finance Enterprise

Integrate dynamic web content in your generative AI application using a web search API and Amazon Bedrock Agents

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

APIs Chatbots Construction Engineering

Build end-to-end document processing pipelines with Amazon Textract IDP CDK Constructs

AWS Machine Learning

MARCH 31, 2023

In this post, we demonstrate how to solve these challenges using Amazon Textract IDP CDK Constructs , a set of pre-built IDP constructs, to accelerate the development of real-world document processing pipelines. However, you can extend these constructs for any form type. Queries is a list of queries.

Construction

Construction APIs Accountability Banking

Generate training data and cost-effectively train categorical models with Amazon Bedrock

AWS Machine Learning

MARCH 27, 2025

In the following sections, we provide a detailed explanation on how to construct your first prompt, and then gradually improve it to consistently achieve over 90% accuracy. Later, if they saw the employee making mistakes, they might try to simplify the problem and provide constructive feedback by giving examples of what not to do, and why.

Education

Education Engineering APIs Enterprise

Pixtral-12B-2409 is now available on Amazon Bedrock Marketplace

AWS Machine Learning

MARCH 3, 2025

You can find detailed usage instructions, including sample API calls and code snippets for integration. However, to invoke the deployed model programmatically with Amazon Bedrock APIs, you need to use the endpoint ARN as model-id in the Amazon Bedrock SDK. To begin using Pixtral 12B, choose Deploy.

Benchmark

Benchmark APIs Enterprise Construction

Model customization, RAG, or both: A case study with Amazon Nova

AWS Machine Learning

APRIL 10, 2025

Fine-tune an Amazon Nova model using the Amazon Bedrock API In this section, we provide detailed walkthroughs on fine-tuning and hosting customized Amazon Nova models using Amazon Bedrock. We first provided a detailed walkthrough on how to fine-tune, host, and conduct inference with customized Amazon Nova through the Amazon Bedrock API.

APIs

APIs Metrics Best practices Construction

Enterprise-grade natural language to SQL generation using LLMs: Balancing accuracy, latency, and scale

AWS Machine Learning

APRIL 24, 2025

The solution uses the data domain to construct prompt inputs for the generative LLM. This mapping is similar in nature to intent classification, and enables the construction of an LLM prompt that is scoped for each input query (described next). Scoping data domain for focused prompt construction This is a divide-and-conquer pattern.

Enterprise

Enterprise Construction Scripts APIs

Secure Amazon SageMaker Studio presigned URLs Part 3: Multi-account private API access to Studio

AWS Machine Learning

APRIL 11, 2023

In the post Secure Amazon SageMaker Studio presigned URLs Part 2: Private API with JWT authentication , we demonstrated how to build a private API to generate Amazon SageMaker Studio presigned URLs that are only accessible by an authenticated end-user within the corporate network from a single account.

APIs

APIs Accountability Scripts Enterprise

Enhancing LLM Capabilities with NeMo Guardrails on Amazon SageMaker JumpStart

AWS Machine Learning

FEBRUARY 5, 2025

Colang is purpose-built for simplicity and flexibility, featuring fewer constructs than typical programming languages, yet offering remarkable versatility. It leverages natural language constructs to describe dialogue interactions, making it intuitive for developers and simple to maintain. Integrating Llama 3.1 The Llama 3.1

Chatbots

Chatbots Construction Best practices APIs

Revolutionize trip planning with Amazon Bedrock and Amazon Location Service

AWS Machine Learning

NOVEMBER 14, 2024

The user’s request is sent to AWS API Gateway , which triggers a Lambda function to interact with Amazon Bedrock using Anthropic’s Claude Instant V1 FM to process the user’s request and generate a natural language response of the place location. It will then return the place name with the highest similarity score.

APIs

APIs Engineering Personalization Transportation

Transforming credit decisions using generative AI with Rich Data Co and AWS

AWS Machine Learning

FEBRUARY 10, 2025

They provide access to external data and APIs or enable specific actions and computation. To efficiently use the models context window, we construct a tool selector that retrieves only the relevant tools based on the information in the agent state. Tools Tools extend agent capabilities beyond the FM.

Chief Customer Officer

Chief Customer Officer Banking SaaS Engineering

Build an Amazon SageMaker Model Registry approval and promotion workflow with human intervention

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 EventBridge model registration event rule invokes a Lambda function that constructs an email with a link to approve or reject the registered model.

APIs

APIs Construction Engineering Analytics

Building Generative AI prompt chaining workflows with human in the loop

AWS Machine Learning

MAY 17, 2024

With prompt chaining, you construct a set of smaller subtasks as individual prompts. Detect if the review content has any harmful information using the Amazon Comprehend DetectToxicContent API. Repeat the toxicity detection through the Comprehend API for the LLM generated response. If the toxicity of the review is less than 0.4

APIs

APIs Construction Engineering Enterprise

Automate the process to change image backgrounds using Amazon Bedrock and AWS Step Functions

AWS Machine Learning

MARCH 7, 2024

The Streamlit web application calls an Amazon API Gateway REST API endpoint integrated with the Amazon Rekognition DetectLabels API , which detects labels for each image. Constructs a request payload for the Amazon Bedrock InvokeModel API. Invokes the Amazon Bedrock InvokeModel API action.

APIs

APIs Entertainment Construction Advertising

Supercharge your AI team with Amazon SageMaker Studio: A comprehensive view of Deutsche Bahn’s AI platform transformation

AWS Machine Learning

FEBRUARY 29, 2024

The endpoints like SageMaker API, SageMaker Studio, and SageMaker notebook facilitate secure and reliable communication between the platform account’s VPC and the SageMaker domain managed by AWS in the SageMaker service account. Notably, each SageMaker domain is provisioned through its individual SageMakerStudioStack.

APIs

APIs Transportation Construction Analytics

Create a document lake using large-scale text extraction from documents with Amazon Textract

AWS Machine Learning

JANUARY 8, 2024

The second approach is a turnkey deployment of various infrastructure components using AWS Cloud Development Kit (AWS CDK) constructs. The AWS CDK construct provides a resilient and flexible framework to process your documents and build an end-to-end IDP pipeline. Now on to our second solution for documents at scale.

Scripts

Scripts Construction APIs Healthcare

Build a receipt and invoice processing pipeline with Amazon Textract

AWS Machine Learning

MARCH 26, 2024

The next stage is the extraction phase, where you pass the collected invoices and receipts to the Amazon Textract AnalyzeExpense API to extract financially related relationships between text such as vendor name, invoice receipt date, order date, amount due, amount paid, and so on. It is available both as a synchronous or asynchronous API.

APIs

APIs Construction Analytics Enterprise

Achieve operational excellence with well-architected generative AI solutions using Amazon Bedrock

AWS Machine Learning

OCTOBER 2, 2024

It’s a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like Anthropic, Cohere, Meta, Mistral 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.

Government

Government APIs Enterprise Best practices

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 2

AWS Machine Learning

NOVEMBER 15, 2024

An alternative approach to routing is to use the native tool use capability (also known as function calling) available within the Bedrock Converse API. In this scenario, each category or data source would be defined as a ‘tool’ within the API, enabling the model to select and use these tools as needed.

APIs

APIs Engineering Chatbots Construction

Bring legacy machine learning code into Amazon SageMaker using AWS Step Functions

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. We do so using AWS SDK for Python (Boto3) CreateProcessingJob API calls.

Scripts

Scripts APIs Engineering Construction

Imperva optimizes SQL generation from natural language using Amazon Bedrock

AWS Machine Learning

JUNE 20, 2024

Constructing SQL queries from natural language isn’t a simple task. Figure 2: High level database access using an LLM flow The challenge An LLM can construct SQL queries based on natural language. Figure 2: High level database access using an LLM flow The challenge An LLM can construct SQL queries based on natural language.

Construction

Construction APIs Metrics Engineering

What Timeframe for an AI Chatbot Project?

Inbenta

APRIL 29, 2020

This short timeframe is made possible by: An API with a multitude of proven functionalities; A proprietary and patented NLP technology developed and perfected over the course of 15 years by our in-house Engineers and Linguists; A well-established development process. Lack of recommendations on poorly constructed decision trees.

Chatbots

Chatbots APIs Construction Best practices

Build a serverless exam generator application from your own lecture content using Amazon Bedrock

AWS Machine Learning

MAY 15, 2024

The Amazon Bedrock API returns the output Q&A JSON file to the Lambda function. The container image sends the REST API request to Amazon API Gateway (using the GET method). API Gateway communicates with the TakeExamFn Lambda function as a proxy. The JSON file is returned to API Gateway.

Education

Education APIs Engineering Banking

Accelerate IaC troubleshooting with Amazon Bedrock Agents

AWS Machine Learning

FEBRUARY 25, 2025

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.

APIs

APIs Accountability Engineering Construction

Use Kubernetes Operators for new inference capabilities in Amazon SageMaker that reduce LLM deployment costs by 50% on average

AWS Machine Learning

APRIL 19, 2024

ACK is a framework for building Kubernetes custom controllers, where each controller communicates with an AWS service API. These controllers allow Kubernetes users to provision AWS resources like buckets, databases, or message queues simply by using the Kubernetes API. The model is configured in a new construct, an inference component.

APIs

APIs Engineering Construction Enterprise

Unlock the potential of generative AI in industrial operations

AWS Machine Learning

MARCH 19, 2024

To enhance code generation accuracy, we propose dynamically constructing multi-shot prompts for NLQs. The dynamically constructed multi-shot prompt provides the most relevant context to the FM, and boosts the FM’s capability in advanced math calculation, time series data processing, and data acronym understanding.

Construction

Construction Scripts APIs Enterprise

CBRE and AWS perform natural language queries of structured data using Amazon Bedrock

AWS Machine Learning

MAY 30, 2024

AWS Prototyping successfully delivered a scalable prototype, which solved CBRE’s business problem with a high accuracy rate (over 95%) and supported reuse of embeddings for similar NLQs, and an API gateway for integration into CBRE’s dashboards. The following diagram illustrates the web interface and API management layer.

Real estate

Real estate APIs Metrics Construction

Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock

AWS Machine Learning

NOVEMBER 17, 2023

The action is an API that the model can invoke from an allowed set of APIs. Action groups are mapped to an AWS Lambda function and related API schema to perform API calls. Customers converse with the bot in natural language with multiple steps invoking external APIs to accomplish subtasks.

APIs

APIs Customer Service Construction Analytics

Automate chatbot for document and data retrieval using Agents and Knowledge Bases for Amazon Bedrock

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

Chatbots APIs Engineering Automotive

Build a secure enterprise application with Generative AI and RAG using Amazon SageMaker JumpStart

AWS Machine Learning

SEPTEMBER 6, 2023

These SageMaker endpoints are consumed in the Amplify React application through Amazon API Gateway and AWS Lambda functions. To protect the application and APIs from inadvertent access, Amazon Cognito is integrated into Amplify React, API Gateway, and Lambda functions.

Enterprise

Enterprise APIs Real estate Construction

Reinvent personalization with generative AI on Amazon Bedrock using task decomposition for agentic workflows

AWS Machine Learning

SEPTEMBER 18, 2024

Client profiles – We have three business clients in the construction, manufacturing, and mining industries, which are mid-to-enterprise companies. Pre-Construction Services - Feasibility Studies - Site Selection and Evaluation. Pre-Construction Services - Feasibility Studies - Site Selection and Evaluation.

Personalization

Personalization Construction Consulting Consulting

Improving inclusion and accessibility through automated document translation with an open source app using Amazon Translate

AWS Machine Learning

MAY 1, 2024

For interacting with AWS services, the AWS Amplify JS library for React simplifies the authentication, security, and API requests. The backend uses several serverless and event-driven AWS services, including AWS Step Functions for low-code workflows, AWS AppSync for a GraphQL API, and Amazon Translate. 1 – Translating a document.

APIs

APIs Construction Best practices Technology

Knowledge Bases for Amazon Bedrock now supports hybrid search

AWS Machine Learning

MARCH 1, 2024

Use hybrid search and semantic search options via SDK When you call the Retrieve API, Knowledge Bases for Amazon Bedrock selects the right search strategy for you to give you most relevant results. You have the option to override it to use either hybrid or semantic search in the API.

APIs

APIs Finance Chatbots Enterprise

How SailPoint uses Anthropic’s Claude on Amazon Bedrock to automatically generate TypeScript code for SaaS connectors

AWS Machine Learning

OCTOBER 16, 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.

SaaS

SaaS APIs Construction Accountability

Dynamic video content moderation and policy evaluation using AWS generative AI services

AWS Machine Learning

MAY 30, 2024

The frontend UI interacts with the extract microservice through a RESTful interface provided by Amazon API Gateway. The UI constructs evaluation prompts and sends them to Amazon Bedrock LLMs, retrieving evaluation results synchronously. Detect generic objects and labels using the Amazon Rekognition label detection API.

Advertising

Advertising APIs Education Analytics

Customize Amazon Textract with business-specific documents using Custom Queries

AWS Machine Learning

NOVEMBER 6, 2023

You can use the adapter for inference by passing the adapter identifier as an additional parameter to the Analyze Document Queries API request. Adapters can be created via the console or programmatically via the API. The API request is similar to the Amazon Textract Queries API request, with the addition of the AdaptersConfig object.

APIs

APIs Best practices Banking Accountability

Improve data extraction and document processing with Amazon Textract

AWS Machine Learning

NOVEMBER 2, 2022

This solution uses Amazon Textract IDP CDK constructs to build the document processing workflow that handles Amazon Textract asynchronous invocation, raw response extraction, and persistence in Amazon Simple Storage Service (Amazon S3). All the extracted data is returned with bounding box coordinates.

Construction

Construction APIs Government Enterprise

Amazon Textract’s new Layout feature introduces efficiencies in general purpose and generative AI document processing tasks

AWS Machine Learning

NOVEMBER 21, 2023

Prior to the introduction of this feature, customers had to construct these elements using post-processing code and the words and lines response from Amazon Textract. The LAYOUT feature of AnalyzeDocument API can now detect up to ten different layout elements in a document’s page.

APIs

APIs Construction Metrics Education

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

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

Trending Sources

Streamline RAG applications with intelligent metadata filtering using Amazon Bedrock

Centralize model governance with SageMaker Model Registry Resource Access Manager sharing

GraphStorm 0.3: Scalable, multi-task learning on graphs with user-friendly APIs

Track LLM model evaluation using Amazon SageMaker managed MLflow and FMEval

Speed up your time series forecasting by up to 50 percent with Amazon SageMaker Canvas UI and AutoML APIs

Integrate dynamic web content in your generative AI application using a web search API and Amazon Bedrock Agents

Build end-to-end document processing pipelines with Amazon Textract IDP CDK Constructs

Generate training data and cost-effectively train categorical models with Amazon Bedrock

Pixtral-12B-2409 is now available on Amazon Bedrock Marketplace

Model customization, RAG, or both: A case study with Amazon Nova

Enterprise-grade natural language to SQL generation using LLMs: Balancing accuracy, latency, and scale

Secure Amazon SageMaker Studio presigned URLs Part 3: Multi-account private API access to Studio

Enhancing LLM Capabilities with NeMo Guardrails on Amazon SageMaker JumpStart

Revolutionize trip planning with Amazon Bedrock and Amazon Location Service

Transforming credit decisions using generative AI with Rich Data Co and AWS

Build an Amazon SageMaker Model Registry approval and promotion workflow with human intervention

Building Generative AI prompt chaining workflows with human in the loop

Automate the process to change image backgrounds using Amazon Bedrock and AWS Step Functions

Supercharge your AI team with Amazon SageMaker Studio: A comprehensive view of Deutsche Bahn’s AI platform transformation

Create a document lake using large-scale text extraction from documents with Amazon Textract

Build a receipt and invoice processing pipeline with Amazon Textract

Achieve operational excellence with well-architected generative AI solutions using Amazon Bedrock

From RAG to fabric: Lessons learned from building real-world RAGs at GenAIIC – Part 2

Bring legacy machine learning code into Amazon SageMaker using AWS Step Functions

Imperva optimizes SQL generation from natural language using Amazon Bedrock

What Timeframe for an AI Chatbot Project?

Build a serverless exam generator application from your own lecture content using Amazon Bedrock

Accelerate IaC troubleshooting with Amazon Bedrock Agents

Use Kubernetes Operators for new inference capabilities in Amazon SageMaker that reduce LLM deployment costs by 50% on average

Unlock the potential of generative AI in industrial operations

CBRE and AWS perform natural language queries of structured data using Amazon Bedrock

Build a foundation model (FM) powered customer service bot with agents for Amazon Bedrock

Automate chatbot for document and data retrieval using Agents and Knowledge Bases for Amazon Bedrock

Build a secure enterprise application with Generative AI and RAG using Amazon SageMaker JumpStart

Reinvent personalization with generative AI on Amazon Bedrock using task decomposition for agentic workflows

Improving inclusion and accessibility through automated document translation with an open source app using Amazon Translate

Knowledge Bases for Amazon Bedrock now supports hybrid search

How SailPoint uses Anthropic’s Claude on Amazon Bedrock to automatically generate TypeScript code for SaaS connectors

Dynamic video content moderation and policy evaluation using AWS generative AI services

Customize Amazon Textract with business-specific documents using Custom Queries

Improve data extraction and document processing with Amazon Textract

Amazon Textract’s new Layout feature introduces efficiencies in general purpose and generative AI document processing tasks

Stay Connected