AWS Machine Learning Blog
Building intelligent AI voice agents with Pipecat and HAQM Bedrock – Part 1
In this series of posts, you will learn how to build intelligent AI voice agents using Pipecat, an open-source framework for voice and multimodal conversational AI agents, with foundation models on HAQM Bedrock. It includes high-level reference architectures, best practices and code samples to guide your implementation.
Stream multi-channel audio to HAQM Transcribe using the Web Audio API
In this post, we explore the implementation details of a web application that uses the browser’s Web Audio API and HAQM Transcribe streaming to enable real-time dual-channel transcription. By using the combination of AudioContext, ChannelMergerNode, and AudioWorklet, we were able to seamlessly process and encode the audio data from two microphones before sending it to HAQM Transcribe for transcription.
How Kepler democratized AI access and enhanced client services with HAQM Q Business
At Kepler, a global full-service digital marketing agency serving Fortune 500 brands, we understand the delicate balance between creative marketing strategies and data-driven precision. In this post, we share how implementing HAQM Q Business transformed our operations by democratizing AI access across our organization while maintaining stringent security standards, resulting in an average savings of 2.7 hours per week per employee in manual work and improved client service delivery.
Build a serverless audio summarization solution with HAQM Bedrock and Whisper
In this post, we demonstrate how to use the Open AI Whisper foundation model (FM) Whisper Large V3 Turbo, available in HAQM Bedrock Marketplace, which offers access to over 140 models through a dedicated offering, to produce near real-time transcription. These transcriptions are then processed by HAQM Bedrock for summarization and redaction of sensitive information.
Implement semantic video search using open source large vision models on HAQM SageMaker and HAQM OpenSearch Serverless
In this post, we demonstrate how to use large vision models (LVMs) for semantic video search using natural language and image queries. We introduce some use case-specific methods, such as temporal frame smoothing and clustering, to enhance the video search performance. Furthermore, we demonstrate the end-to-end functionality of this approach by using both asynchronous and real-time hosting options on HAQM SageMaker AI to perform video, image, and text processing using publicly available LVMs on the Hugging Face Model Hub. Finally, we use HAQM OpenSearch Serverless with its vector engine for low-latency semantic video search.
Multi-account support for HAQM SageMaker HyperPod task governance
In this post, we discuss how an enterprise with multiple accounts can access a shared HAQM SageMaker HyperPod cluster for running their heterogenous workloads. We use SageMaker HyperPod task governance to enable this feature.
Build a Text-to-SQL solution for data consistency in generative AI using HAQM Nova
This post evaluates the key options for querying data using generative AI, discusses their strengths and limitations, and demonstrates why Text-to-SQL is the best choice for deterministic, schema-specific tasks. We show how to effectively use Text-to-SQL using HAQM Nova, a foundation model (FM) available in HAQM Bedrock, to derive precise and reliable answers from your data.
Modernize and migrate on-premises fraud detection machine learning workflows to HAQM SageMaker
Radial is the largest 3PL fulfillment provider, also offering integrated payment, fraud detection, and omnichannel solutions to mid-market and enterprise brands. In this post, we share how Radial optimized the cost and performance of their fraud detection machine learning (ML) applications by modernizing their ML workflow using HAQM SageMaker.
Contextual retrieval in Anthropic using HAQM Bedrock Knowledge Bases
Contextual retrieval enhances traditional RAG by adding chunk-specific explanatory context to each chunk before generating embeddings. This approach enriches the vector representation with relevant contextual information, enabling more accurate retrieval of semantically related content when responding to user queries. In this post, we demonstrate how to use contextual retrieval with Anthropic and HAQM Bedrock Knowledge Bases.
Run small language models cost-efficiently with AWS Graviton and HAQM SageMaker AI
In this post, we demonstrate how to deploy a small language model on SageMaker AI by extending our pre-built containers to be compatible with AWS Graviton instances. We first provide an overview of the solution, and then provide detailed implementation steps to help you get started. You can find the example notebook in the GitHub repo.