AWS Machine Learning Blog

In this post, we demonstrate model customization (fine-tuning) for tool use with HAQM Nova. We first introduce a tool usage use case, and gave details about the dataset. We walk through the details of HAQM Nova specific data formatting and showed how to do tool calling through the Converse and Invoke APIs in HAQM Bedrock. After getting the baseline results from HAQM Nova models, we explain in detail the fine-tuning process, hosting fine-tuned models with provisioned throughput, and using the fine-tuned HAQM Nova models for inference.

In this post, we introduced the Open Source Bedrock Agent Evaluation framework, a Langfuse-integrated solution that streamlines the agent development process. We demonstrated how this evaluation framework can be integrated with pharmaceutical research agents. We used it to evaluate agent performance against biomarker questions and sent traces to Langfuse to view evaluation metrics across question types.

In this post, the AWS and Cisco teams unveil a new methodical approach that addresses the challenges of enterprise-grade SQL generation. The teams were able to reduce the complexity of the NL2SQL process while delivering higher accuracy and better overall performance.

The AFX team’s product migration to the Nova Lite model has delivered tangible enterprise value by enhancing sales workflows. By migrating to the HAQM Nova Lite model, the team has not only achieved significant cost savings and reduced latency, but has also empowered sellers with a leading intelligent and reliable solution.

In this post, we walk you through how to build a hybrid search solution using OpenSearch Service powered by multimodal embeddings from the HAQM Titan Multimodal Embeddings G1 model through HAQM Bedrock. This solution demonstrates how you can enable users to submit both text and images as queries to retrieve relevant results from a sample retail image dataset.

In this post, we discuss how you can build an AI-powered document processing platform with open source NER and LLMs on SageMaker.

In this post, we explore two approaches for securing sensitive data in RAG applications using HAQM Bedrock. The first approach focused on identifying and redacting sensitive data before ingestion into an HAQM Bedrock knowledge base, and the second demonstrated a fine-grained RBAC pattern for managing access to sensitive information during retrieval. These solutions represent just two possible approaches among many for securing sensitive data in generative AI applications.

Today, we’re excited to announce the launch of HAQM SageMaker Large Model Inference (LMI) container v15, powered by vLLM 0.8.4 with support for the vLLM V1 engine. This release introduces significant performance improvements, expanded model compatibility with multimodality (that is, the ability to understand and analyze text-to-text, images-to-text, and text-to-images data), and provides built-in integration with vLLM to help you seamlessly deploy and serve large language models (LLMs) with the highest performance at scale.

In the first post of this series, we introduced a comprehensive evaluation framework for HAQM Q Business, a fully managed Retrieval Augmented Generation (RAG) solution that uses your company’s proprietary data without the complexity of managing large language models (LLMs). The first post focused on selecting appropriate use cases, preparing data, and implementing metrics to […]

Today, we’re happy to announce the general availability of HAQM Bedrock Intelligent Prompt Routing. In this blog post, we detail various highlights from our internal testing, how you can get started, and point out some caveats and best practices. We encourage you to incorporate HAQM Bedrock Intelligent Prompt Routing into your new and existing generative AI applications.