Category: Thought Leadership

This post demonstrates how enterprises can implement a scalable agentic text-to-SQL solution using Amazon Bedrock Agents, with advanced error-handling tools and automated schema discovery to enhance database query efficiency.

Discover how to build a GenAI powered virtual IT troubleshooting assistant using Amazon Q Business. This innovative solution integrates with popular ITSM tools like ServiceNow, Atlassian Jira, and Confluence to streamline information retrieval and enhance collaboration across your organization. By harnessing the power of generative AI, this assistant can significantly boost operational efficiency and provide 24/7 support tailored to individual needs. Learn how to set up, configure, and leverage this solution to transform your enterprise information management.

In this post, we show how SageMaker HyperPod, and its new features introduced at AWS re:Invent 2024, is designed to meet the demands of modern AI workloads, offering a persistent and optimized cluster tailored for distributed training and accelerated inference at cloud scale and attractive price-performance.

In this post, we discuss best practices for applying LLMs to generate ground truth for evaluating question-answering assistants with FMEval on an enterprise scale. FMEval is a comprehensive evaluation suite from Amazon SageMaker Clarify, and provides standardized implementations of metrics to assess quality and responsibility. To learn more about FMEval, see Evaluate large language models for quality and responsibility of LLMs.

In this post, we present the continuous self-instruct fine-tuning framework as a compound AI system implemented by the DSPy framework. The framework first generates a synthetic dataset from the domain knowledge base and documents for self-instruction, then drives model fine-tuning through SFT, and introduces the human-in-the-loop workflow to collect human and AI feedback to the model response, which is used to further improve the model performance by aligning human preference through reinforcement learning (RLHF/RLAIF).

In this post, we demonstrate how to deploy distilled versions of DeepSeek-R1 models using Amazon Bedrock Custom Model Import. We focus on importing the variants currently supported DeepSeek-R1-Distill-Llama-8B and DeepSeek-R1-Distill-Llama-70B, which offer an optimal balance between performance and resource efficiency.

Optimizing costs of generative AI applications on AWS is critical for realizing the full potential of this transformative technology. The post outlines key cost optimization pillars, including model selection and customization, token usage, inference pricing plans, and vector database considerations.

This post focuses on doing RAG on heterogeneous data formats. We first introduce routers, and how they can help managing diverse data sources. We then give tips on how to handle tabular data and will conclude with multimodal RAG, focusing specifically on solutions that handle both text and image data.

This post outlines a custom multilingual document extraction and content assessment framework using a combination of Anthropic’s Claude 3 on Amazon Bedrock and Amazon A2I to incorporate human-in-the-loop capabilities.

In this post, we cover the core concepts behind RAG architectures and discuss strategies for evaluating RAG performance, both quantitatively through metrics and qualitatively by analyzing individual outputs. We outline several practical tips for improving text retrieval, including using hybrid search techniques, enhancing context through data preprocessing, and rewriting queries for better relevance.