Blog

Your blog category

Foundational data protection for enterprise LLM acceleration with Protopia AI

This post is written in collaboration with Balaji Chandrasekaran, Jennifer Cwagenberg and Andrew Sansom and Eiman Ebrahimi from Protopia AI. New and powerful large language models (LLMs) are changing businesses rapidly, improving efficiency and effectiveness for a variety of enterprise use cases. Speed is of the essence, and adoption of LLM technologies can make or […]

Foundational data protection for enterprise LLM acceleration with Protopia AI Read More »

Use custom metadata created by Amazon Comprehend to intelligently process insurance claims using Amazon Kendra

Structured data, defined as data following a fixed pattern such as information stored in columns within databases, and unstructured data, which lacks a specific form or pattern like text, images, or social media posts, both continue to grow as they are produced and consumed by various organizations. For instance, according to International Data Corporation (IDC),

Use custom metadata created by Amazon Comprehend to intelligently process insurance claims using Amazon Kendra Read More »

Enable faster training with Amazon SageMaker data parallel library

Large language model (LLM) training has become increasingly popular over the last year with the release of several publicly available models such as Llama2, Falcon, and StarCoder. Customers are now training LLMs of unprecedented size ranging from 1 billion to over 175 billion parameters. Training these LLMs requires significant compute resources and time as hundreds

Enable faster training with Amazon SageMaker data parallel library Read More »

Tesla recalls more than 2 million cars over Autopilot safety

Following a two-year investigation by the National Highway Traffic Safety Administration (NHTSA), Tesla will recall over two million vehicles to address Autopilot safety concerns. Fixes will be issued through free over-the-air (OTA) updates, adding features that ensure drivers pay attention while using Tesla’s Autopilot driver assistance system. It affects all current Tesla EVs built since

Tesla recalls more than 2 million cars over Autopilot safety Read More »

How Q4 Inc. used Amazon Bedrock, RAG, and SQLDatabaseChain to address numerical and structured dataset challenges building their Q&A chatbot

This post is co-written with Stanislav Yeshchenko from Q4 Inc. Enterprises turn to Retrieval Augmented Generation (RAG) as a mainstream approach to building Q&A chatbots. We continue to see emerging challenges stemming from the nature of the assortment of datasets available. These datasets are often a mix of numerical and text data, at times structured,

How Q4 Inc. used Amazon Bedrock, RAG, and SQLDatabaseChain to address numerical and structured dataset challenges building their Q&A chatbot Read More »

Boosting RAG-based intelligent document assistants using entity extraction, SQL querying, and agents with Amazon Bedrock

Conversational AI has come a long way in recent years thanks to the rapid developments in generative AI, especially the performance improvements of large language models (LLMs) introduced by training techniques such as instruction fine-tuning and reinforcement learning from human feedback. When prompted correctly, these models can carry coherent conversations without any task-specific training data.

Boosting RAG-based intelligent document assistants using entity extraction, SQL querying, and agents with Amazon Bedrock Read More »

Scroll to Top