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

Favorite 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

Read More
Shared by AWS Machine Learning December 7, 2023

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

Favorite 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

Read More
Shared by AWS Machine Learning December 7, 2023

Mitigate hallucinations through Retrieval Augmented Generation using Pinecone vector database & Llama-2 from Amazon SageMaker JumpStart

Favorite Despite the seemingly unstoppable adoption of LLMs across industries, they are one component of a broader technology ecosystem that is powering the new AI wave. Many conversational AI use cases require LLMs like Llama 2, Flan T5, and Bloom to respond to user queries. These models rely on parametric

Read More
Shared by AWS Machine Learning December 7, 2023