Intelligent Document Processing + Retrieval-Augmented Generation

Hi Everyone,

We are back! In an effort to make the User Group sessions easy for presenters and attendees to fit into their schedules, we are moving to a quarterly meeting cadence. We are also going to experiment with meeting over lunch instead of in the evening.

For this next session, we will discuss extracting information from documents and then an increasingly common pattern for using this information — as context for Generative AI models.

Intelligent Document Processing (IDP) using AWS AI services — Godwin Sahayaraj Vincent, AWS

What is Intelligent Document Processing (IDP)? AI can automate document processing for forms such as pictures or hand-written tables, forms, and filings by combining Optical Character Recognition (OCR) and Natural Language Processing (NLP) to read and understand a document and extract specific terms or words.

Organizations across industries often have to deal with a lot of documents in their day-to-day business processes. These documents contain critical information that are key to making decisions on time in order to maintain the highest levels of customer satisfaction, faster customer onboarding, and lower customer churn. In most cases, documents are processed manually to extract information and insights, which is time-consuming, error-prone, expensive, and difficult to scale. There is limited automation available today to process and extract information from these documents.

We will discuss how you can implement Intelligent Document Processing with AWS AI services to helps automate information extraction from documents of different types and formats, quickly and with high accuracy. Faster information extraction with high accuracy helps in making quality business decisions on time, while reducing overall costs.

Retrieval-Augmented Generation (RAG) using LangChain -- Giuseppe Zappia, AWS

What is Retrieval Augmented Generation (RAG)? RAG is a key pattern for supplementing Generative AI text models with data outside of what it was trained on. With RAG, the external data is retrieved and then used to augment prompts by adding relevant retrieved data in context.In this technical overview, we will explore the concept of Retrieval Augmented Generation (RAG) and its role in improving the outputs for large language models (LLMs) by incorporating external data to user prompts to create a high-quality, contextually relevant output.

You'll learn about the components of RAG workflows and how to use the open source framework LangChain to reduce complexity while increasing development velocity for building GenAI applications. (edited)