Summary In this post, we’ll build a Retrieval Augmented Generation (RAG) tool to process the PDF files downloaded from arXiv in the previous post DeepResearch Part 1. This RAG tool will be capable of loading, processing, and semantically searching the document content. It’s a versatile tool applicable to various text sources, including web pages.
Building the RAG Tool Following up on our arXiv downloader, we now need a tool to process the downloaded PDFs.
Summary Retrieval-Augmented Generation (RAG) is a powerful technique that enhances large language models (LLMs) by allowing them to use external knowledge sources.
An Artificial Intelligence (AI) system consists of components working together to apply knowledge learned from data. Some common components of those systems are:
Large Language Model (LLM): Typically the core component of the system, often there is more than one. These are large models that have been trained on massive amounts of data and can make intelligent predictions based on their training.
Summary CAG performs better but does not solve the key reason RAG was created small context windows.
Retrieval-Augmented Generation (RAG) is currently(early 2025) the most popular way to use external knowledge in current LLM opperations. RAG allows you to enhance your LLM with data beyond the data it was trained on. Ther are many great RAG solutions and products.
RAG has some drawbacks - There can be significant retreival latency as it searches for and organizes the correct data.