This week we will be talking about Retrieval Augmented Generation – also known as RAG. The basic premise is to use an existing LLM to generate content based on an existing collection of documents. This removes the need to fine-tune an LLM, which is cost prohibitive and hardware constrained. Over the next several sessions, we will […]

Continuing our discussion about Retrieval Augmented Generation (RAG), this week we will incorporate ChromaDB as the storage and query mechanism for the embeddings. Our initial SpaceApps submission held all of the embeddings in memory and used a cosine similarity metric for queries. We will go through the ChromaDB API and design decisions required to replace the […]

Continuing our discussion about Retrieval Augmented Generation (RAG), this week we will incorporate LLM Sherpa to provide chunks of text from PDF documents that have been retrieved from the NASA archive. Our initial attempt used PyPDF2 to read text from the PDF documents. It was very slow and provided limited strings of text that did not […]