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 […]

We have Josh Phillips presenting this week, so you don’t want to miss this! Join us as we explore the crucial task of selecting optimal embedding models to enhance AI performance across a variety of applications. This meetup will delve into the Multilingual Transferable Embedding Benchmark (MTEB), a pivotal resource providing a comprehensive framework to […]

SBIR/STTR Topics The second round of SBIR Topics for DoD were released last week. As usual, we will go through any that are labeled as Machine Learning or Artificial Intelligence – which looks like 13 SBIR and 9 STTR out of 176 total topics. You can find the full list below in the Links, just search […]

This week we will take another look at llama-ccp, this time using the python wrapper available in llama-cpp-python. This library can be installed and imported directly, or run as a separate service available through the OpenAI API. We covered the basics of llama-cpp last year and looked through the different quantization approaches available. It provides […]

We are going to take a break from the formal sessions this week to get together at Stovehouse and hang out for a bit. This is a great opportunity to relax and meet others involved in Huntsville AI. We have a wide variety of backgrounds, so I always learn something interesting. This officially starts at […]

This week we have Andrew Tuggle from Womble Bond Dickinson (US) LLP joining us to talk about Law and AI. He has been involved in our meetups for years and always has an interesting perspective from an attorney’s point of view. As AI becomes more advanced and ubiquitous, it is raising new legal issues across many domains. In this session, […]

We’re going to add in a new topic to the NASA RAG series this week, so check below for some rearranging of the schedule. As always, if there is something that you would like to talk about (or have someone cover) – please let me know! After a few rounds of iteration using ChromaDB for […]

If you have ever tried to prompt an LLM to give you what you want, you have probably run into some frustrating challenges. This frustration can range from trying to write what you want in pseudo-code to arguing with a child about putting their toys away. This week we will focus on some guidelines for […]

We have been covering a series this year based on how a RAG works, and how to build one. Now it’s time to look at what it will cost to deploy it! BLUF: If you have constraints that require you to host your own LLM instead of using services such as OpenAI, Anthropic, or Google […]