Authors

Description

Large language models (LLMs) have demonstrated an impressive ability to store and deploy vast knowledge in response to user queries. While this has enabled the creation of powerful artificial intelligence systems such as ChatGPT, compressing global knowledge in this way has two key limitations. First, an LLM's knowledge is static, i.e., it is not updated as new information becomes available. Second, LLMs may have insufficient “understanding” of specialized and niche information that was not highlighted in their training data. These limitations can result in unintended (and even fictitious) model responses to user queries. Using the technique augmented retrieval generation or RAG, is a way to mitigate these limitations by augmenting a model through a specialized and mutable knowledge base, giving previously trained LLMs access to very specific information as additional context when answering our queries, especially with our data (Databases or PDF files), this allows for the creation of more robust and adaptive AI systems. In this talk, I will discuss the theory and practice of implementing on an LLM with additional RAG capabilities using the Hugging Face, LangChain and vector database transformer libraries.