Dexa/Super Data Science: ML & AI Podcast with Jon Krohn

AI Assistant Challenges

Blending external knowledge with AI assistants presents unique challenges. The importance of a clean and well-structured knowledge base cannot be overstated, as discrepancies can lead to misleading answers. Companies must implement processes for data cleanup and conversation analysis to enhance both the AI assistant's performance and the quality of the knowledge base over time.

In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
743: How to Integrate Generative AI Into Your Business — with Piotr Grudzień
Related Questions
- I'm thinking that classical or deep ML solutions have a flaw in that they cannot be extended. For example, if one builds a model and wants to introduce a new feature, typically the model has to be retrained from scratch. So, I'm considering building a Knowledge Graph using LLMs. This knowledge graph would have to include time-dependent data (for example, it should be able to retrieve the "current" President of the USA and also previous presidents if asked). I'm thinking this Knowledge Graph could be used for Retrieval Augmented Generation (RAG) to help with business goals or maybe used with more clever User Interfaces (UIs). I'm not sure how to build or populate this KG and also have a rough idea of how to use it. Can you help me with suggesting particular paths for building and populating this Knowledge Graph?