Evolving Graph Technologies
The emergence of GQL as an ISO standard marks a significant evolution in query languages, with enhancements in tools like Gremlin that now support advanced string and date manipulations. As the landscape shifts, the concept of graph RAG is gaining traction, blending graphs with generative AI to create more comprehensive and explainable outputs. Despite these advancements, the core challenges in the field remain, albeit with new perspectives.In this clip
From this podcast
Data Skeptic
Customizing a Graph Solution
Related Questions
Can you help me with suggesting particular paths for building and populating a Knowledge Graph using LLMs that includes time-dependent data, such as retrieving the "current" President of the USA and previous presidents? I'm considering using this Knowledge Graph for Retrieval Augmented Generation (RAG) to help with business goals or clever User Interfaces (UIs).
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?