Hi ,
When ChatGPT was first released, there was talk it would lead to traditional search engines, like Google, soon becoming obsolete. That was until users discovered generative AI’s one major drawback – it makes stuff up.
Because of the stochastic nature of ChatGPT, it is never going to be possible to completely eliminate hallucinations. However, there are ways to work around this issue. One such way is through leveraging knowledge graphs and retrieval augmented generation (or RAG).
In the latest episode of Value
Driven Data Science, I'm joined by Kirk Marple, CEO of Graphlit, to discuss how knowledge graphs and RAG can be leveraged to improve the quality of generative AI.
Highlights include:
- (00:19) Meet Kirk Marple
- (01:22) Leveraging knowledge graphs and RAG
- (06:08)
Challenges with named entity extraction
- (09:16) Cost implications of LLMs
- (12:17) Deep dive into RAG
- (16:58) Vector search explained
- (20:49) Graph databases and RAG
- (38:58) Future of RAG and AI
- (43:08) Final thoughts
You can listen to this episode by clicking the button below, or find it on Apple Podcasts, Amazon Music, Spotify or Google Podcasts.
