AI in the EnterpriseTALK
To RAG or Not to RAG?
Owen ChenVP, AI/ML Engineering at Fidelity Investments
- Day
- Tuesday, March 24
- Time
- 2:30 PM EDT – 3:00 PM EDT
- Room
- Junior Ballroom A
There is a debate on whether to use retrieval augmented generation (RAG) or provide a full context to LLM. In this talk, I will discuss the different approaches on building an enterprise AI solution that leverages an internal enterprise knowledge.