Databricks’ Adam Gurary on retrieval, metadata, and why most AI work happens before the model
Very helpful breakdown and mapping of value and blockages on the DE side
Thank you! And yes, definitely agree that better results often just come from filtering on recency + product fields vs using fancier embedding models
Very helpful breakdown and mapping of value and blockages on the DE side
Thank you! And yes, definitely agree that better results often just come from filtering on recency + product fields vs using fancier embedding models