Local Caching for LLM Columns #360
Description
Priority Level
Medium (Nice to have)
Is your feature request related to a problem? Please describe.
Training models and evaluating whether synthetic data improves performance requires generating significant amounts of data. This experimentation phase is expensive and time-consuming because it often involves rerunning the same prompts across multiple pipeline iterations. If novel outputs are not required for identical inputs, we can save time and money by implementing a caching system.
Describe the solution you'd like
I would like a simple cache option on LLM columns (Text, Structured, Code, and Judge).
Describe alternatives you've considered
No response
Additional context
No response