Skip to main content

GEN_AI__USAGE__CACHE_CREATION__INPUT_TOKENS

relay_conventions::attributes

Constant GEN_AI__USAGE__CACHE_CREATION__INPUT_TOKENS 

Source 
pub const GEN_AI__USAGE__CACHE_CREATION__INPUT_TOKENS: &str = "gen_ai.usage.cache_creation.input_tokens";
Expand description

The number of tokens written to the cache when processing the AI input (prompt).

  • Scrubbing: Manual
  • Rewriting behavior: None

ยงAliases