Skip to main content

compress_messages_with_full_ai

matrixcode_core::compress

Function compress_messages_with_full_ai 

Source 
pub async fn compress_messages_with_full_ai(
    messages: &[Message],
    config: &CompressionConfig,
    ai_mode: AiCompressionMode,
    fast_model: Box<dyn Provider>,
    main_model: Box<dyn Provider>,
    token_usage: u32,
    context_window: u32,
) -> Result<Vec<Message>>
Expand description

Compress messages with full AI support (async version).

Uses both fast_model and main_model for different compression tasks.