ai_tokenopt 0.5.8

Adaptive token optimization engine for LLM inference pipelines — compresses prompts, conversation history, tool schemas, and output streams to minimize token usage while preserving response quality.
Documentation
1
2
3
4
5
6
7
8
//! Conversation history compaction and summarization

pub mod compactor;
pub mod dedup;
pub mod paraphraser;
pub mod relevance;
pub mod summarizer;
pub mod summary_compactor;