embedcache 0.1.1

High-performance text embedding service with caching capabilities
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12

//! LLM-based chunking implementations
//!
//! This module provides intelligent chunking strategies that use Large Language Models
//! to identify semantic boundaries in text.

mod client;
mod concept;
mod introspection;

pub use client::{create_llm_client, LLMClient, LLMConfig, LLMProvider};
pub use concept::LLMConceptChunker;
pub use introspection::LLMIntrospectionChunker;