late-chunking 开源项目推荐（8 个）

superlinear-ai /raglite

SYS RAGLite是一个用于使用DuckDB或PostgreSQL的检索增强生成（RAG）的Python工具包

TheSOV /KubernetesCrew

AI-powered automation system that transforms natural language requirements into production-ready Kubernetes manifests through three specialized CrewAI agents. System is able to execute manifest creation and editing, knowledge retrieval using RAG with late chunking, web search, and static and runtime validation of the configuration files.

ndgigliotti /afterthoughts

Sentence-aware embeddings using late chunking with transformers.

joeywhelan /late-chunking

This demo measures late chunking against standard embedding on two corpora — one where it hurts and one where it helps — producing concrete retrieval numbers that engineers can use to make an informed choice.

Lu1sDV /obsidian-weaviate-embeddings

An experiment with VectorDB and Semantic Search, in Obsidian

emerose /fancychunk

A small, focused library for splitting Markdown documents into semantically coherent chunks for retrieval-augmented generation.

RichardZhu02me /Lumen-Parser

Advanced High-Fidelity RAG pipeline featuring Agentic Hierarchy Parsing for structural correction and Context-Sensitive Late Chunking for preserving document context.

FMFigueroa /financebench-rag-eval

Rigorous evaluation of contextual retrieval techniques on FinanceBench: comparing 5 embedders × 4 chunking strategies with bootstrapped confidence intervals on FinMTEB and FinanceBench.