text-chunking

A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.

A package for parsing PDFs and analyzing their content using LLMs.

🍱 Semantically create chunks from large document for passing to LLM workflows

Embedding-driven, context-aware text chunking for Semantic Kernel and RAG workflows in .NET

🧠✂️ SemanticSlicer — A smart text chunker for LLM-ready documents.

⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex.

An offline desktop app that turns PDFs, Word files and other documents into high-quality Anki flashcards with a local LLM, with smart deck matching, AI editing and direct Anki sync. Free personal use under AL-1.1; commercial use under ACL-1.0.

This project is designed to extract text from documents and prepare it for processing by Large Language Models (LLM). Implemented a feature to store and utilize text style information, enabling the program to identify and segment content based on potential headers and titles.

Cutting-edge tool designed to intelligently segment text documents into optimally-sized chunks

A lightweight TypeScript text splitter for RAG applications

An exploration of text splitting and chunking in JavaScript

⚡ The fastest semantic text chunking library a SIMD-accelerated Rust core with a sync + async Python API.

A service-oriented .NET library for AI with interchangeable orchestrations and vector stores.

Fast, deterministic, parallel text chunking for RAG pipelines. Rust core, Python bindings.

A RAG (Retrieval-Augmented Generation) pipeline implementation using .NET 10, Gemini AI, and Qdrant Vector Database.

Sementic chunking algorithm in (mostly) Go

Preprocess document service for RAG (Retriveal Augumented Generation)

Text Chunking Strategies for RAG — a practical Python demo showcasing fixed-size, sentence-based, and recursive chunking techniques for LLM embeddings, vector databases, and Retrieval-Augmented Generation (RAG) pipelines.

A RAG system that stops GPT from confidently making things up.

A Streamlit-based semantic search engine that converts documents into embeddings and retrieves the most meaningful text chunks using cosine similarity and dynamic chunking.