iyulab-rnd 

Core components for LMSupply libraries: HuggingFace model downloading, caching, GPU execution providers, and common utilities.

Text processing infrastructure for LMSupply - tokenization, vocabulary management, and encoding utilities

Complete document processing SDK optimized for RAG systems. Transform PDF, DOCX, Excel, PowerPoint, Markdown and other formats into high-quality chunks with intelligent semantic boundary detection. Includes... More information

A simple and intuitive library for accessing object values using string path expressions in .NET.

Code generation tool that supports M3L with SQL Server cascade path validation.

Core vision processing components for LMSupply: image loading, preprocessing, and tensor conversion utilities shared by LMSupply.Captioner and LMSupply.Ocr.

A simple .NET library for local text embeddings with automatic model downloading from HuggingFace. Supports CUDA, DirectML, and CoreML GPU acceleration.

A simple .NET library for local OCR with automatic model downloading from HuggingFace. Features 2-stage detection+recognition pipeline using PaddleOCR models. Supports CUDA, DirectML, and CoreML GPU... More information

A simple .NET library for local image captioning with automatic model downloading from HuggingFace. Supports CUDA, DirectML, and CoreML GPU acceleration.

FluxIndex Core - Domain models and application interfaces for FluxIndex RAG system

A .NET library for local LLM text generation using ONNX Runtime GenAI. Supports streaming, chat templates, and automatic hardware detection with CUDA/DirectML GPU acceleration.

Shared abstractions for the Flux ecosystem - IEnrichedChunk, ISourceMetadata, and related interfaces for RAG data pipeline interoperability

A lightweight, zero-configuration semantic reranker for .NET. Supports multiple cross-encoder models with automatic download, GPU acceleration, and HuggingFace caching.

Pure document extraction SDK for RAG systems. Zero AI dependencies. Extract text from PDF, DOCX, Excel, PowerPoint, Markdown, HTML, and text files. Provides IDocumentReader interface and implementations. Use... More information

llama.cpp server management for LMSupply. Provides llama-server downloading, GPU detection, and server pooling for GGUF model inference.

Text preprocessing library for RAG pipelines: PII masking, content filtering, and intelligent chunking including semantic chunking with Korean language support.

FluxIndex SDK - Complete RAG infrastructure with FileFlux integration, FluxCurator preprocessing, and FluxImprover quality enhancement. AI providers are externally injectable.

IronHive abstractions and interfaces

Core library for FluxCurator - Minimal dependencies. PII masking, content filtering, and rule-based chunking with Korean language support.

Local speech-to-text transcription using Whisper models with ONNX Runtime. Zero-configuration, automatic GPU acceleration, and lazy model downloading.