chunking-strategy

Visual tool to compare 6 RAG chunking strategies side-by-side with grading and query selection

LumenFlow is an AI-assisted customer support operations platform featuring local LLM workflows, retrieval-augmented generation, grounded drafting, human review, and evaluation-first system design.

Comparison of text chunking strategies for RAG, with a focus on Persian text

AI-powered backend system for debugging distributed systems using RAG, semantic search, and LLM-based root cause analysis.

AI-powered RAG system for Indian Income Tax that provides accurate, citation-backed answers using vector search, hybrid retrieval, and LLMs.

High-performance RAG API with AI, multi-format docs, Gemini integration, security, CLI.

Applying domain specific evaluations to RAG chunking and embedding functions

An enterprise-ready document classification service built with FastAPI that automatically classifies uploaded documents and recommends the optimal processing strategy for Enterprise AI and RAG applications.

Reference RAG implementation tracing every choice to a numbered decision, not an unexamined default. Structure-aware chunking, provider-agnostic embeddings, hybrid dense+BM25 retrieval, negation-aware groundedness checking ported from Sentinel. 27 tests, zero API key required to run them.

Chunking In Enterprise Document Processing Pipeline for building Retrieval-Augmented Generation (RAG) and Enterprise AI Knowledge Assistants.

Experimental RAG pipeline exploring chunking strategies, vector databases, and semantic search. Built as an educational project.

An Overview of the Latest Document Chunking Research

See how chunking strategy changes RAG retrieval. Same document, same question, different chunks → different answer. Built with Next.js, Voyage embeddings, and Claude.