md2rag - RAG Pipeline Automation
Business Goal
Accelerating development by automating the data preparation workflow (chunking, cleaning, embedding) for LLM projects.
Preparing raw data for vector databases is often the most time-consuming part of building RAG applications. md2rag is an open-source CLI tool that hierarchically parses Markdown documents, cleans them, generates embeddings, and uploads them to Qdrant with a single command.