wurzel
An open-source Python framework for building ETL pipelines that feed Retrieval-Augmented Generation systems, with multi-tenancy, cloud-native deployment and job scheduling.
wurzel is a Python library for the extract, transform and load steps behind Retrieval-Augmented Generation systems. It is built around a step abstraction that can be run from its own CLI or called programmatically, and it uses pydantic and pandera for type-checked data.
The repository ships initial integrations for RAG-ecosystem tools including Qdrant, Milvus and Hugging Face, giving a starting point for scalable pipelines. It targets multi-tenant deployments, is designed for cloud-native environments such as Kubernetes and Docker, and supports built-in or external scheduling of ETL jobs.