DocAILab/XRAG
XRAG is a benchmark for evaluating core component modules in advanced Retrieval-Augmented Generation systems.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
XRAG provides a configurable framework to benchmark foundational modules of RAG pipelines, including text splitters, embedders, retrievers, rerankers, and orchestrators such as self-RAG and adaptive-RAG. It is built on LlamaIndex and supports systematic evaluation of how each component affects end-to-end RAG performance. The project is published as a PyPI package and accompanies an ICDE 2026 paper.
Frequently asked
- What is DocAILab/XRAG?
- XRAG is a benchmark for evaluating core component modules in advanced Retrieval-Augmented Generation systems.
- Is XRAG open source?
- Yes — DocAILab/XRAG is open source, released under the Apache-2.0 license.
- What language is XRAG written in?
- DocAILab/XRAG is primarily written in Python.
- How popular is XRAG?
- DocAILab/XRAG has 591 stars on GitHub.
- Where can I find XRAG?
- DocAILab/XRAG is on GitHub at https://github.com/DocAILab/XRAG.