BigHugger
GH Repository · HKUDS

MiniRAG

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

stars
2,017
30-day movement
+41/day
Related entries
60
Connections
1
pythondockerPythonretrieval-augmented-generationraglarge-language-models

MiniRAG is a Python-based retrieval-augmented generation framework from HKUDS, published as an ACL 2026 paper under the title 'Making RAG Simpler with Small and Open-Sourced Language Models'. It ships as a repository with Docker and Python toolchain support and an MIT licence.

Reach for it when you want to run RAG with small, open-sourced language models rather than large proprietary ones.

Use it to

  • Run RAG pipelines on small open-source models
  • Deploy a RAG setup via the provided Docker toolchain
  • Study the ACL 2026 MiniRAG approach
  • Extend an MIT-licensed RAG codebase

For Developers and researchers building RAG with small models

Role
rag
Language
Python
Licence
MIT
Forks
257
Open issues
29
Last push
2025-10-16
Latest release
v0.0.1 · 2025-01-16
topicsragretrieval-augmented-generationlarge-language-modelspythondocker