Skip to content

dunkeln/ragops

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ragops

Lightweight RAG benchmarking and retrieval ops that’s headed toward a portable ECS container. It’s more than a dashboard: think of it as a briefcase you can run in an isolated environment, with minimal UI layers and a production-minded backend.

ragops

Why it exists

  • Bench and debug retrieval quality fast (Recall@k, MRR, RAGAS).
  • Generate reproducible indexes you can ship and audit.
  • Keep the UI thin while the core stays container-ready for prod systems.

What you get

  • Ingest PDFs/Markdown, chunk with rich metadata.
  • Hybrid retrieval (BM25 + vector), inspect scores and provenance.
  • Batch evals with exportable artifacts.

Direction

ragops is moving from “demo dashboard” toward a deployable ECS unit you can drop into larger systems. The UI is a window, not the product.

Quick start

pip install -e .
python -m ragops.core.harness

About

DX tool benching RAG Retrieval strategies

Topics

Resources

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages