rasinmuhammed/rag-tui
⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex.
This tool helps AI engineers and developers debug and refine their Retrieval-Augmented Generation (RAG) pipelines. It takes documents and queries as input, letting you visually inspect how text is broken into 'chunks' and how those chunks are retrieved, then outputs optimized configurations for production. It's designed for anyone building or maintaining AI applications that use RAG to ensure accurate and relevant responses.
Available on PyPI.
Use this if you need to visually understand, tune, and debug the chunking and retrieval stages of your RAG pipeline to prevent your LLM from generating incorrect or irrelevant answers.
Not ideal if you are not building or maintaining RAG-based AI applications, as this tool is specifically for RAG pipeline debugging.
Stars
21
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 08, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/rasinmuhammed/rag-tui"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
kbeaugrand/KernelMemory.StructRAG
Microsoft's Kernel Memory StructRAG implementation
metawake/ragtune
EXPLAIN ANALYZE for RAG retrieval — inspect, debug, benchmark, and tune your retrieval layer
rag-fish/NoesisNoema
A private, offline, multi-RAGpack LLM RAG app for macOS/iOS. Instant, context-aware answers—your...
derekshi1/DataResRAG
An ambitious project using RAG to create specialized course planning for UCLA students based on...
chernistry/sentio
Boilerplate RAG System with LangGraph Architecture