kamathhrishi/sourcemapr
Debug RAG pipelines with just 2 lines of code
This tool helps AI engineers and researchers understand and fix problems in their Retrieval Augmented Generation (RAG) systems. It allows you to trace exactly how an AI's answer was generated, showing which document snippets (chunks) it used and the full conversation with the AI model. You feed in your RAG pipeline's activity, and it provides a visual dashboard to see the entire process, pinpointing issues like hallucinations or poor retrieval.
Available on PyPI.
Use this if you are building or maintaining RAG applications, especially those processing PDF documents, and need to thoroughly debug why your AI is giving certain answers or to evaluate your retrieval and chunking strategies.
Not ideal if your primary documents are not PDFs or if you need to debug complex, multi-step AI agent pipelines, as support for these is currently experimental.
Stars
13
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 29, 2025
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/kamathhrishi/sourcemapr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OpenBMB/UltraRAG
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
Quansight/ragna
RAG orchestration framework ⛵️
microsoft/rag-time
RAG Time: A 5-week Learning Journey to Mastering RAG
AnkitNayak-eth/EpsteinFiles-RAG
A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).
apify/apify-haystack
The official integration for Apify and Haystack 2.0