kamathhrishi/sourcemapr

Debug RAG pipelines with just 2 lines of code

25
/ 100
Experimental

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.

AI-debugging RAG-pipeline-evaluation LLM-observability natural-language-processing document-intelligence
No License
Maintenance 6 / 25
Adoption 5 / 25
Maturity 14 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

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.