Advanced-RAG-Evaluation-Pipeline Sam33r-Shahzad · COMPLETED
Production-ready RAG architecture featuring multi-metric evaluation. Implements ChromaDB vector retrieval with mathematical scoring (MRR, nDCG) and automated LLM-as-a-Judge validation via Groq (Llama-3.3) for factual accuracy, completeness, and relevance checking. Built using Python and LiteLLM.
github.com/Sam33r-Shahzad/Advanced-RAG-Evaluation-Pipeline · ★ 1 · Forks 0 · Size 3.9 MB
SUMMARY
Technologies 4
Scored 4
Observed 4
Practices 6
Evidence 4
Skips 0
COVERAGE
Analyzed 105 files · 2 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
77 files · PRODUCTION
Python LANGUAGE Depth 70
8 files · PRODUCTION
Pydantic LIBRARY Depth 74
4 files · PRODUCTION
pandas LIBRARY Depth 54
1 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-06-25
Last commit 2026-06-25
Active months 1
Commits 2