Semantic-Search-RAG-Engine-Built-From-Scratch MelihOrel · COMPLETED
🔍 A Semantic Search and RAG engine built entirely from scratch—no LangChain or LlamaIndex. It features custom chunking experiments, dense/sparse/hybrid retrieval (Qdrant + BM25), and rigorous IR evaluation (nDCG@k, MRR) using real-world CFPB data. 🚀📚
github.com/MelihOrel/Semantic-Search-RAG-Engine-Built-From-Scratch · ★ 2 · Forks 0 · Size 811 KB
SUMMARY
Technologies 7
Scored 7
Observed 7
Practices 6
Evidence 8
Skips 0
COVERAGE
Analyzed 20 files · 3 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
12 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 74
5 files · PRODUCTION
TypeScript LANGUAGE Depth 58
1 files · PRODUCTION
pandas LIBRARY Depth 70
4 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-06-22
Last commit 2026-06-22
Active months 1
Commits 3