arabic-rag-pipeline PYTHON01100100 · PARTIAL
A single-file RAG pipeline for Arabic PDF lectures with two-stage retrieval, cross-encoder reranking, OCR fallback, and conversation memory — powered by Gemini and ChromaDB.
github.com/PYTHON01100100/arabic-rag-pipeline · ★ 0 · Forks 0 · Size 2.2 MB
SUMMARY
Technologies 10
Scored 8
Observed 8
Practices 6
Evidence 11
Skips 2
COVERAGE
Analyzed 36 files · 3 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
JSON LANGUAGE Depth 70
1 files · PRODUCTION
Shell LANGUAGE Depth 70
5 files · PRODUCTION
Markdown LANGUAGE Depth 70
14 files · PRODUCTION
YAML LANGUAGE Depth 70
5 files · PRODUCTION
Python LANGUAGE Depth 70
2 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth —
0 files · config only
Requests LIBRARY Depth 54
1 files · PRODUCTION
python-dotenv LIBRARY Depth —
0 files · config only
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · observedlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-02-17
Last commit 2026-08-18
Active months 2
Commits 3