Python · MIT
salikhussain71-code/PAKGOV-RAG-project
Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation.
★ 130
Stars
5 forks · 2 open issues
+1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
22.0
Momentum / 100
see the breakdown below
51d ago
Created
last push 5d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 1.1 | +1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.04× the monthly pace |
| Freshness | 15 | 14.8 | last push 5d ago; decays to zero at 180 days |
| Scale | 15 | 6.1 | 130 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 22.0 | sum of the above |
Detail
| Topics | artificial-intelligenceinformation-retrievallegal-nlplow-resource-languagesnlpocrragretrieval-augmented-generationtransformersurdu-nlp |
| Matched on | RAG (rag, retrieval-augmented-generation) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +61 stars over 17 days = 3.6/day |
| Lifetime average | 2.65 stars/day over 49 days |
| First seen here | 2026-10-19 |
| Last read | 2d ago |