mba/Research
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4 Commits 1 Branch 0 Tags
main
Commit Graph

4 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mahdi Bazrafshan
0488a7e0d0 docs(rag): add top-level readme for chunking directory 2026-07-21 10:14:42 +03:30
Mahdi Bazrafshan
642aec93f2 docs(rag): add domain model and original research input 2026-07-21 10:10:06 +03:30
Mahdi Bazrafshan
6c9cebaaa0 docs(research): add farsi embedding model research knowledge base 
Body:
        Why:
        - Insurance RAG pipeline needs Farsi-optimized embeddings
        - Current local baseline (Nomic Embed) is English-only

        Changes:
        - 8 cloud model profiles with curl + python test commands
        - 5 local model profiles with VRAM, serving platform notes
        - Persian benchmark landscape (MIRACL-Fa, mMARCO, FaMTE, MTEB)
        - Decision report with ranked options and recommendations
        - Full comparison table (15 models × 10 columns)

        Impact:
        - Knowledge base for embedding model selection
        - Top picks: BGE-M3 (local), Cohere embed-v4.0 (cloud)
        - Critical: Nomic Embed must be replaced (English-only)
 2026-07-20 15:00:11 +03:30
Mahdi Bazrafshan
72d8a3ebe4 Initial commit 2026-07-20 14:55:50 +03:30