Skillget

genpark-reciprocal-rank-fusion-rrf-reranker-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Gecti
  • Code scan — Scanned 6 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

Reciprocal Rank Fusion (RRF) multi-retriever rank aggregator with rank discount constant

README.md

genpark-reciprocal-rank-fusion-rrf-reranker-skill

Agent Skill implementing Reciprocal Rank Fusion (RRF) rank aggregation for hybrid search pipelines in 100% Python standard library.

Architectural Flow

flowchart TD
    Q["Search Query"] --> R1["Retriever 1 (BM25 Lexical)"]
    Q --> R2["Retriever 2 (Dense Vector)"]
    Q --> R3["Retriever 3 (Graph Knowledge)"]
    R1 --> L1["Ranked List 1"]
    R2 --> L2["Ranked List 2"]
    R3 --> L3["Ranked List 3"]
    L1 & L2 & L3 --> RRF["RRF Formula: Score(d) = Sum 1/(k + r(d))"]
    RRF --> Final["Consensus Ranked Output"]

Yorumlar (0)

Sonuc bulunamadi