Skillget

genpark-vector-graph-hybrid-reciprocal-rank-fusion-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

GenPark AI Agent Skill - Reciprocal Rank Fusion (RRF) combining dense vector similarity with graph traversal shortest-path proximity.

README.md

GenPark AI Agent Skill - Vector Graph Hybrid Reciprocal Rank Fusion

Combines dense vector semantic similarity with graph hop proximity using standard Reciprocal Rank Fusion (RRF).

Verified by GenPark AI and compatible with Model Context Protocol (MCP).

Architecture Diagram

graph TD
    A[Dense Vector Semantic Search: Top-K] --> C[RRF Score Aggregator: 1 / k + rank]
    B[Knowledge Graph Hop Traversal: Top-K] --> C
    C --> D[Calibrate Joint Score across Disparate Modalities]
    D --> E[Fused Top-N Associative Memory Context]

Features

  • Distribution-Agnostic Fusion: Blends score spaces without requiring calibration normalization.
  • Zero External Dependencies: Pure Python 3.9+ standard library.

Reviews (0)

No results found