flowchart TD
    UserQuery["User Prompt / Agent Goal"] --> SemCache["Semantic Cache Check"]
    SemCache -->|Cache Hit| FastReturn["Cached Response (0ms)"]
    SemCache -->|Cache Miss| DualRetrieval["Dual Retrieval Pipeline"]
    
    subgraph DualRetrieval ["Hybrid Search Engine"]
        BM25Lex["BM25 Okapi Lexical Ranker"]
        DenseVec["Dense Cosine Vector Similarity"]
    end
    
    DualRetrieval --> RRF["Reciprocal Rank Fusion (RRF)"]
    RRF --> GraphExp["Knowledge Graph Triplet Expansion"]
    GraphExp --> LostMiddle["Lost-In-The-Middle Context Reorderer"]
    LostMiddle --> LLM["LLM Synthesis with Optimal Context"]
    LLM --> EpisodicMem["Episodic Consolidation & Recency Decay"]

from client import CosineBM25ReciprocalRankFusion

# Initialize engine
engine = CosineBM25ReciprocalRankFusion()

# Execute self-testing benchmark suite
result = engine.run_benchmark_rrf_fusion()
print("Execution Result:", result)

{
  "mcpServers": {
    "genpark-cosine-bm25-reciprocal-rank-fusion-skill": {
      "command": "python",
      "args": ["-u", "/path/to/genpark-cosine-bm25-reciprocal-rank-fusion-skill/mcp_server.py"]
    }
  }
}

pip install git+https://github.com/alphaparkinc/genpark-cosine-bm25-reciprocal-rank-fusion-skill.git