nexus-rag

Parthp28/nexus-rag

★ 0 stars Python AI/LLM Updated 5d ago

Hybrid RAG system with MCP server — 0.90 RAGAS faithfulness, 0.96 context precision, 91 tests

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "nexus-rag": {
      "command": "uvx",
      "args": [
        "nexus-rag"
      ]
    }
  }
}

Or install with pip: pip install nexus-rag

README Excerpt

A production-grade hybrid RAG system combining dense vector search, BM25 keyword retrieval, and Cohere cross-encoder reranking — exposed via a FastAPI REST interface and a Model Context Protocol (MCP) server for direct integration with AI assistants. <table> <thead> <tr><th>Metric</th><th>Value</th><th>Threshold</th></tr>

Topics

fastapihybrid-retrievallanggraphllmmcppythonqdrantragragas

nexus-rag

Quick Install

README Excerpt

Topics

Related AI/LLM Servers