manufacturing-nl-analytics

Sudeera844/manufacturing-nl-analytics
★ 0 stars Python AI/LLM Updated today
NL-to-SQL agent over a manufacturing lakehouse (DuckDB/Databricks) : LangGraph ReAct agent + MCP tool server, with LLM-judged groundedness checks and per-query cost/latency tracking.
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": {
    "manufacturing-nl-ana": {
      "command": "uvx",
      "args": [
        "manufacturing-nl-analytics"
      ]
    }
  }
}

Or install with pip: pip install manufacturing-nl-analytics

README Excerpt

An NL-to-SQL agent over a manufacturing lakehouse -- ask a question in plain English, the agent writes and runs the SQL, and every answer is checked for whether it's actually supported by the data it returned. Built to demonstrate the half of the "AI Engineer" job spec that [`agentic-erp-assistant`](../agentic-erp-assistant)

Tools (3)

get_schemalist_tablesrun_sql_query