---

name: warnerco-schematica description: Develop and extend the WARNERCO Robotics Schematica system - an agentic RAG application with FastAPI, FastMCP, LangGraph orchestration, and 3-tier memory (JSON/Chroma/Azure AI Search). Use when working on the schematica backend, adding schematics, modifying the LangGraph flow, updating dashboards, or deploying to Azure.

WARNERCO Robotics Schematica

Agentic robot schematics system with semantic memory and retrieval-augmented generation.

Architecture

Copy┌─────────────────────────────────────────────────────────────┐
│                     FastAPI + FastMCP                       │
├─────────────────────────────────────────────────────────────┤
│  LangGraph Flow                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐    │
│  │ Parse    │→ │ Retrieve │→ │ Compress │→ │ Reason   │→ ··│
│  │ Intent   │  │          │  │ Context  │  │ (LLM)    │    │
│  └──────────┘  └──────────┘  └──────────┘  └──────────┘    │
├─────────────────────────────────────────────────────────────┤
│  3-Tier Memory                                              │
│  ┌───────────┐  ┌───────────┐  ┌─────────────────┐         │
│  │ JSON      │→ │ Chroma    │→ │ Azure AI Search │         │
│  │ (source)  │  │ (vectors) │  │ (enterprise)    │         │
│  └───────────┘  └───────────┘  └─────────────────┘         │
└─────────────────────────────────────────────────────────────┘

Project Structure

Copysrc/warnerco/backend/
├── app/
│   ├── main.py           # FastAPI application
│   ├── config.py         # Settings and environment
│   ├── models.py         # Pydantic schemas
│   ├── routes.py         # API endpoints
│   ├── mcp_tools.py      # FastMCP tool definitions
│   ├── adapters/         # Memory backend implementations
│   │   ├── json_store.py
│   │   ├── chroma_store.py
│   │   └── azure_store.py
│   └── langgraph/
│       └── flow.py       # 5-node RAG orchestration
├── data/
│   ├── schematics/       # JSON source of truth
│   └── chroma/           # Vector embeddings
├── static/dash/          # SPA dashboards
└── .env                  # Configuration

Commands

Copycd src/warnerco/backend

# Local development
uv sync
uv run uvicorn app.main:app --reload --port 8000

# Index schematics into Chroma
uv run python -c "from app.adapters.chroma_store import ChromaMemoryStore; import asyncio; asyncio.run(ChromaMemoryStore().index_all())"

# MCP stdio server (for Claude Desktop)
uv run warnerco-mcp

Memory Backend Selection

Set MEMORY_BACKEND in .env:

MCP Tools

LangGraph Flow

5-node retrieval-augmented generation:

1. parse_intent - Classify query (lookup/diagnostic/analytics/search)
2. retrieve - Fetch candidates from memory backend
3. compress_context - Minimize token bloat
4. reason - LLM generates response (Azure OpenAI gpt-4o-mini)
5. respond - Format for dashboards/MCP

Adding Schematics

Edit data/schematics/schematics.json:

Copy{
  "id": "WRN-00026",
  "model": "WC-900",
  "name": "New Robot Name",
  "component": "component description",
  "version": "v1.0",
  "summary": "Technical summary...",
  "category": "sensors",
  "status": "active",
  "tags": ["tag1", "tag2"],
  "specifications": {
    "spec_key": "spec_value"
  },
  "url": "https://schematics.warnerco.io/..."
}

Then re-index: uv run python -c "...index_all()"

Dashboards

• Schematics Browser (/dash/schematics/) - Search, filter, view robot data
• Memory Learning (/dash/memory/) - Educational RAG visualization

Azure Deployment

See references/azure-deployment.md for:

• Container App setup
• APIM configuration
• AI Search indexing
• OpenAI model deployment

API Endpoints