Ops Deck Lite

1. Install dependencies

npm install -g pm2
pip install fastapi uvicorn aiofiles
Ollama embedding model
ollama pull qwen3-embedding:8b

2. Create the Code Search service

mkdir -p pipeline/work/code-search
cd pipeline/work/code-search
The server needs:
- server.py (FastAPI app)
- code_index.db (SQLite, auto-created on first index)
- Ollama running locally for embeddings

Key code search server features:

3. Create the Prompt Library

mkdir -p pipeline/work/prompt-library/backend
cd pipeline/work/prompt-library/backend
Express server with:
- GET /api/prompts (list all)
- GET /api/prompts/:id (get one)
- POST /api/prompts (create)
- PUT /api/prompts/:id (update)
- DELETE /api/prompts/:id (delete)
- SQLite or JSON file storage

4. PM2 config

// ecosystem.config.cjs
module.exports = {
  apps: [
    {
      name: 'code-search',
      cwd: './pipeline/work/code-search',
      script: 'server.py',
      interpreter: 'python3',
      autorestart: true,
    },
    {
      name: 'prompt-library-api',
      cwd: './pipeline/work/prompt-library/backend',
      script: 'server.js',
      autorestart: true,
    },
  ]
};

5. Start and index

pm2 start ecosystem.config.cjs
pm2 save
Initial code index (takes a few minutes depending on codebase size)
curl -X POST http://localhost:5204/api/index?summarize=true
Set up nightly re-index
(crontab -l 2>/dev/null; echo "0 4 * * * curl -s -X POST http://localhost:5204/api/index?summarize=true > /dev/null") | crontab -