A comprehensive system for submitting and managing maintenance work orders with AI-powered features for transcription, location detection, and work order generation.

• Authentication: User authentication and authorization system
• Work Order Generation: AI-powered work order creation from audio descriptions and/or images
• Audio Transcription: Convert audio recordings to text using OpenAI Whisper
• Location Detection: Identify and match location references in work order descriptions
• Wand Management: Track and manage maintenance wands/devices

Transcribe audio recordings to text using OpenAI's Whisper model.

Endpoint: POST /api/transcribe

Request Body:

{
  "audioB64": "data:audio/mp3;base64,YOUR_BASE64_AUDIO_DATA_HERE"
}

Response:

{
  "success": true,
  "transcription": "The transcribed text will appear here."
}

Generate and manage maintenance work orders.

Generate Work Order: POST /api/workorders/generate

Request Body:

{
  "imageB64": "data:image/jpeg;base64,YOUR_BASE64_IMAGE_DATA_HERE", // Optional
  "audioB64": "data:audio/mp3;base64,YOUR_BASE64_AUDIO_DATA_HERE", // Optional
  "fromName": "John Doe"
}

Response:

{
  "subject": "Maintenance Request - [Issue Summary]",
  "body": "Full work order email body..."
}

• Authentication: /api/auth/*
• Locations: /api/locations/*
• Wands: /api/wands/*

• Deno runtime
• OpenAI API key (set as environment variable)

Create a .env file with the following variables:

OPENAI_API_KEY=your_openai_api_key

• Initialize node modules: deno cache --node-modules-dir .
• Generate database migrations: deno run -A --node-modules-dir npm:drizzle-kit generate

• /backend: Server-side code
  • /db: Database schemas and queries
  • /routes: API routes and handlers
  • /workorders: Work order generation logic
• /frontend: Client-side code
  • /components: React components
  • /pages: Page components
• /shared: Shared code between frontend and backend
• /pi: Code for Raspberry Pi devices (wands)

• Enroll devices
• Implement vector similarity search: https://orm.drizzle.team/docs/guides/vector-similarity-search
• Add more comprehensive documentation