Files
tfm_ainventory/PLAN.md

32 lines
1.6 KiB
Markdown

# Inventory PWA System Implementation Plan
This document outlines the technical architecture for the unified Inventory System (FastAPI + PWA).
## Proposed Architecture
### 1. Backend Server (Linux / Docker)
- **Framework:** Python + FastAPI
- **Database:** SQLite (SQLAlchemy ORM)
- **Key Modules:**
- `Items / Interventions`: Standard CRUD logic.
- `Audit`: Every payload that mutates data writes an immutable log row.
- `AI-OCR`: Endpoint integrating Google Gemini Vision API (via Google AI Studio key) for complex label extraction onboarding.
### 2. Unified Web Application (PWA)
- **Framework:** React + Next.js (or equivalent).
- **Offline Engine:** Service Workers, IndexedDB local storage map.
- **Desktop Mode:** Full width dashboard, management, and settings.
- **Mobile Mode (Browser / Add to Homescreen):** Dedicated full-screen scanner using `html5-qrcode`.
### 3. AI Cost Strategy
- **Routine Scans (Check-ins/Outs):** Client-side HTML5 barcode scanner. **Cost: $0.**
- **Label Scanning (New Item):** Proxies a request to the Gemini API to parse the SFP label into JSON template fields.
## Implementation Phases
- **Phase 1: Database & Backend Foundation** - SQLite schemas, User management, and Python API structures.
- **Phase 2: Core Inventory API** - Endpoints to Add/Remove items, offline sync-merge logic, Audit triggers.
- **Phase 3: The PWA Frontend** - PWA manifest, offline capabilities, UI scaffolding for Desktop/Mobile.
- **Phase 4: Client-Side Scanning** - Integration of local JS barcode reading for routine stock scanning.
- **Phase 5: Gemini AI Vision Integration** - Server-side Gemini API integration and the text-mapping frontend view.