bede/tfm_ainventory
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Build [v1.9.24]

Browse Source
This commit is contained in:
Daniel Bedeleanu
2026-04-15 15:33:14 +03:00
parent f751cc20a7
commit 73ab38d237
4 changed files with 21 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
PROJECT_ARCHITECTURE.md
View File

@@ -12,7 +12,7 @@ A unified system to maintain an inventory of "items" and their quantities, inclu
- **Database:** SQLite (SQLAlchemy) - Local file-based persistence
- **Validation:** Pydantic v2
- **Auth:** Hybrid LDAP (python-ldap) + PBKDF2 local password hash caching
- **AI Engine:** Google GenAI SDK (Gemini 2.0 Flash) - Location: `backend/ai/`
- **AI Engine:** Google GenAI SDK (Gemini 2.0 Flash) & Anthropic SDK (Claude 3.5 Sonnet) - Location: `backend/ai/`
### 2.2 Frontend (Web & PWA)
- **Architecture:** Next.js 15+ (App Router)
@@ -32,7 +32,7 @@ A unified system to maintain an inventory of "items" and their quantities, inclu
- **PWA Deployment:** `next-pwa` (Service Workers + Manifest.json)
- **HTTPS Proxy:** `caddy` or `local-ssl-proxy` (Port 8909)
- **Servers:** Frontend (Port 8907), Backend (Port 8906)
- **Configuration:** Centrally managed via root `inventory.env` (Network/CORS/API Keys) and `config/` directory (LDAP, Caddyfile).
- **Configuration:** Centrally managed via root `inventory.env` (Network/CORS/API Keys), `config/` directory (LDAP, Caddyfile), and a dynamic `ConfigManager` (`backend/config_manager.py`) for runtime environment and AI provider settings.
## 3. Data Models & Entities
- **Item:** Name, Category Group (Structured), Item Type (Specific), Quantity, Barcode, Part Number, Box Label (Association).
@@ -43,7 +43,8 @@ A unified system to maintain an inventory of "items" and their quantities, inclu
## 4. Scanning & Optimization Strategy (Crucial)
### 4.1 AI Usage Policy
- **Routine Operations (Check-in/Out):** Executes entirely on the local device unconditionally using `html5-qrcode` ($0 cost). No AI is allowed here.
- **New Item Onboarding (AI Label OCR):** Uses cloud AI (`gemini-2.0-flash`). The user takes a photo, AI extracts data based on strict templates.
- **New Item Onboarding (AI Label OCR):** Uses cloud AI (`gemini-2.0-flash` or `claude-3-5-sonnet`). The user takes a photo, AI extracts data based on strict templates.
- **AI Provider Selection (v1.9.23):** Administrators can choose between Gemini and Claude via the Admin Dashboard. API keys are managed securely in the environment.
- **AI Box Discovery Mode (v1.6.0):** Supports specialized `mode="box"` prompt that focuses exclusively on prominent container names/hand-written labels, ignoring technical spec noise.
- **Validation Mask:** AI-extracted data is NEVER saved directly. It is presented in a validation UI for human confirmation.
@@ -103,3 +104,9 @@ To ensure enterprise-grade protection, the following policies are enforced:
To ensure deployment stability on macOS environments with potentially broken developer tool links (`xcode-select` errors):
- **Direct Binary Mapping:** The system bypasses path resolution by using a hardcoded direct link to the Git binary in `.git_path` (`/Library/Developer/CommandLineTools/usr/bin/git`).
- **Persistence Mandate:** This path is protected by mandatory AI rules and must never be removed or modified to ensure `save-version` and automated deployment scripts remain functional.
106:
107: ## 8. Multi-AI Engine & Dynamic Configuration (v1.9.23)
108: To enhance extraction flexibility and system resilience:
109: - **Unified AI Core:** The backend uses an abstraction layer to handle multiple AI providers (Gemini and Claude).
110: - **Dynamic Configuration:** System settings (AI Provider, API Keys, Backup Policies) are managed via `backend/config_manager.py`, allowing real-time updates without restarting the container.
111: - **Admin Standardization:** The Admin Dashboard features a standardized configuration UI with secure field masking for sensitive credentials.