Build [v1.7.0] - GitGuard - Infrastructure Hardening

This commit is contained in:
Daniel Bedeleanu
2026-04-12 22:45:27 +03:00
parent 0a6368b9f6
commit 994920bda2
14 changed files with 262 additions and 76 deletions

View File

@@ -7,36 +7,55 @@ base_dir = os.path.dirname(os.path.abspath(__file__))
dotenv_path = os.path.join(base_dir, ".env")
load_dotenv(dotenv_path)
def extract_label_info(image_bytes: bytes):
def extract_label_info(image_bytes: bytes, mode: str = "item"):
"""
Orchestrates extraction across multiple AI providers.
Order: Gemini (Flash/Pro) -> Claude (Haiku/Sonnet)
"""
prompt = """
Extract technical inventory information from this label image.
CRITICAL INSTRUCTIONS:
1. Look at the most prominent text (usually top 1-2 rows). This is the product NAME and MODEL.
2. Extract the PART NUMBER (P/N, Model No, Type). If no explicit Part Number is found, synthesize one from the most unique identifier in the header (e.g. 'OM4-MMF-DX').
3. Separate the COLOR (e.g. Turquoise, Yellow, Black).
4. Extract CATEGORY based on the item type (e.g. Patchcord, SFP, Connector).
5. Extract technical SPECS (e.g. '2.0mm', '10G', '850nm').
Return ONLY a valid JSON object:
{
"name": "Full descriptive name from header",
"part_number": "Unique identifier for fast scanning",
"category": "Broad category",
"color": "Color if present",
"specs": "Brief tech specs list",
"barcode": "Barcode value if visible",
"quantity": 1
}
Modes: 'item' (full technical extraction), 'box' (container discovery)
"""
if mode == "box":
prompt = """
Identify the CONTAINER or BOX name from this image.
Look for large, prominent, bold, or hand-written text that identifies a storage unit.
Ignore small technical details, quantities, or fine print.
Return ONLY a valid JSON object:
{
"box_label": "The identified container name",
"name": "Same as box_label",
"category": "Storage",
"specs": "Brief description if useful",
"quantity": 1
}
"""
else:
prompt = """
Extract technical inventory information from this label image.
CRITICAL INSTRUCTIONS:
1. Look at the most prominent text (usually top 1-2 rows). This is the product NAME and MODEL.
2. Extract the PART NUMBER (P/N, Model No, Type). If no explicit Part Number is found, synthesize one from the most unique identifier in the header (e.g. 'OM4-MMF-DX').
3. Separate the COLOR (e.g. Turquoise, Yellow, Black).
4. Extract CATEGORY based on the item type (e.g. Patchcord, SFP, Connector).
5. Extract technical SPECS (e.g. '2.0mm', '10G', '850nm').
Return ONLY a valid JSON object:
{
"name": "Full descriptive name from header",
"part_number": "Unique identifier for fast scanning",
"category": "Broad category",
"color": "Color if present",
"specs": "Brief tech specs list",
"barcode": "Barcode value if visible",
"quantity": 1
}
"""
# 1. Try Gemini
result = gemini.extract(image_bytes, prompt)
if result:
# Maintenance: Ensure fields are mapped if mode was box
if mode == "box" and "box_label" in result and "name" not in result:
result["name"] = result["box_label"]
return result
# 2. Try Claude (Fallback)