utils/seed_data.py

"""
Seeds the incident log CSV and ChromaDB with sample data for testing.
Run once: python -m utils.seed_data
"""

import sys, os
sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))

from utils.incident_logger import log_incident
from rag_module.vector_store import rebuild_from_csv

SAMPLE_INCIDENTS = [
    ("KA05MN1234", "car",   "Gate_A",      "normal",       ""),
    ("MH12AB5678", "truck", "VIP_LOT",      "unauthorized", "Heavy vehicle in VIP zone"),
    ("KA01XY9999", "car",   "Gate_B",      "flagged",      "Reported stolen vehicle"),
    ("DL4CAF0001", "bus",   "Gate_A",      "normal",       ""),
    ("TN09CD2222", "car",   "COMPACT_ONLY","normal",       ""),
    ("UNKNOWN",    "car",   "Gate_C",      "flagged",      "Plate unreadable"),
    ("KA05MN1234", "car",   "Gate_A",      "anomaly",      "Same plate seen 6x in 10 min"),
    ("AP28PQ3344", "motorcycle", "Gate_B", "normal",       ""),
    ("KA01XY9999", "car",   "Gate_A",      "unauthorized", "Blacklisted vehicle re-entry"),
    ("GJ05BK7777", "car",   "Gate_A",      "normal",       ""),
]

print("Seeding incidents...")
for plate, cls, zone, status, notes in SAMPLE_INCIDENTS:
    row = log_incident(plate, cls, zone, status, notes)
    print(f"  Logged: {row['id']} | {plate} | {status}")

print("\nRebuilding ChromaDB from CSV...")
rebuild_from_csv()
print("Done! You can now query the RAG pipeline.")