dataset/data-normalization/merge_data.py

import json

with open("BHT NMLT train.json", "r", encoding="utf-8") as f:
    data1 = json.load(f)

with open("BHT-NMLT - CuoiKi.json", "r", encoding="utf-8") as f:
    data2 = json.load(f)

with open("bai_tap.json", "r", encoding="utf-8") as f:
    data3 = json.load(f)

# kiểm tra an toàn
assert isinstance(data1, list)
assert isinstance(data2, list)
assert isinstance(data3, list)

merged_data = data1 + data2 + data3

with open("knowledge_base.json", "w", encoding="utf-8") as f:
    json.dump(merged_data, f, ensure_ascii=False, indent=2)

print(
    f"Merged {len(data1)} + {len(data2)} + {len(data3)} "
    f"items -> {len(merged_data)} items"
)