src/constants.py

# embedding models dictionary
EMBEDDING_MODELS_DICT = {
    "Xenova/all-MiniLM-L6-v2": "https://huggingface.co/Xenova/all-MiniLM-L6-v2/resolve/main/onnx/model_quantized.onnx",
    "nomic-ai/nomic-embed-text-v1.5": "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5/resolve/main/onnx/model_quantized.onnx",
    "Xenova/all-mpnet-base-v2": "https://huggingface.co/Xenova/all-mpnet-base-v2/resolve/main/onnx/model_quantized.onnx",
    "Xenova/paraphrase-mpnet-base-v2": "https://huggingface.co/Xenova/paraphrase-mpnet-base-v2/resolve/main/onnx/model_quantized.onnx",
    "Xenova/all-MiniLM-L12-v2": "https://huggingface.co/Xenova/all-MiniLM-L12-v2/resolve/main/onnx/model_quantized.onnx",
    "nomic-ai/modernbert-embed-base": "https://huggingface.co/nomic-ai/modernbert-embed-base/resolve/main/onnx/model_quantized.onnx",
    # "Xenova/distiluse-base-multilingual-cased-v1": "https://huggingface.co/Xenova/distiluse-base-multilingual-cased-v1/resolve/main/onnx/model_quantized.onnx",
    # "Xenova/distiluse-base-multilingual-cased-v2": "https://huggingface.co/Xenova/distiluse-base-multilingual-cased-v2/resolve/main/onnx/model_quantized.onnx",
    # "Xenova/paraphrase-multilingual-MiniLM-L12-v2": "https://huggingface.co/Xenova/paraphrase-multilingual-MiniLM-L12-v2/resolve/main/onnx/model_quantized.onnx",
    # "Xenova/paraphrase-multilingual-mpnet-base-v2": "https://huggingface.co/Xenova/paraphrase-multilingual-mpnet-base-v2/resolve/main/onnx/model_quantized.onnx",
    # "Xenova/LaBSE": "https://huggingface.co/Xenova/LaBSE/resolve/main/onnx/model_quantized.onnx",
}

TOPIC_LABELS = [
    "Arts & Entertainment",
    "Business and Consumer Services",
    "Community and Society",
    "Computers Electronics and Technology",
    "Ecommerce & Shopping",
    "Finance",
    "Food and Drink",
    "Gambling",
    "Games",
    "Health",
    "Heavy Industry and Engineering",
    "Hobbies and Leisure",
    "Home and Garden",
    "Jobs and Career",
    "Law and Government",
    "Lifestyle",
    "News & Media Publishers",
    "Pets and Animals",
    "Reference Materials",
    "Science and Education",
    "Sports",
    "Travel and Tourism",
    "Vehicles",
    "Adult",
]