import pickle
import datasets
from renumics import spotlight
from renumics.spotlight import dtypes as spotlight_dtypes
import os

if __name__ == "__main__":
    dataset_name="ai-aerospace/ac-text-embedding-ada-002-ams-test"
    # Load dataset using datasets.load_dataset()
    dataset = datasets.load_dataset(dataset_name, split="train",data_dir=os.environ.get("HF_HOME"))
    print("Dataset loaded using datasets.load_dataset().")

    df = dataset.to_pandas()

    view = spotlight.show(df, port=7860, host="0.0.0.0", 
                dtype={"used_by_questions": spotlight_dtypes.SequenceDType(spotlight_dtypes.str_dtype)}, 
                allow_filebrowsing=True)