embed_documents.py

import pandas as pd
from buster.documents_manager import DeepLakeDocumentsManager

if __name__ == "__main__":
    vector_store_path = "deeplake_store"
    chunk_file = "data/output.csv"
    overwrite = True

    df = pd.read_csv(chunk_file)

    # some pre-processing based on the latest file provided
    df["url"] = df["source"]
    df["source"] = "towardsai_blog"
    df = df.dropna()

    dm = DeepLakeDocumentsManager(vector_store_path, overwrite=overwrite)
    dm.batch_add(df)
    zipped_file_path = dm.to_zip()
    print(f"Contents zipped to: {zipped_file_path}")