# store data in dataframe
df = pd.DataFrame(video_data_list)

# Load the model
model = SentenceTransformer("all-mpnet-base-v2")

# Encode all titles
embeddings = model.encode(df['title'].to_list())

# compute similarities
similarities = model.similarity(embeddings, embeddings)

# match least JDs least similar to positive match as the negative match
similarities_argsorted = np.argsort(similarities.numpy(), axis=1)
negative_pair_index_list = []

for i in range(len(similarities)):

    # Start with the smallest similarity index for the current row
    j = 0
    index = int(similarities_argsorted[i][j])

    # Ensure the index is unique
    while index in negative_pair_index_list:
        j += 1  # Move to the next smallest index
        index = int(similarities_argsorted[i][j])  # Fetch next smallest index

    negative_pair_index_list.append(index)

# add negative pairs to df
df['title_neg'] = df['title'].iloc[negative_pair_index_list].values