def get_COS_recommendations(df, product, column='product'):
# Get the index of the product that matches the product name
df['ing#List'] = df['ing#List'].astype(str)
tfidf = TfidfVectorizer(stop_words=[0])
terms = tfidf.get_feautre_names()
tfidf_matrix = tfidf.fit_transform(df['ing#List'])
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
indices = pd.Series(df.index, index=df[column]).drop_duplicates()
idx = indices[product]
# Get the pairwsie similarity scores of all products with that product
sim_scores = list(enumerate(cosine_sim[idx]))
# Sort the products based on the similarity scores
sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
# Get the scores of the 10 most similar products
sim_scores = sim_scores[1:11]
# Get the product indices
product_indices = [i[0] for i in sim_scores]
# Return the top 10 most similar products and their ingredients
return df[['product', 'brand', 'ingList']].iloc[product_indices]
