test.py

import pandas as pd
import numpy as np
from sentence_transformers import SentenceTransformer
import chromadb
import os

# Load the MovieLens dataset
movies = pd.read_csv('tmdb_5000_movies.csv')
credits = pd.read_csv('tmdb_5000_credits.csv')

# Let's take a peek at what we're working with
print(f"Total movies: {len(movies)}")
movies[['title', 'overview', 'genres', 'release_date']].head(2)
--------------------------------------------------------------------