Update app.py

app.py

@@ -3,10 +3,11 @@ os.system('pip install transformers')
 # Import the necessary libraries
 import os
 os.system('pip install torch')
+# Import the necessary libraries
 from transformers import AutoModel, AutoTokenizer
 import torch
 from torch.utils.data import DataLoader, Dataset
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split  # Importing train_test_split from scikit-learn
 import pandas as pd
 import gradio as gr
 
@@ -14,9 +15,9 @@ import gradio as gr
 model = AutoModel.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
 
-# Function to load dataset (adjust this function if your dataset is complex)
+# Function to load the dataset
 def load_dataset():
-    df = pd.read_excel("your_dataset.xlsx")  # Ensure this file exists in your working directory
+    df = pd.read_excel("your_dataset.xlsx")  # Ensure the file name and path are correct
     print("Columns in the dataset:", df.columns.tolist())
     return df