Update app.py

app.py

@@ -13,41 +13,55 @@ install("pandas")
 install("scikit-learn")
 install("gradio")
 
-# 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
+import os
 import pandas as pd
 import gradio as gr
-import os
+from transformers import AutoModel, AutoTokenizer
 
 # Load the pre-trained model and tokenizer
-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)
+def load_model_and_tokenizer():
+    try:
+        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)
+        return model, tokenizer
+    except Exception as e:
+        print(f"Error loading model or tokenizer: {e}")
+        return None, None
 
 # Function to load the dataset
 def load_dataset():
-    # Use the uploaded file path
     file_path = "Valid-part-2.xlsx"
     if not os.path.exists(file_path):
         raise FileNotFoundError(f"Dataset not found. Please ensure that '{file_path}' exists.")
     
-    df = pd.read_excel(file_path)  # Load the Excel file
-    print("Columns in the dataset:", df.columns.tolist())
-    return df
+    try:
+        df = pd.read_excel(file_path)
+        print("Columns in the dataset:", df.columns.tolist())
+        return df
+    except Exception as e:
+        print(f"Error loading dataset: {e}")
+        return None
 
 # Function to search by name and return the PEC number
 def search_by_name(name, df):
-    name_matches = df[df['name'].str.contains(name, case=False, na=False)]
-    if not name_matches.empty:
-        return f"Your PEC number: {name_matches['PEC number'].values[0]}"
-    else:
-        return "No matches found for your name."
+    if df is None:
+        return "Error: Dataset not loaded."
+    
+    try:
+        name_matches = df[df['name'].str.contains(name, case=False, na=False)]
+        if not name_matches.empty:
+            return f"Your PEC number: {name_matches['PEC number'].values[0]}"
+        else:
+            return "No matches found for your name."
+    except Exception as e:
+        return f"Error during search: {e}"
 
 # Gradio interface
 def build_interface():
     df = load_dataset()  # Load your dataset
+    if df is None:
+        return None
+    
     iface = gr.Interface(
         fn=lambda name: search_by_name(name, df),
         inputs=gr.Textbox(label="Please write your Name"),
@@ -59,9 +73,13 @@ def build_interface():
 
 # Main function to run the Gradio app
 if __name__ == "__main__":
-    try:
+    model, tokenizer = load_model_and_tokenizer()
+    if model is None or tokenizer is None:
+        print("Failed to load model or tokenizer. Exiting.")
+    else:
         iface = build_interface()
-        iface.launch()
-    except FileNotFoundError as e:
-        print(str(e))
+        if iface is not None:
+            iface.launch()
+        else:
+            print("Failed to build interface due to dataset issues.")