Update app.py

app.py

@@ -23,27 +23,33 @@ def load_dataset(file_path='PEC_Numbers_and_Names.xlsx'):
     df = pd.read_excel(file_path)
     return df
 
-# Load the model and tokenizer from Hugging Face
-tokenizer = AutoTokenizer.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
-model = AutoModel.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
-
-# Define the function to get the name based on the PEC number
-def get_name(pec_number, df):
-    result = df[df['PEC No.'] == pec_number]
+# Debugging function to get PEC number based on the name
+def get_pec_number(name, df):
+    print("Column names in DataFrame:", df.columns.tolist())  # Print the column names
+    print(f"Looking for Name: '{name}'")
+    
+    # Normalize the input and dataset
+    df['Name'] = df['Name'].str.strip().str.lower()
+    name = name.strip().str.lower()
+    
+    result = df[df['Name'] == name]
+    
     if not result.empty:
-        return result.iloc[0]['Name']
+        print(f"Found PEC Number: {result.iloc[0]['PEC No.']}")
+        return result.iloc[0]['PEC No.']
     else:
-        return "PEC Number not found."
+        print("Name not found.")
+        return "Name not found."
 
-# Function to process the PEC number using the Hugging Face model
-def process_with_model(pec_number):
-    inputs = tokenizer(pec_number, return_tensors="pt")
+# Function to process the name using the Hugging Face model
+def process_with_model(name):
+    inputs = tokenizer(name, return_tensors="pt")
     with torch.no_grad():
         outputs = model(**inputs)
     return outputs.last_hidden_state.mean(dim=1).squeeze().tolist()
 
 # Combine both functions to create a prediction
-def predict(pec_number, file):
+def predict(name, file):
     try:
         # Load the dataset from the uploaded file if provided
         if file is not None:
@@ -51,27 +57,28 @@ def predict(pec_number, file):
         else:
             df = load_dataset()
 
-        name = get_name(pec_number, df)
-        model_output = process_with_model(pec_number)
-        return f"Name: {name}\nModel Output: {model_output}"
+        pec_number = get_pec_number(name, df)
+        model_output = process_with_model(name)
+        return f"PEC Number: {pec_number}\nModel Output: {model_output}"
     except FileNotFoundError as e:
         return str(e)
 
+# Load the model and tokenizer from Hugging Face
+tokenizer = AutoTokenizer.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
+model = AutoModel.from_pretrained("Alibaba-NLP/gte-multilingual-base", trust_remote_code=True)
+
 # Build the Gradio interface with file upload option
 iface = gr.Interface(
     fn=predict,
     inputs=[
-        gr.Textbox(lines=1, placeholder="Enter PEC Number..."),
+        gr.Textbox(lines=1, placeholder="Enter Name..."),
         gr.File(label="Upload PEC Numbers and Names file (optional)")
     ],
     outputs="text",
-    title="PEC Number Lookup with Model Integration",
-    description="Enter a PEC number to retrieve the corresponding name and process it with a Hugging Face model. Optionally, upload the Excel file if not found."
+    title="Name to PEC Number Lookup with Model Integration",
+    description="Enter a name to retrieve the corresponding PEC number and process it with a Hugging Face model. Optionally, upload the Excel file if not found."
 )
 
 # Run the Gradio interface
 if __name__ == "__main__":
     iface.launch()
-
-
-