Spaces:
Sleeping
Sleeping
| # Install necessary libraries | |
| import os | |
| import subprocess | |
| # Function to install a package if it is not already installed | |
| def install(package): | |
| subprocess.check_call([os.sys.executable, "-m", "pip", "install", package]) | |
| # Ensure the necessary packages are installed | |
| install("transformers") | |
| install("torch") | |
| install("pandas") | |
| install("scikit-learn") | |
| install("gradio") | |
| import os | |
| import pandas as pd | |
| import gradio as gr | |
| from transformers import AutoModel, AutoTokenizer | |
| # Load the pre-trained model and tokenizer | |
| 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(): | |
| 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.") | |
| 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): | |
| 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"), | |
| outputs=gr.Textbox(label="Your PEC number"), | |
| title="PEC Number Lookup", | |
| description="Enter your name to find your PEC number." | |
| ) | |
| return iface | |
| # Main function to run the Gradio app | |
| if __name__ == "__main__": | |
| 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() | |
| if iface is not None: | |
| iface.launch() | |
| else: | |
| print("Failed to build interface due to dataset issues.") | |