diff --git a/local_evaluation.py b/local_evaluation.py index 221358e3b167e5f1259125cac76dd932d28e554d..2420b94eaddf9a555c2432caf005076a150ce1c5 100644 --- a/local_evaluation.py +++ b/local_evaluation.py @@ -2,6 +2,7 @@ import pandas as pd from tqdm import tqdm import torch import numpy as np +import os from sentence_transformers import SentenceTransformer import metrics @@ -205,7 +206,17 @@ def get_task_parsers(): # Main execution function to load data, generate model outputs, evaluate, and aggregate scores def main(): # Load development data + # Please download the development data from : https://www.aicrowd.com/challenges/meta-comprehensive-rag-benchmark-kdd-cup-2024/dataset_files + # and place it at: ./data/development.json DATA_FILENAME = "./data/development.json" + + if not os.path.exists(DATA_FILENAME): + raise FileNotFoundError( + f"Development data file not found at {DATA_FILENAME}." + "Please download the development data from : https://www.aicrowd.com/challenges/meta-comprehensive-rag-benchmark-kdd-cup-2024/dataset_files" + "and place it at: ./data/development.json" + ) + data_df = load_development_data(DATA_FILENAME) # Load the model from the user's custom configuration