diff --git a/main.py b/main.py index 2052e49..7b41d6f 100644 --- a/main.py +++ b/main.py @@ -1015,9 +1015,9 @@ def batch_run_documents( page_filter_ground_truth_file = ( r"/data/emea_ar/ground_truth/page_filter/datapoint_page_info_88_documents.xlsx" ) - re_run_extract_data = False + re_run_extract_data = True re_run_mapping_data = True - force_save_total_data = True + force_save_total_data = False calculate_metrics = False extract_way = "text" @@ -1348,7 +1348,7 @@ if __name__ == "__main__": # special_doc_id_list = ["553242411"] - doc_source = "aus_prospectus" + doc_source = "emea_ar" if doc_source == "aus_prospectus": document_sample_file = r"./sample_documents/aus_prospectus_100_documents_multi_fund_sample.txt" with open(document_sample_file, "r", encoding="utf-8") as f: