up

app.py

@@ -17,6 +17,8 @@ print("pandoc", pypandoc.__version__)
 #document.add_heading('Labels for ', level=1)
 RESULTS_FOLDER = "./results"
 
+DOC_FOLDER = snapshot_download("claudiag/atlas", token=os.environ.get("HF_TOKEN"))
+
 CAT_TO_CODEWORDS = {
     "Prejudices": ["prejudice", "judge", "preconceive", "stigma", "assumption", "assume", "misunderstanding", "unexamined", "distorted", "clear", "compar"],
     "Self-knowledge": ["self-knowledge", "self-awareness", "introspection", "examined", "myself", "realization", "belief"],
@@ -105,7 +107,6 @@ def main(filename, codewords_mapping):
 
 
 def convert(*keywords):
-    cached_folder = snapshot_download("claudiag/atlas", token=os.environ.get("HF_TOKEN"))
     codewords_mapping = {k: v for k,v in zip(CATEGORIES, keywords)}
 
     num_files = 0
@@ -114,7 +115,7 @@ def convert(*keywords):
     os.makedirs(RESULTS_FOLDER)
 
     result_files = []
-    for folder in tqdm.tqdm(glob.glob(os.path.join(cached_folder, "/*"))):
+    for folder in tqdm.tqdm(glob.glob(os.path.join(DOC_FOLDER, "/*"))):
         all_files = tqdm.tqdm(glob.glob(f"./{folder}/*"))
         num_files += len(all_files)