up

app.py

@@ -5,6 +5,7 @@ import shutil
 import os
 import tqdm
 from huggingface_hub import snapshot_download
+from huggingface_hub import HfApi, login
 import tempfile
 import re
 import pdfminer
@@ -12,12 +13,18 @@ import pdfminer
 print("pdfminer", pdfminer.__version__)
 print("pandoc", pypandoc.__version__)
 
+HF_TOKEN = os.environ.get("HF_TOKEN")
+
+api = HfApi()
+login(HF_TOKEN)
+
+
 #from docx import Document
 #document = Document()
 #document.add_heading('Labels for ', level=1)
 RESULTS_FOLDER = "./results"
 
-DOC_FOLDER = snapshot_download("claudiag/atlas", token=os.environ.get("HF_TOKEN"), repo_type="dataset")
+DOC_FOLDER = snapshot_download("claudiag/atlas", token=HF_TOKEN, repo_type="dataset")
 
 CAT_TO_CODEWORDS = {
     "Prejudices": ["prejudice", "judge", "preconceive", "stigma", "assumption", "assume", "misunderstanding", "unexamined", "distorted", "clear", "compar"],
@@ -127,7 +134,14 @@ def convert(*keywords):
 
             return f"Retrieved from {num_files}"
 
-inputs = [gr.Textbox(label=f"Enter your keywords for {k}", max_lines=2, placeholder=CAT_TO_CODEWORDS[k]) for k in CATEGORIES]
+#    api.upload_file(
+#            path_or_fileobj="/path/to/local/folder/README.md",
+#            path_in_repo="README.md",
+#            repo_id="username/test-dataset",
+#            repo_type="dataset",
+#            )
+
+inputs = [gr.Textbox(label=f"Enter your keywords for {k}", max_lines=2, placeholder=CAT_TO_CODEWORDS[k], value=CAT_TO_CODEWORDS[k]) for k in CATEGORIES]
 
 iface = gr.Interface(
         fn=convert, inputs=inputs, outputs="text")