.

app.py

@@ -29,6 +29,7 @@ sorted_day = sorted(date_dict[last_year][last_month].keys())
 last_day = sorted_day[-1]
 last_papers = date_dict[last_year][last_month][last_day]
 selected_paper = last_papers[0]
+visible = True if len(sorted_year) > 0 else False
 
 with gr.Blocks(css="constants/styles.css", theme=gr.themes.Soft()) as demo:
     cur_arxiv_id = gr.Textbox(selected_paper['arxiv_id'], visible=False)
@@ -54,7 +55,7 @@ with gr.Blocks(css="constants/styles.css", theme=gr.themes.Soft()) as demo:
 
     gr.Markdown("# Let's explore papers with auto generated Q&As")
     
-    with gr.Column(elem_id="control-panel", elem_classes=["group"]):
+    with gr.Column(elem_id="control-panel", elem_classes=["group"], visible=visible):
         with gr.Column():
             with gr.Row():
                 year_dd = gr.Dropdown(sorted_year, value=last_year, label="Year", interactive=True, filterable=False)    
@@ -82,7 +83,7 @@ with gr.Blocks(css="constants/styles.css", theme=gr.themes.Soft()) as demo:
             search_r9 = gr.Button(visible=False, elem_id="search_r9", elem_classes=["no-radius"])
             search_r10 = gr.Button(visible=False, elem_id="search_r10", elem_classes=["no-radius"])
 
-    with gr.Column(scale=7):
+    with gr.Column(scale=7, visible=visible):
         title = gr.Markdown(f"# {selected_paper['title']}", elem_classes=["markdown-center"])
         # with gr.Row():
         with gr.Row():
@@ -150,21 +151,21 @@ with gr.Blocks(css="constants/styles.css", theme=gr.themes.Soft()) as demo:
                     breath_q_eli5_2 = gr.Markdown(f"↪ **(ELI5)** {selected_paper['2_additional_breath_q:answers:eli5']}", elem_classes=["small-font"])
                     breath_q_expert_2 = gr.Markdown(f"↪ **(Technical)** {selected_paper['2_additional_breath_q:answers:expert']}", visible=False, elem_classes=["small-font"])
 
-        gr.Markdown("## Request any arXiv ids")
-        arxiv_queue = gr.Dataframe(
-            headers=["Requested arXiv IDs"], col_count=(1, "fixed"),
-            value=requested_arxiv_ids_df,
-            datatype=["str"],
-            interactive=False,
-        )
-
-        arxiv_id_enter = gr.Textbox(placeholder="Enter comma separated arXiv IDs...", elem_classes=["textbox-no-label"])
-        arxiv_id_enter.submit(
-            add_arxiv_ids_to_queue,
-            [arxiv_queue, arxiv_id_enter],
-            [arxiv_queue, arxiv_id_enter],
-            concurrency_limit=20,
-        )
+    gr.Markdown("## Request any arXiv ids")
+    arxiv_queue = gr.Dataframe(
+        headers=["Requested arXiv IDs"], col_count=(1, "fixed"),
+        value=requested_arxiv_ids_df,
+        datatype=["str"],
+        interactive=False,
+    )
+
+    arxiv_id_enter = gr.Textbox(placeholder="Enter comma separated arXiv IDs...", elem_classes=["textbox-no-label"])
+    arxiv_id_enter.submit(
+        add_arxiv_ids_to_queue,
+        [arxiv_queue, arxiv_id_enter],
+        [arxiv_queue, arxiv_id_enter],
+        concurrency_limit=20,
+    )
 
     gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
 
@@ -390,7 +391,7 @@ scheduler.add_job(
     ],
     start_date=start_date
 )
-# scheduler.start()
+scheduler.start()
 
 demo.queue(
     default_concurrency_limit=20,

init.py

@@ -2,10 +2,12 @@ import os
 import copy
 import datasets
 import pandas as pd
+from datasets import Dataset
 from collections import defaultdict
 
 from datetime import datetime, timedelta
 from background import process_arxiv_ids
+from utils import create_hf_hub
 from apscheduler.schedulers.background import BackgroundScheduler
 
 def _count_nans(row):
@@ -79,6 +81,19 @@ def update_dataframe(request_data_repo_id):
     request_ds = datasets.load_dataset(request_data_repo_id)
     return _initialize_requested_arxiv_ids(request_ds)
 
+def initialize_repos(
+    source_data_repo_id, request_data_repo_id, hf_token
+):
+    if create_hf_hub(source_data_repo_id, hf_token) is False:
+        print(f"{source_data_repo_id} repository already exists")
+
+    if create_hf_hub(request_data_repo_id, hf_token) is False:
+        print(f"{request_data_repo_id} repository already exists")
+    else:
+        df = pd.DataFrame(data={"Requested arXiv IDs": [["top"]]})
+        ds = Dataset.from_df(df)
+        ds.push_to_hub(request_data_repo_id, token=hf_token)
+
 def get_secrets():
     global gemini_api_key
     global hf_token

utils.py

@@ -4,6 +4,15 @@ import pandas as pd
 from huggingface_hub import create_repo
 from huggingface_hub.utils import HfHubHTTPError
 
+def create_hf_hub(
+    repo_id, hf_token
+):
+    try:
+        create_repo(repo_id, repo_type="dataset", token=hf_token)
+    except HfHubHTTPError as e:
+        return False
+    return True
+
 def push_to_hf_hub(
 	ds, repo_id, hf_token, append=True
 ):