charlieoneill commited on
Commit
41fb331
1 Parent(s): 4c2dac4

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +40 -2
app.py CHANGED
@@ -373,14 +373,45 @@ def create_interface():
373
  for doc_id in topk_doc_ids:
374
  metadata = df_metadata[df_metadata['arxiv_id'] == doc_id].iloc[0]
375
  title = metadata['title'].replace('[', '').replace(']', '')
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  search_results.append([
377
- title,
378
  int(metadata['citation_count']),
379
  int(metadata['year'])
380
  ])
381
 
382
  return search_results, all_values, all_indices
383
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  @gr.render(inputs=[input_text, search_results_state, feature_values_state, feature_indices_state, manually_added_features_state, subject])
385
  def show_components(text, search_results, feature_values, feature_indices, manually_added_features, current_subject):
386
  if len(text) == 0:
@@ -402,10 +433,17 @@ def create_interface():
402
 
403
  with gr.Row():
404
  with gr.Column(scale=2):
 
 
 
 
 
405
  df = gr.Dataframe(
406
  headers=["Title", "Citation Count", "Year"],
407
  value=search_results,
408
- label="Top 10 Search Results"
 
 
409
  )
410
 
411
  feature_search = gr.Textbox(label="Search Feature Labels")
 
373
  for doc_id in topk_doc_ids:
374
  metadata = df_metadata[df_metadata['arxiv_id'] == doc_id].iloc[0]
375
  title = metadata['title'].replace('[', '').replace(']', '')
376
+ # Remove single quotes from title
377
+ title = title.replace("'", "")
378
+
379
+ url_id = doc_id.replace('_arXiv.txt', '')
380
+ if 'astro-ph' in url_id:
381
+ url_id = url_id.split('astro-ph')[1]
382
+ url = f"https://arxiv.org/abs/astro-ph/{url_id}"
383
+ else:
384
+ # Create the clickable link based on the doc_id
385
+ if '.' in doc_id:
386
+ url = f"https://arxiv.org/abs/{doc_id.replace('_arXiv.txt', '')}"
387
+ else:
388
+ url = f"https://arxiv.org/abs/hep-ph/{doc_id.replace('_arXiv.txt', '')}"
389
+
390
+ linked_title = f"[{title}]({url})"
391
+
392
  search_results.append([
393
+ linked_title,
394
  int(metadata['citation_count']),
395
  int(metadata['year'])
396
  ])
397
 
398
  return search_results, all_values, all_indices
399
 
400
+
401
+
402
+ # # Prepare search results
403
+ # search_results = []
404
+ # for doc_id in topk_doc_ids:
405
+ # metadata = df_metadata[df_metadata['arxiv_id'] == doc_id].iloc[0]
406
+ # title = metadata['title'].replace('[', '').replace(']', '')
407
+ # search_results.append([
408
+ # title,
409
+ # int(metadata['citation_count']),
410
+ # int(metadata['year'])
411
+ # ])
412
+
413
+ # return search_results, all_values, all_indices
414
+
415
  @gr.render(inputs=[input_text, search_results_state, feature_values_state, feature_indices_state, manually_added_features_state, subject])
416
  def show_components(text, search_results, feature_values, feature_indices, manually_added_features, current_subject):
417
  if len(text) == 0:
 
433
 
434
  with gr.Row():
435
  with gr.Column(scale=2):
436
+ # df = gr.Dataframe(
437
+ # headers=["Title", "Citation Count", "Year"],
438
+ # value=search_results,
439
+ # label="Top 10 Search Results"
440
+ # )
441
  df = gr.Dataframe(
442
  headers=["Title", "Citation Count", "Year"],
443
  value=search_results,
444
+ label="Top 10 Search Results",
445
+ datatype=["markdown", "number", "number"], # Add this line
446
+ wrap=True # Add this line to ensure long titles don't get cut off
447
  )
448
 
449
  feature_search = gr.Textbox(label="Search Feature Labels")