update options input for huggingface and update exception handling for app.py

app.py

@@ -43,6 +43,12 @@ def reset_project():
  logging.info(f"{index} index has been deleted from the vectordb. Delete reset_project() if you want to persist recommended papers.")
  return f"{file_path} has been deleted.<br />{index} index has been deleted from the vectordb.<br />"
 
+def reset_csv():
+ file_path = 'arxiv-scrape.csv'
+ if os.path.exists(file_path):
+ os.remove(file_path)
+ logging.info(f"{file_path} has been deleted. Delete reset_project() if you want to persist recommended papers.")
+
 with gr.Blocks() as demo:
 
  zotero_api_key = gr.Textbox(label="Zotero API Key")
@@ -87,13 +93,8 @@ with gr.Blocks() as demo:
  ids = get_zotero_ids(zotero_api_key, zotero_library_id, zotero_tag)
 
  df = get_arxiv_papers(ids)
- try:
- embeddings, dim = get_hf_embeddings(hf_api_key, df)
- except KeyError as e:
- print(e)
- print('\n Resetting project...')
- reset_project()
- exit()
+
+ embeddings, dim = get_hf_embeddings(hf_api_key, df)
 
  feedback = upload_to_pinecone(pinecone_api_key, index_name, namespace_name, embeddings, dim, df)
 

utils.py

@@ -59,10 +59,10 @@ def get_hf_embeddings(api_key, df):
  API_URL = "https://api-inference.huggingface.co/models/malteos/scincl"
  headers = {"Authorization": f"Bearer {api_key}"}
 
- response = requests.post(API_URL, headers=headers, json={"inputs": title_abs, "wait_for_model": False})
- print(str(response.status_code) + 'This part needs an update, causing KeyError 0 ')
+ response = requests.post(API_URL, headers=headers, json={"inputs": title_abs, "options": {"wait_for_model": False}})
+ 
  if response.status_code == 503:
- response = requests.post(API_URL, headers=headers, json={"inputs": title_abs, "wait_for_model": True})
+ response = requests.post(API_URL, headers=headers, json={"inputs": title_abs, "options": {"wait_for_model": True}})
 
  embeddings = response.json()
 
@@ -102,9 +102,9 @@ def get_new_papers(df):
  if df.empty:
  return 'No New Papers Found'
  else:
- df_main = pd.concat([df_main, df], ignore_index= True)
- df_main.drop_duplicates(inplace= True)
- df_main.to_csv('arxiv-scrape.csv', index = False)
+ # df_main = pd.concat([df_main, df], ignore_index= True) #persistence of recommended paper removed for demo
+ # df_main.drop_duplicates(inplace= True)
+ # df_main.to_csv('arxiv-scrape.csv', index = False)
  return df
 
 def recommend_papers(api_key, index, namespace, embeddings, df, threshold):