add deletion of csv file and index created during a session

app.py

@@ -2,6 +2,7 @@ import logging
 import os
 import gradio as gr
 import pandas as pd
+from pinecone import Pinecone
 from utils import get_zotero_ids, get_arxiv_papers, get_hf_embeddings, upload_to_pinecone, get_new_papers, recommend_papers
 
 HF_API_KEY = os.getenv('HF_API_KEY')
@@ -94,4 +95,16 @@ with gr.Blocks() as demo:
 
         return results
 
+file_path = 'arxiv-scrape.csv'
+if os.path.exists(file_path):
+    os.remove(file_path)
+    logging.info(f"{file_path} has been deleted. Delete this part of the code if you want to persist recommended papers.")
+
+api_key = os.getenv('PINECONE_API_KEY')
+index = os.getenv('INDEX_NAME')
+pc = Pinecone(api_key = api_key)
+if index in pc.list_indexes().names():
+    pc.delete_index(index)
+    logging.info(f"{index} index has been deleted from the vectordb. Delete this part of the code if you want to persist recommended papers.")
+
 demo.launch(share = True)

utils.py

@@ -60,7 +60,7 @@ def get_hf_embeddings(api_key, df):
     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')
+    print(str(response.status_code) + 'This part needs an update, causing KeyError 0 ')
     if response.status_code == 503:
         response = requests.post(API_URL, headers=headers, json={"inputs": title_abs, "wait_for_model": True})
 
@@ -82,6 +82,7 @@ def upload_to_pinecone(api_key, index, namespace, embeddings, dim, df):
         name=index,
         dimension=dim,
         metric="cosine",
+        deletion_protection="disabled",
         spec=ServerlessSpec(
             cloud='aws', 
             region='us-east-1'