From 23291cac9d93854baf077998557281471bd862b3 Mon Sep 17 00:00:00 2001
From: Karan Kumar Bhagat <92136711+karandomguy@users.noreply.github.com>
Date: Thu, 4 Sep 2025 11:17:33 +0530
Subject: [PATCH] Update document_processing.py

---
 document_processing.py | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/document_processing.py b/document_processing.py
index 3d89845..366f8fa 100644
--- a/document_processing.py
+++ b/document_processing.py
@@ -5,11 +5,6 @@
 import re
 import pandas as pd
 from sentence_transformers import SentenceTransformer
-import chromadb
-from dotenv import load_dotenv
-import requests
-from bs4 import BeautifulSoup
-import time
 
 load_dotenv()
 
@@ -65,8 +60,6 @@ def load_documents(self, filename: str = "medical_documents.json") -> List[Dict[
     
     def save_documents(self, documents: List[Dict[str, Any]], filename: str = "medical_documents.json"):
         """Save documents to JSON file"""
-        os.makedirs(self.data_dir, exist_ok=True)
-        filepath = os.path.join(self.data_dir, filename)
         with open(filepath, 'w') as f:
             json.dump(documents, f, indent=2)
         print(f"Saved {len(documents)} documents to {filepath}")
@@ -244,4 +237,4 @@ def run_pipeline(self, json_file=None, urls=None):
         medical_urls = []
     
     count = processor.run_pipeline(urls=medical_urls)
-    print(f"Successfully processed documents into {count} chunks in the vector database")
\ No newline at end of file
+    print(f"Successfully processed documents into {count} chunks in the vector database")