added refactor and lint format fixes

embedchain/config/InitConfig.py

@@ -62,6 +62,7 @@ def _set_db_to_default(self):
  Sets database to default (`ChromaDb`).
  """
  from embedchain.vectordb.chroma_db import ChromaDB
+
  self.db = ChromaDB(ef=self.ef, host=self.host, port=self.port)
 
  def _setup_logging(self, debug_level):

embedchain/loaders/site_map.py

@@ -7,27 +7,18 @@
 class SitemapLoader:
  def load_data(self, sitemap_url):
  """
- This method takes a sitemap url as input and retrieves
- all the urls to use the WebPageLoader to load content
+ This method takes a sitemap URL as input and retrieves
+ all the URLs to use the WebPageLoader to load content
  of each page.
  """
  output = []
  web_page_loader = WebPageLoader()
-
  response = requests.get(sitemap_url)
-
- if response.status_code == 200:
- soup = BeautifulSoup(response.text, features="xml")
- links = [link.text for link in soup.find_all("loc")]
-
- for link in links:
- each_load_data = web_page_loader.load_data(link)
- # WebPageLoader returns a list with single element
- # which is extracted and appended to the output list
- # containing data for all pages
- output.append(each_load_data[0])
-
- return output
-
- else:
- raise response.raise_for_status()
+ response.raise_for_status()
+
+ soup = BeautifulSoup(response.text, "xml")
+ links = [link.text for link in soup.find_all("loc")]
+ for link in links:
+ each_load_data = web_page_loader.load_data(link)
+ output.append(each_load_data)
+ return [data[0] for data in output]

embedchain/vectordb/chroma_db.py

@@ -1,5 +1,5 @@
-import os
 import logging
+import os
 
 import chromadb
 from chromadb.utils import embedding_functions