Update utils.py

utils.py

@@ -6,8 +6,8 @@ import asyncio
 from langchain.document_loaders.sitemap import SitemapLoader
 
 
-#Function to fetch data from website
-#https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/sitemap
+#Step 1: Loading data from website
+
 def get_website_data(sitemap_url):
 
     loop = asyncio.new_event_loop()
@@ -20,7 +20,7 @@ def get_website_data(sitemap_url):
 
     return docs
 
-#Function to split data into smaller chunks
+#Step 2:Split data into smaller chunks
 def split_data(docs):
 
     text_splitter = RecursiveCharacterTextSplitter(
@@ -32,13 +32,13 @@ def split_data(docs):
     docs_chunks = text_splitter.split_documents(docs)
     return docs_chunks
 
-#Function to create embeddings instance
+#Step3: Embedding this Function to create embeddings instance
 def create_embeddings():
 
     embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
     return embeddings
 
-#Function to push data to Pinecone
+#Step 3: Push data to Pinecone
 def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings,docs):
 
     pinecone.init(
@@ -50,7 +50,7 @@ def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,em
     index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
     return index
 
-#Function to pull index data from Pinecone
+#Step 4 & 5 pull index data from Pinecone
 def pull_from_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings):
 
     pinecone.init(
@@ -63,7 +63,7 @@ def pull_from_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,
     index = Pinecone.from_existing_index(index_name, embeddings)
     return index
 
-#This function will help us in fetching the top relevent documents from our vector store - Pinecone Index
+#Step 4 & 5 Fetch the top relevent documents from our vector store - Pinecone Index
 def get_similar_docs(index,query,k=2):
 
     similar_docs = index.similarity_search(query, k=k)