Update utils.py

utils.py

@@ -51,11 +51,11 @@ def create_embeddings_load_data():
 
 
 #Function to push data to Vector Store - Pinecone here
-def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings,docs):
+def push_to_pinecone(PINECONE_PROJECT_ID,PINECONE_REGION,pinecone_index_name,embeddings,docs):
 
     pinecone.init(
-    api_key=pinecone_apikey,
-    environment=pinecone_environment
+    api_key=PINECONE_PROJECT_ID,
+    environment=PINECONE_REGION
     )
     
     Pinecone.from_documents(docs, embeddings, index_name=pinecone_index_name)
@@ -63,15 +63,15 @@ def push_to_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,em
 
 
 #Function to pull infrmation from Vector Store - Pinecone here
-def pull_from_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings):
+def pull_from_pinecone(PINECONE_PROJECT_ID,PINECONE_REGION,pinecone_index_name,embeddings):
     # For some of the regions allocated in pinecone which are on free tier, the data takes upto 10secs for it to available for filtering
     #so I have introduced 20secs here, if its working for you without this delay, you can remove it :)
     #https://docs.pinecone.io/docs/starter-environment
     print("20secs delay...")
     time.sleep(20)
     pinecone.init(
-    api_key=pinecone_apikey,
-    environment=pinecone_environment
+    api_key=PINECONE_PROJECT_ID,
+    environment=PINECONE_REGION
     )
 
     index_name = pinecone_index_name
@@ -82,16 +82,16 @@ def pull_from_pinecone(pinecone_apikey,pinecone_environment,pinecone_index_name,
 
 
 #Function to help us get relavant documents from vector store - based on user input
-def similar_docs(query,k,pinecone_apikey,pinecone_environment,pinecone_index_name,embeddings,unique_id):
+def similar_docs(query,k,PINECONE_PROJECT_ID,PINECONE_REGION,pinecone_index_name,embeddings,unique_id):
 
     pinecone.init(
-    api_key=pinecone_apikey,
-    environment=pinecone_environment
+    api_key=PINECONE_PROJECT_ID,
+    environment=PINECONE_REGION
     )
 
     index_name = pinecone_index_name
 
-    index = pull_from_pinecone(pinecone_apikey,pinecone_environment,index_name,embeddings)
+    index = pull_from_pinecone(PINECONE_PROJECT_ID,PINECONE_REGION,index_name,embeddings)
     similar_docs = index.similarity_search_with_score(query, int(k),{"unique_id":unique_id})
     #print(similar_docs)
     return similar_docs