Update app.py

app.py

@@ -34,9 +34,6 @@ def insert_or_fetch_embeddings(index_name):
 # Initialize or fetch Pinecone vector store
 vector_store = insert_or_fetch_embeddings(index_name)
 
-# Define the metadata for filtering
-# metadata = {'source': '/Users/cheynelevesseur/Desktop/Python_Code/Projects/LLM/Intensifying Literacy Instruction - Essential Practices (NATIONAL).pdf'}
-
 # calculate embedding cost using tiktoken
 def calculate_embedding_cost(text):
     import tiktoken
@@ -56,7 +53,7 @@ def ask_with_memory(vector_store, query, chat_history=[]):
     # The retriever is created with metadata filter directly in search_kwargs
     # retriever = vector_store.as_retriever(search_type='similarity', search_kwargs={'k': 3, 'filter': {'source': {'$eq': 'https://mimtsstac.org/sites/default/files/session-documents/Intensifying%20Literacy%20Instruction%20-%20Essential%20Practices%20%28NATIONAL%29.pdf'}}})
     retriever = vector_store.as_retriever(search_type='similarity', search_kwargs={'k': 3, 'filter': {'source':'https://mimtsstac.org/sites/default/files/session-documents/Intensifying%20Literacy%20Instruction%20-%20Essential%20Practices%20%28NATIONAL%29.pdf'}})
-
+    
     chain= ConversationalRetrievalChain.from_llm(llm, retriever)
     result = chain({'question': query, 'chat_history': st.session_state['history']})
     # Append to chat history as a dictionary