Update app.py

app.py

@@ -19,10 +19,8 @@ llm_groq = ChatGroq(
 st.set_page_config(page_title="DocDynamo", layout="wide")
 st.title("DocDynamo🚀")
 
-# Upload PDF file
 uploaded_file = st.file_uploader("Please upload a PDF file to begin!", type="pdf")
 
-# Sidebar content
 st.sidebar.title("DocDynamo By OpenRAG")
 st.sidebar.markdown(
     """
@@ -53,7 +51,6 @@ Experience the future of PDF interaction with DocDynamo. Welcome to a new era of
 )
 
 if uploaded_file:
-    # Inform the user that processing has started
     with st.spinner(f"Processing `{uploaded_file.name}`..."):
         # Read the PDF file
         pdf = PyPDF2.PdfReader(uploaded_file)
@@ -61,18 +58,18 @@ if uploaded_file:
         for page in pdf.pages:
             pdf_text += page.extract_text()
 
-        # Split the text into chunks
+        
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=1200, chunk_overlap=50)
         texts = text_splitter.split_text(pdf_text)
 
-        # Create a Chroma vector store
+        
         embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={'device': "cpu"})
         docsearch = Chroma.from_texts(texts, embeddings)
 
-        # Initialize message history for conversation
+    
         message_history = ChatMessageHistory()
 
-        # Memory for conversational context
+
         memory = ConversationBufferMemory(
             memory_key="chat_history",
             output_key="answer",
@@ -80,7 +77,7 @@ if uploaded_file:
             return_messages=True,
         )
 
-        # Create a chain that uses the Chroma vector store
+    
         chain = ConversationalRetrievalChain.from_llm(
             llm=llm_groq,
             chain_type="stuff",
@@ -94,14 +91,13 @@ if uploaded_file:
     user_input = st.text_input("Ask a question about the PDF:")
 
     if user_input:
-        # Call the chain with user's message content
         res = chain.invoke(user_input)
         answer = res["answer"]
         source_documents = res["source_documents"]
 
-        text_elements = []  # Initialize list to store text elements
+        text_elements = [] 
 
-        # Process source documents if available
+    
         if source_documents:
             for source_doc in source_documents:
                 text_elements.append(source_doc.page_content)