Update app.py

app.py

@@ -97,10 +97,8 @@ def retrieve_context(query, k=3):
 
 # Main application layout
 if 'DEEPSEEK_API_KEY' in st.session_state:
-    # Create a two-column layout
-    col1, col2 = st.columns([3, 1])
-    
-    with col2:
+    # Create a sidebar for document upload and settings
+    with st.sidebar:
         st.header("Document Upload")
         uploaded_files = st.file_uploader(
             "Upload your documents", 
@@ -128,17 +126,37 @@ if 'DEEPSEEK_API_KEY' in st.session_state:
         if st.button("Clear Knowledge Base"):
             st.session_state.vectorstore = None
             st.success("Knowledge base cleared!")
+        
+        st.header("About")
+        st.markdown("""
+        This RAG chatbot uses:
+        - 🦜 LangChain for memory and document processing
+        - 🔍 FAISS for vector storage and retrieval
+        - 🧠 HuggingFace for lightweight embeddings (paraphrase-MiniLM-L3-v2)
+        - 🤖 DeepSeek API for AI responses
+        - 🖥️ Streamlit for the web interface
+        
+        The chatbot can:
+        - Upload and process PDF and text documents
+        - Retrieve relevant information from documents
+        - Generate informed responses using your documents
+        - Maintain conversation context
+        """)
     
-    with col1:
+    # Main chat area - create a container for the chat history
+    chat_container = st.container()
+    with chat_container:
         # Display chat history
         for message in st.session_state.chat_history:
             with st.chat_message(message["role"]):
                 st.write(message["content"])
 
-# Move chat_input outside of any container
+# IMPORTANT: Place chat_input outside of any container and if block
+# This must be at the main page level
 user_input = st.chat_input("Type your message here...")
 
-if user_input:
+# Handle user input - but only process if API key is available
+if user_input and 'DEEPSEEK_API_KEY' in st.session_state:
     # Add user message to chat history
     st.session_state.chat_history.append({"role": "user", "content": user_input})
     
@@ -176,22 +194,4 @@ if user_input:
                 st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
             
             except Exception as e:
-                st.error(f"Error: {str(e)}")
-
-# Sidebar with info
-with st.sidebar:
-    st.header("About")
-    st.markdown("""
-    This RAG chatbot uses:
-    - 🦜 LangChain for memory and document processing
-    - 🔍 FAISS for vector storage and retrieval
-    - 🧠 HuggingFace for lightweight embeddings (paraphrase-MiniLM-L3-v2)
-    - 🤖 DeepSeek API for AI responses
-    - 🖥️ Streamlit for the web interface
-    
-    The chatbot can:
-    - Upload and process PDF and text documents
-    - Retrieve relevant information from documents
-    - Generate informed responses using your documents
-    - Maintain conversation context
-    """)
+                st.error(f"Error: {str(e)}")