Update app.py

app.py

@@ -33,6 +33,8 @@ if "history" not in st.session_state:
     st.session_state.history = []
 if "authenticated" not in st.session_state:
     st.session_state.authenticated = False
+if "uploaded_files" not in st.session_state:
+    st.session_state.uploaded_files = []
 
 # File processing logic
 def process_input(input_data):
@@ -44,7 +46,8 @@ def process_input(input_data):
     status.text("Reading file...")
     progress_bar.progress(0.20)
     
-    file_extension = input_data.name.lower().split('.')[-1]
+    file_name = input_data.name
+    file_extension = file_name.lower().split('.')[-1]
     documents = ""
     
     # Step 2: Extract text based on file type
@@ -78,7 +81,7 @@ def process_input(input_data):
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
     texts = text_splitter.split_text(documents)
     
-    # Step 4: Create embeddings
+    # Step 4: Create or update embeddings
     status.text("Creating embeddings...")
     progress_bar.progress(0.80)
     
@@ -87,18 +90,21 @@ def process_input(input_data):
         model_kwargs={'device': 'cpu'}
     )
     
-    # Step 5: Initialize FAISS vector store
-    status.text("Building vector store...")
+    # Step 5: Initialize or append to FAISS vector store
+    status.text("Building or updating vector store...")
     progress_bar.progress(1.0)
     
-    dimension = len(hf_embeddings.embed_query("test"))
-    index = faiss.IndexFlatL2(dimension)
-    vector_store = FAISS(
-        embedding_function=hf_embeddings,
-        index=index,
-        docstore=InMemoryDocstore({}),
-        index_to_docstore_id={}
-    )
+    if st.session_state.vectorstore is None:
+        dimension = len(hf_embeddings.embed_query("test"))
+        index = faiss.IndexFlatL2(dimension)
+        vector_store = FAISS(
+            embedding_function=hf_embeddings,
+            index=index,
+            docstore=InMemoryDocstore({}),
+            index_to_docstore_id={}
+        )
+    else:
+        vector_store = st.session_state.vectorstore
     
     # Add texts to vector store
     uuids = [str(uuid.uuid4()) for _ in texts]
@@ -106,6 +112,7 @@ def process_input(input_data):
     
     # Complete processing
     status.text("Processing complete!")
+    st.session_state.uploaded_files.append(file_name)
     
     return vector_store
 
@@ -143,7 +150,7 @@ def answer_question(vectorstore, query):
     except requests.exceptions.HTTPError as e:
         raise RuntimeError(f"Error querying LLM: {str(e)}. Please try again or check model endpoint.")
 
-# Sidebar with BSNL logo and authentication
+# Sidebar with BSNL logo, authentication, and controls
 with st.sidebar:
     try:
         st.image("bsnl_logo.png", width=200)
@@ -153,10 +160,10 @@ with st.sidebar:
     st.header("RAG Control Panel")
     api_key_input = st.text_input("Enter RAG Access Key", type="password")
     
-    # Blue authenticate button style
+    # Blue button styles
     st.markdown("""
         <style>
-        .auth-button button {
+        .auth-button button, .delete-button button {
             background-color: #007BFF !important;
             color: white !important;
             font-weight: bold;
@@ -166,13 +173,14 @@ with st.sidebar:
             transition: all 0.3s ease;
             width: 100%;
         }
-        .auth-button button:hover {
+        .auth-button button:hover, .delete-button button:hover {
             background-color: #0056b3 !important;
             transform: scale(1.05);
         }
         </style>
     """, unsafe_allow_html=True)
     
+    # Authenticate button
     with st.container():
         st.markdown('<div class="auth-button">', unsafe_allow_html=True)
         if st.button("Authenticate"):
@@ -184,21 +192,40 @@ with st.sidebar:
         st.markdown('</div>', unsafe_allow_html=True)
     
     if st.session_state.authenticated:
+        # Display uploaded files
+        if st.session_state.uploaded_files:
+            st.subheader("Uploaded Files")
+            for file_name in st.session_state.uploaded_files:
+                st.write(f"- {file_name}")
+        
+        # File uploader
         input_data = st.file_uploader("Upload a file (PDF, XLS/XLSX, DOC/DOCX, TXT)", type=["pdf", "xls", "xlsx", "doc", "docx", "txt"])
         
         if st.button("Process File") and input_data is not None:
-            try:
-                vector_store = process_input(input_data)
-                st.session_state.vectorstore = vector_store
-                st.success("File processed successfully. You can now ask questions.")
-            except PermissionError as e:
-                st.error(f"File upload failed: Permission error - {str(e)}. Check file system access.")
-            except OSError as e:
-                st.error(f"File upload failed: OS error - {str(e)}. Check server configuration.")
-            except ValueError as e:
-                st.error(f"File upload failed: {str(e)} (Invalid file format).")
-            except Exception as e:
-                st.error(f"File upload failed: {str(e)} (Exception type: {type(e).__name__}). Please try again or check server logs.")
+            if input_data.name in st.session_state.uploaded_files:
+                st.warning(f"File '{input_data.name}' has already been processed. Please upload a different file or delete the vector store.")
+            else:
+                try:
+                    vector_store = process_input(input_data)
+                    st.session_state.vectorstore = vector_store
+                    st.success("File processed successfully. You can now ask questions.")
+                except PermissionError as e:
+                    st.error(f"File upload failed: Permission error - {str(e)}. Check file system access.")
+                except OSError as e:
+                    st.error(f"File upload failed: OS error - {str(e)}. Check server configuration.")
+                except ValueError as e:
+                    st.error(f"File upload failed: {str(e)} (Invalid file format).")
+                except Exception as e:
+                    st.error(f"File upload failed: {str(e)} (Exception type: {type(e).__name__}). Please try again or check server logs.")
+        
+        # Delete vector store button
+        if st.session_state.vectorstore is not None:
+            st.markdown('<div class="delete-button">', unsafe_allow_html=True)
+            if st.button("Delete Vector Store"):
+                st.session_state.vectorstore = None
+                st.session_state.uploaded_files = []
+                st.success("Vector store deleted successfully.")
+            st.markdown('</div>', unsafe_allow_html=True)
     
     st.subheader("Chat History")
     for i, (q, a) in enumerate(st.session_state.history):
@@ -246,7 +273,7 @@ def main():
     """, unsafe_allow_html=True)
     
     st.title("RAG Q&A App with Mistral AI")
-    st.markdown("Welcome to the BSNL RAG App! Upload a PDF, XLS/XLSX, DOC/DOCX, or TXT file and ask questions.", unsafe_allow_html=True)
+    st.markdown("Welcome to the BSNL RAG App! Upload a PDF, XLS/XLSX, DOC/DOCX, or TXT file and ask questions. Files are stored in the vector store until explicitly deleted.", unsafe_allow_html=True)
     
     if not st.session_state.authenticated:
         st.warning("Please authenticate using the sidebar.")