Update app.py

app.py

@@ -28,10 +28,18 @@ if "vector_store" not in st.session_state:
     st.session_state.vector_store = None
 if "documents" not in st.session_state:
     st.session_state.documents = None
-
-# Step 1: Choose PDF Source
-pdf_source = st.radio("Upload or provide a link to a PDF:", ["Upload a PDF file", "Enter a PDF URL"], index=0, horizontal=True)
-
+if "processed" not in st.session_state:
+    st.session_state.processed = False  # Prevent redundant processing
+
+# Step 1: Choose PDF Source (Horizontal radio buttons)
+pdf_source = st.radio(
+    "Upload or provide a link to a PDF:", 
+    ["Upload a PDF file", "Enter a PDF URL"], 
+    index=0, 
+    horizontal=True
+)
+
+pdf_path = None
 if pdf_source == "Upload a PDF file":
     uploaded_file = st.file_uploader("Upload your PDF file", type="pdf")
     if uploaded_file:
@@ -39,6 +47,7 @@ if pdf_source == "Upload a PDF file":
         with open(pdf_path, "wb") as f:
             f.write(uploaded_file.getbuffer())
         st.success("✅ PDF Uploaded Successfully!")
+        st.session_state.processed = False  # Reset processing
 
 elif pdf_source == "Enter a PDF URL":
     pdf_url = st.text_input("Enter PDF URL:")
@@ -51,17 +60,12 @@ elif pdf_source == "Enter a PDF URL":
                     with open(pdf_path, "wb") as f:
                         f.write(response.content)
                     st.success("✅ PDF Downloaded Successfully!")
+                    st.session_state.processed = False  # Reset processing
                 else:
                     st.error("❌ Failed to download PDF. Check the URL.")
-                    pdf_path = None
-            except Exception as e:
-                st.error(f"Error downloading PDF: {e}")
-                pdf_path = None
-else:
-    pdf_path = None
 
 # Step 2: Process PDF and Create Vector Store (Only if Not Processed)
-if pdf_path and st.session_state.vector_store is None:
+if pdf_path and not st.session_state.processed:
     with st.spinner("Loading and processing PDF..."):
         loader = PDFPlumberLoader(pdf_path)
         docs = loader.load()
@@ -73,7 +77,7 @@ if pdf_path and st.session_state.vector_store is None:
             embedding_model = HuggingFaceEmbeddings(model_name=model_name, model_kwargs={'device': 'cpu'})
             text_splitter = SemanticChunker(embedding_model)
             documents = text_splitter.split_documents(docs)
-            st.session_state.documents = documents  # Store in session state
+            st.session_state.documents = documents
             st.success(f"✅ **Document Chunked!** Total Chunks: {len(documents)}")
 
         # Step 4: Setup Vectorstore
@@ -85,7 +89,8 @@ if pdf_path and st.session_state.vector_store is None:
             )
             vector_store.add_documents(documents)
             num_documents = len(vector_store.get()["documents"])
-            st.session_state.vector_store = vector_store  # Store vector store in session state
+            st.session_state.vector_store = vector_store  # Store in session state
+            st.session_state.processed = True  # Mark as processed
             st.success(f"✅ **Vector Store Created!** Total documents stored: {num_documents}")
 
 # Step 5: Query Input (Only allow if vector store exists)
@@ -137,13 +142,5 @@ if st.session_state.vector_store:
         st.subheader("🟥 RAG Final Response")
         st.success(final_response['final_response'])
 
-        # Step 10: Display Workflow Breakdown
-        st.subheader("🔍 **Workflow Breakdown:**")
-        st.json({
-            "Context Relevancy Evaluation": relevancy_response["relevancy_response"],
-            "Relevant Contexts": relevant_response["context_number"],
-            "Extracted Contexts": final_contexts["relevant_contexts"],
-            "Final Answer": final_response["final_response"]
-        })
 else:
     st.warning("📄 Please upload or provide a PDF URL first.")