Update app.py

app.py

@@ -24,7 +24,7 @@ rag_llm.verbose = True
 # Clear ChromaDB cache to fix tenant issue
 chromadb.api.client.SharedSystemClient.clear_system_cache()
 
-st.title("Blah")
+st.title("Blah - 1")
 
 # **Initialize session state variables**
 if "pdf_path" not in st.session_state:
@@ -56,7 +56,7 @@ if pdf_source == "Upload a PDF file":
         st.session_state.vector_created = False
 
 elif pdf_source == "Enter a PDF URL":
-    pdf_url = st.text_input("Enter PDF URL:", value="https://arxiv.org/pdf/2406.06998")
+    pdf_url = st.text_input("Enter PDF URL:")
     if pdf_url and not st.session_state.get("pdf_loaded", False):
         with st.spinner("Downloading PDF..."):
             try:
@@ -74,7 +74,7 @@ elif pdf_source == "Enter a PDF URL":
             except Exception as e:
                 st.error(f"Error downloading PDF: {e}")
 
-# Step 2: Process PDF
+# Step 2: Process PDF 
 if st.session_state.pdf_path and not st.session_state.get("pdf_loaded", False):
     with st.spinner("Loading and processing PDF..."):
         loader = PDFPlumberLoader(st.session_state.pdf_path)
@@ -83,7 +83,7 @@ if st.session_state.pdf_path and not st.session_state.get("pdf_loaded", False):
         st.session_state.pdf_loaded = True  # ✅ Prevent re-loading
         st.success(f"✅ **PDF Loaded!** Total Pages: {len(docs)}")
 
-# Step 3: Chunking
+# Step 3: Chunking 
 if st.session_state.get("pdf_loaded", False) and not st.session_state.get("chunked", False):
     with st.spinner("Chunking the document..."):
         model_name = "nomic-ai/modernbert-embed-base"
@@ -94,12 +94,11 @@ if st.session_state.get("pdf_loaded", False) and not st.session_state.get("chunk
         st.session_state.chunked = True  # ✅ Prevent re-chunking
         st.success(f"✅ **Document Chunked!** Total Chunks: {len(documents)}")
 
-# Step 4: Setup Vectorstore
+# Step 4: Setup Vectorstore 
 if st.session_state.get("chunked", False) and not st.session_state.get("vector_created", False):
     with st.spinner("Creating vector store..."):
-        model_name = "nomic-ai/modernbert-embed-base"
-        embedding_model = HuggingFaceEmbeddings(model_name=model_name, model_kwargs={'device': 'cpu'}, encode_kwargs={'normalize_embeddings': False})
-
+        embedding_model = HuggingFaceEmbeddings(model_name="nomic-ai/modernbert-embed-base", model_kwargs={'device': 'cpu'}, encode_kwargs={'normalize_embeddings': False})
+        
         vector_store = Chroma(
             collection_name="deepseek_collection",
             collection_metadata={"hnsw:space": "cosine"},
@@ -112,11 +111,11 @@ if st.session_state.get("chunked", False) and not st.session_state.get("vector_c
         st.session_state.vector_created = True  # ✅ Prevent re-creating vector store
         st.success(f"✅ **Vector Store Created!** Total documents stored: {num_documents}")
 
-# Step 5: Query Input (this should not trigger previous steps!)
+# Step 5: Query Input 
 if st.session_state.get("vector_created", False) and st.session_state.get("vector_store", None):
     query = st.text_input("🔍 Enter a Query:")
 
-    if query:
+    if query and st.session_state.get("vector_created", False):
         with st.spinner("Retrieving relevant contexts..."):
             retriever = st.session_state.vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 5})
             contexts = retriever.invoke(query)