Update app1.py

app1.py

@@ -145,16 +145,39 @@ if st.session_state.chunked and not st.session_state.vector_created:
             st.error(f"❌ Error creating vector store: {e}")
 
 # Debugging Logs
-st.write("📄 **PDF Loaded:**", st.session_state.pdf_loaded)
-st.write("🔹 **Chunked:**", st.session_state.chunked)
-st.write("📂 **Vector Store Created:**", st.session_state.vector_created)
+#st.write("📄 **PDF Loaded:**", st.session_state.pdf_loaded)
+#st.write("🔹 **Chunked:**", st.session_state.chunked)
+#st.write("📂 **Vector Store Created:**", st.session_state.vector_created)
 
 
 # ----------------- Query Input -----------------
-query = st.text_input("🔍 Ask a question about the document:")
+query = None  
+
+# Check if a valid PDF URL has been entered (but not processed yet)
+pdf_url_entered = bool(st.session_state.get("pdf_url"))  # Checks if text is in the input box
+
+# No PDF Provided Yet
+if not st.session_state.pdf_path and not pdf_url_entered:
+    st.info("📥 **Please upload a PDF or enter a valid URL to proceed.**")
+
+# PDF URL Exists but Not Processed Yet (Only show if URL exists but hasn't been downloaded)
+elif pdf_url_entered and not st.session_state.pdf_loaded:
+    st.warning("⚠️ **PDF URL detected! Click 'Download and Process PDF' to proceed.**")
+
+# Processing in Progress 
+elif st.session_state.get("trigger_download", False) and (
+    not st.session_state.pdf_loaded or not st.session_state.chunked or not st.session_state.vector_created
+):
+    st.info("⏳ **Processing your document... Please wait.**")
+
+# ✅ Step 4: Processing Complete, Ready for Questions
+elif st.session_state.pdf_loaded and st.session_state.chunked and st.session_state.vector_created:
+    st.success("🎉 **Processing complete! You can now ask questions.**")
+    query = st.text_input("🔍 **Ask a question about the document:**")
+    
 if query:
     with st.spinner("🔄 Retrieving relevant context..."):
-        retriever = st.session_state.vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 5})
+        retriever = st.session_state.vector_store.as_retriever(search_type="similarity", search_kwargs={"k": 3})
         contexts = retriever.invoke(query)
         # Debugging: Check what was retrieved
         st.write("Retrieved Contexts:", contexts)
@@ -227,7 +250,7 @@ if query:
         context_prompt = PromptTemplate(
             input_variables=["context_number"],
             template="""
-            You main task is to analyze the json structure as a part of the Context Number Response and the list of Contexts provided in the 'Content List' and perform the following steps:-
+            Your main task is to analyze the json structure as a part of the Context Number Response and the list of Contexts provided in the 'Content List' and perform the following steps:-
             (1) Look at the output from the Relevant Context Picker Agent.
             (2) Analyze the 'content' key in the Json Structure format({{"content":<<content_number>>}}).
             (3) Retrieve the value of 'content' key and pick up the context corresponding to that element from the Content List provided.
@@ -247,7 +270,7 @@ if query:
             """
         )
 
-        rag_prompt = """ You are ahelpful assistant very profiient in formulating clear and meaningful answers from the context provided.Based on the CONTEXT Provided ,Please formulate
+        rag_prompt = """ You are a helpful assistant very profiient in formulating clear and meaningful answers from the context provided.Based on the CONTEXT Provided ,Please formulate
         a clear concise and meaningful answer for the QUERY asked.Please refrain from making up your own answer in case the COTEXT provided is not sufficient to answer the QUERY.In such a situation please respond as 'I do not know'.
         
         QUERY: