Update src/streamlit_app.py

src/streamlit_app.py

@@ -158,6 +158,30 @@ with st.sidebar:
     st.markdown("---")
     st.caption("✨ Built by Shubham Sharma")
 
+    # 🧩 Developer Insights (Moved up here from main block)
+    if show_dev:
+        st.markdown("---")
+        with st.expander("🧩 Developer Insights", expanded=False):
+            st.markdown("**Retrieved Chunks (Context):**")
+            retrieved_chunks = st.session_state.get("retrieved", [])
+            for i, r in enumerate(retrieved_chunks, start=1):
+                st.markdown(f"- **Chunk {i}:** {r}")
+
+            toc_data = st.session_state.get("toc", [])
+            if toc_data:
+                st.markdown("---")
+                st.markdown("**Document Sections (TOC):**")
+                toc_text = "\n".join([f"{sec}. {title}" for sec, title in toc_data])
+                st.text_area("", toc_text, height=120)
+
+            doc_text = st.session_state.get("text", "")
+            if doc_text:
+                st.markdown("---")
+                st.markdown("**Document Preview:**")
+                st.text_area("", doc_text[:1000], height=120)
+                st.caption(f"{len(st.session_state.get('chunks', []))} chunks processed.")
+
+
 # ==========================================================
 # 🧠 SESSION STATE
 # ==========================================================
@@ -185,50 +209,78 @@ st.caption("Query SAP documentation and enterprise PDFs — powered by reasoning
 doc_choice = st.radio("Select a document:", ["-- Select --", "Sample PDF", "Upload Custom PDF"], index=0)
 
 # ==========================================================
-# 📂 DOCUMENT HANDLING
+# 📂 DOCUMENT HANDLING — CLEAN + ACCURATE UI FLOW
 # ==========================================================
 if doc_choice == "-- Select --":
     st.info("⬅️ Select or upload a document to begin.")
 else:
+    temp_path = None
+
+    # --- File selection ---
     if doc_choice == "Sample PDF":
         temp_path = os.path.join(os.path.dirname(__file__), "sample.pdf")
-        st.success("📘 Sample document loaded successfully — you can start asking your questions below.")
+        st.markdown("✅ **Sample PDF selected.** Preparing document...")
     else:
-        uploaded_file = st.file_uploader("", type="pdf", label_visibility="collapsed")
+        uploaded_file = st.file_uploader(
+            "Upload a PDF document (max 200MB):",
+            type="pdf",
+            label_visibility="collapsed"
+        )
         if uploaded_file:
             temp_path = os.path.join("/tmp", uploaded_file.name)
             with open(temp_path, "wb") as f:
                 f.write(uploaded_file.getbuffer())
-            st.success("✅ Document processed successfully — you can start asking your questions below.")
+
+            # File badge (nice compact indicator)
+            st.markdown(
+                f"<div style='background:#0f172a;border-radius:8px;"
+                f"padding:6px 10px;margin-top:4px;display:inline-block;'>📄 "
+                f"<b>{uploaded_file.name}</b> — {uploaded_file.size/1024:.1f} KB</div>",
+                unsafe_allow_html=True
+            )
+
         else:
-            temp_path = None
+            st.stop()  # wait until file uploaded before proceeding
 
+    # --- Real processing begins here ---
     if temp_path:
-        with st.spinner("🔍 Processing document..."):
-            text, toc, toc_source = extract_text_from_pdf(temp_path)
-            chunks = chunk_text(text, chunk_size=chunk_size, overlap=overlap)
+        status = st.empty()
+        status.info("📤 Upload complete — reading document...")
+
+        text, toc, toc_source = extract_text_from_pdf(temp_path)
+        status.info("📑 Parsing and chunking document...")
+        chunks = chunk_text(text, chunk_size=chunk_size, overlap=overlap)
+
+        status.info("🧠 Building embeddings and search index...")
+        embeddings = cache_embeddings(os.path.basename(temp_path), chunks, embed_chunks)
+        index = build_faiss_index(embeddings)
+
+        status.success("✅ Document ready — you can start asking your questions below.")
 
-        with st.spinner("⚙️ Building search index..."):
-            embeddings = cache_embeddings(os.path.basename(temp_path), chunks, embed_chunks)
-            index = build_faiss_index(embeddings)
+        # Save for dev sidebar
+        st.session_state.update({
+            "text": text,
+            "toc": toc,
+            "chunks": chunks
+        })
 
+        # --- Suggestion setup ---
         doc_name = os.path.basename(temp_path)
         if st.session_state["last_doc"] != doc_name:
             query_suggestions = generate_dynamic_suggestions_from_toc(toc, chunks, doc_name)
-            st.session_state["query_suggestions_fixed"] = query_suggestions
-            st.session_state["last_doc"] = doc_name
-            st.session_state["user_query_input"] = ""
-            st.session_state["selected_suggestion"] = None
-            st.session_state["show_more"] = False
+            st.session_state.update({
+                "query_suggestions_fixed": query_suggestions,
+                "last_doc": doc_name,
+                "user_query_input": "",
+                "selected_suggestion": None,
+                "show_more": False
+            })
             st.rerun()
         else:
             query_suggestions = st.session_state["query_suggestions_fixed"]
 
-        # ----------------------------------------------------------
-        # 💬 ASK SECTION
-        # ----------------------------------------------------------
+        # --- Ask section ---
         st.markdown("### 💬 Ask the Assistant")
-
         if query_suggestions:
             visible = query_suggestions if st.session_state["show_more"] else query_suggestions[:3]
             cols = st.columns(min(3, len(visible)))
@@ -243,14 +295,12 @@ else:
 
         user_query = st.text_input("Type your question or click one above:", key="user_query_input")
 
-        # ----------------------------------------------------------
-        # 💡 RESPONSE SECTION
-        # ----------------------------------------------------------
         if user_query.strip():
             reasoning_mode = mode == "Extended (Document + General)"
             with st.spinner("💭 Generating your answer..."):
                 retrieved = retrieve_chunks(user_query, index, chunks, top_k=top_k, embeddings=embeddings)
                 answer = generate_answer(user_query, retrieved, reasoning_mode=reasoning_mode)
+                st.session_state["retrieved"] = retrieved
 
             st.markdown("### 🤖 Assistant’s Answer")
 
@@ -259,27 +309,7 @@ else:
                 answer = re.sub(r"(^|\n)-\s*", r"\1<br>• ", answer)
             st.markdown(f"<div class='answer-box'>{answer}</div>", unsafe_allow_html=True)
 
-        # ----------------------------------------------------------
-        # 🧩 SIDEBAR — COLLAPSIBLE DEVELOPER INSIGHTS
-        # ----------------------------------------------------------
-        if show_dev:
-            with st.sidebar:
-                st.markdown("---")
-                with st.expander("🧩 Developer Insights", expanded=False):
-                    st.markdown("**Context Chunks (Retrieved):**")
-                    for i, r in enumerate(retrieved, start=1):
-                        st.markdown(f"- **Chunk {i}:** {r}")
-
-                    if toc:
-                        st.markdown("---")
-                        st.markdown("**Document Sections (TOC):**")
-                        toc_text = "\n".join([f"{sec}. {title}" for sec, title in toc])
-                        st.text_area("", toc_text, height=120)
-
-                    st.markdown("---")
-                    st.markdown("**Document Preview:**")
-                    st.text_area("", text[:1000], height=120)
-                    st.caption(f"{len(chunks)} chunks processed.")
+
 
 # ==========================================================
 # 🎨 Optional Sidebar Scroll Styling (keeps it clean)