Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,34 +1,139 @@
 # ==========================================================
-# streamlit_app.py — Restored Centered Layout + Green Status UI
+# streamlit_app.py — Stable Layout + Latest Backend Improvements
 # ==========================================================
 import os
 import re
 import streamlit as st
+import torch
+
+# ==========================================================
+# ✅ PAGE CONFIG
+# ==========================================================
+st.set_page_config(page_title="Enterprise Knowledge Assistant", layout="wide")
+print("CUDA available:", torch.cuda.is_available())
+
+# ==========================================================
+# ⚙️ CACHE SETUP
+# ==========================================================
+CACHE_DIR = "/tmp/hf_cache"
+os.makedirs(CACHE_DIR, exist_ok=True)
+os.environ.update({
+    "HF_HOME": CACHE_DIR,
+    "TRANSFORMERS_CACHE": CACHE_DIR,
+    "HF_DATASETS_CACHE": CACHE_DIR,
+    "HF_MODULES_CACHE": CACHE_DIR,
+})
+
+# ==========================================================
+# 📦 IMPORTS
+# ==========================================================
 from ingestion import extract_text_from_pdf, chunk_text
 from vectorstore import build_faiss_index
 from qa import retrieve_chunks, generate_answer, cache_embeddings, embed_chunks, genai_generate
 
-# ✅ Centered layout again (this caused the stretch difference)
-st.set_page_config(page_title="Enterprise Knowledge Assistant", layout="centered")
+# ==========================================================
+# 🧠 SMART SUGGESTION GENERATOR
+# ==========================================================
+def generate_dynamic_suggestions_from_toc(toc, chunks, doc_name="Document"):
+    if not toc or not chunks:
+        return []
+    titles = []
+    for sec, raw_title in toc:
+        title = re.sub(r"^\s*[\dA-Za-z.\-]+\s*", "", raw_title)
+        title = re.sub(r"\.{2,}\s*\d+$", "", title).strip()
+        if 4 < len(title) < 120:
+            titles.append(title)
+    context_sample = " ".join(chunks[:3])[:4000]
+    prompt = f"""
+    You are generating short, natural, and context-aware questions for users reading "{doc_name}".
+    Use the Table of Contents and some document text for inspiration.
+
+    TABLE OF CONTENTS:
+    {chr(10).join(['- ' + t for t in titles[:8]])}
+
+    SAMPLE TEXT:
+    {context_sample}
+
+    Generate 5–7 clear and human-like questions based strictly on this document.
+    Each should sound natural, under 18 words, and avoid robotic phrasing.
+    """
+    try:
+        ai_response = genai_generate(prompt)
+        questions = re.findall(r"[-•]?\s*(.+?)\?", ai_response)
+        clean_qs = [q.strip("•-— ").strip() + "?" for q in questions if 8 < len(q) < 120]
+        seen, final = set(), []
+        for q in clean_qs:
+            if q.lower() not in seen:
+                seen.add(q.lower())
+                final.append(q)
+        return final[:7]
+    except Exception:
+        return ["How do I start using this guide?", "What does this document cover?"]
+
+# ==========================================================
+# 🎨 STYLING — MINIMAL ENTERPRISE DESIGN
+# ==========================================================
+st.markdown("""
+<style>
+div.block-container {padding-top: 1.2rem; max-width: 1080px;}
+h1, h2, h3 {color: #f3f4f6; font-weight: 600;}
+.suggest-chip {
+    background: #0f1724;
+    border: 1px solid #374151;
+    border-radius: 14px;
+    color: #e6eef8;
+    padding: 8px 12px;
+    cursor: pointer;
+    font-size: 13px;
+    margin: 6px 6px 6px 0;
+    display: inline-block;
+    transition: background 0.2s, transform 0.1s;
+}
+.suggest-chip:hover {background: #1e3a8a; transform: translateY(-2px);}
+.answer-box {
+    background: linear-gradient(180deg,#0b1220,#071027);
+    border-left: 4px solid #3b82f6;
+    border-radius: 8px;
+    padding: 16px 18px;
+    color: #e6eef8;
+    margin-top: 12px;
+    box-shadow: 0 4px 14px rgba(0,0,0,0.35);
+}
+.stTextInput > div > div > input {
+    background-color: #0f172a !important;
+    color: #f1f5f9 !important;
+    border-radius: 6px !important;
+    border: 1px solid #334155 !important;
+    padding: 8px 10px !important;
+    font-size: 15px !important;
+}
+.stTextInput > label {font-weight: 500;}
+.small-link {
+    font-size: 13px;
+    color: #60a5fa;
+    cursor: pointer;
+}
+</style>
+""", unsafe_allow_html=True)
 
 # ==========================================================
-# 🧭 SIDEBAR — As before
+# 🧭 SIDEBAR
 # ==========================================================
 with st.sidebar:
-    st.markdown("### 🧭 Response Mode")
+    st.markdown("### 🧭 Response Style")
     mode = st.radio(
         "",
         ("Strict (Document-only)", "Extended (Document + general)"),
         index=0,
-        help="Strict = answers only from the document. Extended = may include general context.",
+        help="Strict = answers only from the uploaded document. Extended = may include related general info.",
     )
 
     st.markdown("---")
-    show_advanced = st.checkbox("Show advanced settings (for developers)", value=False)
-    if show_advanced:
-        st.markdown("### Developer Settings")
-        chunk_size = st.slider("Chunk Size (characters)", 200, 1500, 1000, step=50)
-        overlap = st.slider("Chunk Overlap (characters)", 50, 200, 120, step=10)
+    show_dev = st.checkbox("Show advanced settings (for developers)", value=False)
+    if show_dev:
+        st.markdown("### ⚙️ Developer Options")
+        chunk_size = st.slider("Chunk Size", 200, 1500, 1000, step=50)
+        overlap = st.slider("Chunk Overlap", 50, 200, 120, step=10)
         top_k = st.slider("Top K Results", 1, 10, 5)
     else:
         chunk_size, overlap, top_k = 1000, 120, 5
@@ -55,127 +160,88 @@ def set_user_query(q, idx):
     st.experimental_rerun()
 
 # ==========================================================
-# 📘 PAGE HEADER (Centered)
+# 📄 MAIN SECTION
 # ==========================================================
-st.markdown(
-    """
-    <div style="text-align:center; margin-top:-10px;">
-        <h1>📄 Enterprise Knowledge Assistant</h1>
-        <p style="color:gray; font-size:15px;">
-            Query SAP documentation and enterprise PDFs — powered by reasoning and retrieval.
-        </p>
-    </div>
-    """,
-    unsafe_allow_html=True,
-)
+st.title("📄 Enterprise Knowledge Assistant")
+st.caption("Query SAP documentation and enterprise PDFs — powered by reasoning and retrieval.")
+
+doc_choice = st.radio("Select a document:", ["-- Select --", "Sample PDF", "Upload Custom PDF"], index=0)
 
 # ==========================================================
-# 📄 MAIN CONTAINER — Centered
+# 📂 DOCUMENT HANDLING
 # ==========================================================
-col_spacer_left, col_main, col_spacer_right = st.columns([0.15, 0.7, 0.15])
-with col_main:
-
-    # ----------------------------------------------------------
-    # 📂 Document Upload / Selection
-    # ----------------------------------------------------------
-    st.markdown("### Select a document:")
-    doc_choice = st.radio("", ("-- Select --", "Sample PDF", "Upload Custom PDF"))
-
-    temp_path = None
+if doc_choice == "-- Select --":
+    st.info("⬅️ Select or upload a document to begin.")
+else:
     if doc_choice == "Sample PDF":
         temp_path = os.path.join(os.path.dirname(__file__), "sample.pdf")
-        st.success("📘 Sample PDF loaded successfully. Ask questions below.")
-        st.success("✅ Document ready — you can now ask questions below.")
-    elif doc_choice == "Upload Custom PDF":
-        uploaded_file = st.file_uploader("Upload your PDF", type="pdf")
+        st.success("📘 Sample PDF loaded successfully. You can now ask below.")
+    else:
+        uploaded_file = st.file_uploader("", 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(f"✅ '{uploaded_file.name}' uploaded successfully — ready to query below.")
-            st.success("✅ Document ready — you can now ask questions below.")
-    else:
-        st.info("⬅️ Please select or upload a document to begin.")
+            st.success(f"✅ '{uploaded_file.name}' uploaded successfully. You can now ask below.")
+        else:
+            temp_path = None
 
-    # ----------------------------------------------------------
-    # 🧠 Process document when loaded
-    # ----------------------------------------------------------
     if temp_path:
-        text, toc = extract_text_from_pdf(temp_path)
-        chunks = chunk_text(text, chunk_size=chunk_size, overlap=overlap)
-        embeddings = cache_embeddings(os.path.basename(temp_path), chunks, embed_chunks)
-        index = build_faiss_index(embeddings)
+        with st.spinner("🔍 Processing document..."):
+            text, toc = extract_text_from_pdf(temp_path)
+            chunks = chunk_text(text, chunk_size=chunk_size, overlap=overlap)
+        with st.spinner("⚙️ Building search index..."):
+            embeddings = cache_embeddings(os.path.basename(temp_path), chunks, embed_chunks)
+            index = build_faiss_index(embeddings)
+        st.success("✅ Document ready — you can now ask your question below.")
+
+        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
+        else:
+            query_suggestions = st.session_state["query_suggestions_fixed"]
 
         # ----------------------------------------------------------
-        # 💡 Suggested Questions
+        # 💬 ASK SECTION
         # ----------------------------------------------------------
-        if not st.session_state["query_suggestions_fixed"]:
-            st.session_state["query_suggestions_fixed"] = [
-                "What is the purpose of this document?",
-                "How can integration be set up in SAP Cloud?",
-                "What are the prerequisites mentioned?",
-                "What steps are involved in configuration?",
-                "How to troubleshoot integration issues?",
-                "What is the key functionality covered?"
-            ]
-
-        st.markdown("### Ask the Assistant")
-
-        visible_qs = (
-            st.session_state["query_suggestions_fixed"][:3]
-            if not st.session_state["show_more"]
-            else st.session_state["query_suggestions_fixed"]
-        )
-        cols = st.columns(3)
-        for i, q in enumerate(visible_qs):
-            if cols[i % 3].button(f"💬 {q}", key=f"suggest_{i}"):
-                set_user_query(q, i)
-
-        if st.button("Show more ▼" if not st.session_state["show_more"] else "Show less ▲"):
-            st.session_state["show_more"] = not st.session_state["show_more"]
+        st.markdown("### 💬 Ask the Assistant")
 
-        # ----------------------------------------------------------
-        # 🧩 Query Input
-        # ----------------------------------------------------------
-        user_query = st.text_input(
-            "Type your question or click one above:",
-            value=st.session_state["user_query_input"],
-            key="user_query_input"
-        )
+        if query_suggestions:
+            visible = query_suggestions if st.session_state["show_more"] else query_suggestions[:3]
+            cols = st.columns(min(3, len(visible)))
+            for i, q in enumerate(visible):
+                if cols[i % 3].button(f"💬 {q}", key=f"sugg_{i}"):
+                    set_user_query(q, i)
+
+            toggle_text = "Show less ▲" if st.session_state["show_more"] else "Show more ▼"
+            if st.button(toggle_text, help="Show or hide more suggestions"):
+                st.session_state["show_more"] = not st.session_state["show_more"]
+                st.experimental_rerun()
+
+        user_query = st.text_input("Type your question or click one above:", key="user_query_input")
 
         # ----------------------------------------------------------
-        # 🤖 Generate Answer
+        # 💡 RESPONSE SECTION
         # ----------------------------------------------------------
-        if user_query:
+        if user_query.strip():
             reasoning_mode = mode == "Extended (Document + general)"
-            st.markdown(f"**Mode:** {'🧠 Extended' if reasoning_mode else '📄 Strict Document'}")
-
-            with st.spinner("💭 Generating 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.markdown("### Assistant’s Answer")
-            st.markdown(
-                f"""
-                <div style='background:#0f172a;border-left:4px solid #22c55e;
-                padding:12px;border-radius:8px;color:#f1f5f9'>{answer}</div>
-                """,
-                unsafe_allow_html=True,
-            )
-
-            with st.expander("📘 Supporting Context", expanded=False):
-                for i, chunk in enumerate(retrieved, 1):
-                    st.markdown(f"**Chunk {i}:** {chunk.strip()}")
-
-    # ----------------------------------------------------------
-    # 📑 Document Preview
-    # ----------------------------------------------------------
-    if temp_path:
-        st.markdown("---")
-        with st.expander("📄 Document Preview", expanded=False):
-            st.text_area("Extracted text (first 1000 chars):", text[:1000], height=180)
-            st.caption(f"📦 {len(chunks)} chunks processed.")
+            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.markdown("### 🤖 Assistant’s Answer")
+            st.markdown(f"<div class='answer-box'>{answer}</div>", unsafe_allow_html=True)
+
+            with st.expander("📘 Supporting Context"):
+                for i, r in enumerate(retrieved, start=1):
+                    st.markdown(f"**Chunk {i}:** {r}")
+
+            if toc:
+                with st.expander("📚 Explore Document Sections"):
+                    toc_text = "\n".join([f"{sec}. {title}" for sec, title in toc])
+                    st.text_area("", toc_text, height=140)
+
+            with st.expander("📄 Document Preview"):
+                st.text_area("", text[:1000], height=140)
+                st.caption(f"{len(chunks)} chunks processed.")