Update app.py

app.py

@@ -1,8 +1,8 @@
 # ================================================================
 # Self-Sensing Concrete Assistant — Predictor (XGB) + Hybrid RAG
-# - Predictor tab: identical behavior to your "second code"
-# - Literature tab: from your "first code" (Hybrid RAG + MMR)
-# - Hugging Face friendly: online PDF fetching OFF by default
+# - Predictor tab: identical behavior (kept)
+# - Literature tab: Hybrid RAG; LLM runs silently when available
+# - UX: no visible "LLM & Controls" window; prediction=0.0 if incomplete
 # ================================================================
 
 # ---------------------- Runtime flags (HF-safe) ----------------------
@@ -43,7 +43,10 @@ try:
 except Exception:
     OpenAI = None
 
-# ========================= Predictor (kept same as 2nd) =========================
+# LLM availability flag — used internally; UI remains hidden
+LLM_AVAILABLE = (OPENAI_API_KEY is not None and OPENAI_API_KEY.strip() != "" and OpenAI is not None)
+
+# ========================= Predictor (kept) =========================
 CF_COL     = "Conductive Filler Conc. (wt%)"
 TARGET_COL = "Stress GF (MPa-1)"
 
@@ -102,6 +105,13 @@ CATEGORICAL_COLS = {
     "Current Type"
 }
 
+OPTIONAL_FIELDS = {
+    "Filler 2 Type",
+    "Filler 2 Diameter (µm)",
+    "Filler 2 Length (mm)",
+    "Filler 2 Dimensionality",
+}
+
 DIM_CHOICES     = ["0D", "1D", "2D", "3D", "NA"]
 CURRENT_CHOICES = ["DC", "AC", "NA"]
 
@@ -137,7 +147,30 @@ def _coerce_to_row(form_dict: dict) -> pd.DataFrame:
             row[col] = "" if v in (None, "NA") else str(v).strip()
     return pd.DataFrame([row], columns=MAIN_VARIABLES)
 
+def _is_complete(form_dict: dict) -> bool:
+    for col in MAIN_VARIABLES:
+        if col in OPTIONAL_FIELDS:
+            continue
+        v = form_dict.get(col, None)
+        if col in NUMERIC_COLS:
+            try:
+                if v in ("", None) or (isinstance(v, float) and np.isnan(v)):
+                    return False
+            except Exception:
+                return False
+        elif col in CATEGORICAL_COLS:
+            s = "" if v in (None, "NA") else str(v).strip()
+            if s == "":
+                return False
+        else:
+            s = "" if v is None else str(v).strip()
+            if s == "":
+                return False
+    return True
+
 def predict_fn(**kwargs):
+    if not _is_complete(kwargs):
+        return 0.0
     mdl = _load_model_or_error()
     if isinstance(mdl, str):
         return mdl
@@ -193,8 +226,7 @@ def _clear_all():
             cleared.append("")
     return cleared
 
-# ========================= Hybrid RAG (from 1st code) =========================
-# Configuration
+# ========================= Hybrid RAG =========================
 ARTIFACT_DIR    = Path("rag_artifacts"); ARTIFACT_DIR.mkdir(exist_ok=True)
 TFIDF_VECT_PATH = ARTIFACT_DIR / "tfidf_vectorizer.joblib"
 TFIDF_MAT_PATH  = ARTIFACT_DIR / "tfidf_matrix.joblib"
@@ -202,16 +234,13 @@ BM25_TOK_PATH   = ARTIFACT_DIR / "bm25_tokens.joblib"
 EMB_NPY_PATH    = ARTIFACT_DIR / "chunk_embeddings.npy"
 RAG_META_PATH   = ARTIFACT_DIR / "chunks.parquet"
 
-# PDF source (HF-safe: rely on local /papers by default)
-LOCAL_PDF_DIR = Path("./literature_pdfs"); LOCAL_PDF_DIR.mkdir(exist_ok=True)
+LOCAL_PDF_DIR = Path("papers"); LOCAL_PDF_DIR.mkdir(exist_ok=True)
 USE_ONLINE_SOURCES = os.getenv("USE_ONLINE_SOURCES", "false").lower() == "true"
 
-# Retrieval weights
 W_TFIDF_DEFAULT = 0.50 if not USE_DENSE else 0.30
 W_BM25_DEFAULT  = 0.50 if not USE_DENSE else 0.30
-W_EMB_DEFAULT   = 0.00 if not USE_DENSE else 0.40
+W_EMB_DEFAULT   = 0.00 if USE_DENSE is False else 0.40
 
-# Simple text processing
 _SENT_SPLIT_RE = re.compile(r"(?<=[.!?])\s+|\n+")
 TOKEN_RE       = re.compile(r"[A-Za-z0-9_#+\-/\.%]+")
 def sent_split(text: str) -> List[str]:
@@ -220,7 +249,6 @@ def sent_split(text: str) -> List[str]:
 def tokenize(text: str) -> List[str]:
     return [t.lower() for t in TOKEN_RE.findall(text)]
 
-# PDF text extraction (PyMuPDF preferred; pypdf fallback)
 def _extract_pdf_text(pdf_path: Path) -> str:
     try:
         import fitz
@@ -262,7 +290,6 @@ def _safe_init_st_model(name: str):
         USE_DENSE = False
         return None
 
-# Build or load index
 def build_or_load_hybrid(pdf_dir: Path):
     have_cache = (TFIDF_VECT_PATH.exists() and TFIDF_MAT_PATH.exists()
                   and RAG_META_PATH.exists()
@@ -287,13 +314,11 @@ def build_or_load_hybrid(pdf_dir: Path):
             rows.append({"doc_path": str(pdf), "chunk_id": i, "text": ch})
             all_tokens.append(tokenize(ch))
     if not rows:
-        # create empty stub to avoid crashes; UI will message user to upload PDFs
         meta = pd.DataFrame(columns=["doc_path", "chunk_id", "text"])
         vectorizer = None; X_tfidf = None; emb = None; all_tokens = None
         return vectorizer, X_tfidf, meta, all_tokens, emb
 
     meta = pd.DataFrame(rows)
-
     from sklearn.feature_extraction.text import TfidfVectorizer
     vectorizer = TfidfVectorizer(
         ngram_range=(1,2),
@@ -317,13 +342,11 @@ def build_or_load_hybrid(pdf_dir: Path):
             print("Dense embedding failed:", e)
             emb = None
 
-    # Save artifacts
     joblib.dump(vectorizer, TFIDF_VECT_PATH)
-    joblib.dump(X_tfidf, TFIDF_MAT_PATH)
+    joblib.dump(X_tfidF:=X_tfidf, TFIDF_MAT_PATH)  # assign + save
     if BM25Okapi is not None:
         joblib.dump(all_tokens, BM25_TOK_PATH)
     meta.to_parquet(RAG_META_PATH, index=False)
-
     return vectorizer, X_tfidf, meta, all_tokens, emb
 
 tfidf_vectorizer, tfidf_matrix, rag_meta, bm25_tokens, emb_matrix = build_or_load_hybrid(LOCAL_PDF_DIR)
@@ -331,7 +354,7 @@ bm25 = BM25Okapi(bm25_tokens) if (BM25Okapi is not None and bm25_tokens is not N
 st_query_model = _safe_init_st_model(os.getenv("EMB_MODEL_NAME", "sentence-transformers/all-MiniLM-L6-v2"))
 
 def _extract_page(text_chunk: str) -> str:
-    m = list(re.finditer(r"\[\[PAGE=(\d+)\]\]", text_chunk or ""))
+    m = list(re.finditer(r"\\[\\[PAGE=(\\d+)\\]\\]", text_chunk or ""))
     return (m[-1].group(1) if m else "?")
 
 def hybrid_search(query: str, k=8, w_tfidf=W_TFIDF_DEFAULT, w_bm25=W_BM25_DEFAULT, w_emb=W_EMB_DEFAULT):
@@ -360,7 +383,7 @@ def hybrid_search(query: str, k=8, w_tfidf=W_TFIDF_DEFAULT, w_bm25=W_BM25_DEFAUL
 
     # BM25 scores
     if bm25 is not None:
-        q_tokens = [t.lower() for t in re.findall(r"[A-Za-z0-9_#+\-/\.%]+", query)]
+        q_tokens = [t.lower() for t in re.findall(r"[A-Za-z0-9_#+\\-\\/\\.%%]+", query)]
         bm25_scores = np.array(bm25.get_scores(q_tokens), dtype=float)
     else:
         bm25_scores = np.zeros(len(rag_meta), dtype=float); w_bm25 = 0.0
@@ -403,7 +426,6 @@ def mmr_select_sentences(question: str, hits: pd.DataFrame, top_n=4, pool_per_ch
 
     sent_texts = [p["sent"] for p in pool]
 
-    # Embedding-based relevance if available, else TF-IDF
     use_dense = USE_DENSE and st_query_model is not None
     if use_dense:
         try:
@@ -446,7 +468,7 @@ def compose_extractive(selected: List[Dict[str, Any]]) -> str:
     return " ".join(f"{s['sent']} ({s['doc']}, p.{s['page']})" for s in selected)
 
 def synthesize_with_llm(question: str, sentence_lines: List[str], model: str = None, temperature: float = 0.2) -> str:
-    if OPENAI_API_KEY is None or OpenAI is None:
+    if not LLM_AVAILABLE:
         return None
     client = OpenAI(api_key=OPENAI_API_KEY)
     model = model or OPENAI_MODEL
@@ -496,6 +518,7 @@ def rag_reply(
     srcs = {Path(r['doc_path']).name for _, r in hits.iterrows()}
     coverage_note = "" if len(srcs) >= 3 else f"\n\n> Note: Only {len(srcs)} unique source(s) contributed. Add more PDFs or increase Top-K."
 
+    # Hidden policy: if strict==True → no paraphrasing; else try LLM if available
     if strict_quotes_only:
         if not selected:
             return f"**Quoted Passages:**\n\n---\n" + "\n\n".join(hits['text'].tolist()[:2]) + f"\n\n**Citations:** {header_cites}{coverage_note}"
@@ -545,24 +568,60 @@ def rag_chat_fn(message, history, top_k, n_sentences, include_passages,
     except Exception as e:
         return f"RAG error: {e}"
 
-# ========================= UI (predictor styling kept) =========================
+# ========================= UI (science-oriented styling) =========================
 CSS = """
-/* Blue to green gradient background */
+/* Science-oriented: crisp contrast + readable numerics */
+* {font-family: ui-sans-serif, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial;}
 .gradio-container {
-    background: linear-gradient(135deg, #1e3a8a 0%, #166534 60%, #15803d 100%) !important;
+    background: linear-gradient(135deg, #0b1020 0%, #0c2b1a 60%, #0a2b4d 100%) !important;
 }
-* {font-family: ui-sans-serif, system-ui, -apple-system, 'Segoe UI', Roboto, 'Helvetica Neue', Arial;}
-.card {background: rgba(255,255,255,0.07) !important; border: 1px solid rgba(255,255,255,0.12);}
-label.svelte-1ipelgc {color: #e0f2fe !important;}
+.card {background: rgba(255,255,255,0.06) !important; border: 1px solid rgba(255,255,255,0.14); border-radius: 12px;}
+label {color: #e8f7ff !important; text-shadow: 0 1px 0 rgba(0,0,0,0.35); cursor: pointer;}
+input[type="number"] {font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", monospace;}
+
+/* Checkbox clickability fixes */
+input[type="checkbox"], .gr-checkbox, .gr-checkbox > * { pointer-events: auto !important; }
+.gr-checkbox label, .gr-check-radio label { pointer-events: auto !important; cursor: pointer; }
+#rag-tab input[type="checkbox"] { accent-color: #60a5fa !important; }
+
+/* RAG tab background and elements */
+#rag-tab .block, #rag-tab .group, #rag-tab .accordion {
+    background: linear-gradient(160deg, #1f2937 0%, #14532d 55%, #0b3b68 100%) !important;
+    border-radius: 12px;
+    border: 1px solid rgba(255,255,255,0.14);
+}
+#rag-tab input, #rag-tab textarea, #rag-tab select, #rag-tab .scroll-hide, #rag-tab .chatbot textarea {
+    background: rgba(17, 24, 39, 0.85) !important;
+    border: 1px solid #60a5fa !important;
+    color: #e5f2ff !important;
+}
+#rag-tab input[type="range"] { accent-color: #22c55e !important; }
+#rag-tab button { border-radius: 10px !important; font-weight: 600 !important; }
+#rag-tab .chatbot {
+    background: rgba(15, 23, 42, 0.6) !important;
+    border: 1px solid rgba(148, 163, 184, 0.35) !important;
+}
+#rag-tab .message.user {
+    background: rgba(34, 197, 94, 0.15) !important;
+    border-left: 3px solid #22c55e !important;
+}
+#rag-tab .message.bot {
+    background: rgba(59, 130, 246, 0.15) !important;
+    border-left: 3px solid #60a5fa !important;
+    color: #eef6ff !important;
+}
+
+/* Predictor output emphasis */
+#pred-out .wrap { font-size: 20px; font-weight: 700; color: #ecfdf5; }
 """
 
 theme = gr.themes.Soft(
     primary_hue="blue",
     neutral_hue="green"
 ).set(
-    body_background_fill="#1e3a8a",
+    body_background_fill="#0b1020",
     body_text_color="#e0f2fe",
-    input_background_fill="#172554",
+    input_background_fill="#0f172a",
     input_border_color="#1e40af",
     button_primary_background_fill="#2563eb",
     button_primary_text_color="#ffffff",
@@ -574,9 +633,8 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
     gr.Markdown(
         "<h1 style='margin:0'>Self-Sensing Concrete Assistant</h1>"
         "<p style='opacity:.9'>"
-        "Left tab: ML prediction for Stress Gauge Factor (kept identical to your deployed predictor). "
-        "Right tab: Literature Q&A via Hybrid RAG (BM25 + TF-IDF + optional dense) with MMR sentence selection. "
-        "Upload PDFs into <code>papers/</code> in your Space repo."
+        "Left: ML prediction for Stress Gauge Factor (original scale, MPa<sup>-1</sup>). "
+        "Right: Literature Q&A via Hybrid RAG (BM25 + TF-IDF + optional dense) with MMR sentence selection."
         "</p>"
     )
 
@@ -620,7 +678,7 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
 
                 with gr.Column(scale=5):
                     with gr.Group(elem_classes=["card"]):
-                        out_pred = gr.Number(label="Predicted Stress GF (MPa-1)", precision=6)
+                        out_pred = gr.Number(label="Predicted Stress GF (MPa-1)", value=0.0, precision=6, elem_id="pred-out")
                         with gr.Row():
                             btn_pred  = gr.Button("Predict", variant="primary")
                             btn_clear = gr.Button("Clear")
@@ -628,14 +686,14 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
 
                     with gr.Accordion("About this model", open=False, elem_classes=["card"]):
                         gr.Markdown(
-                            "- Pipeline: ColumnTransformer -> (RobustScaler + OneHot) -> XGBoost\n"
-                            "- Target: Stress GF (MPa^-1) on original scale (model trains on log1p).\n"
+                            "- Pipeline: ColumnTransformer → (RobustScaler + OneHot) → XGBoost\n"
+                            "- Target: Stress GF (MPa<sup>-1</sup>) on original scale (model trains on log1p).\n"
                             "- Missing values are safely imputed per-feature.\n"
                             "- Trained columns:\n"
-                            f"  `{', '.join(MAIN_VARIABLES)}`"
+                            f"  `{', '.join(MAIN_VARIABLES)}`",
+                            elem_classes=["prose"]
                         )
 
-            # Wire predictor buttons
             inputs_in_order = [
                 f1_type, f1_diam, f1_len, cf_conc,
                 f1_dim,  f2_type, f2_diam, f2_len,
@@ -650,38 +708,42 @@ with gr.Blocks(css=CSS, theme=theme, fill_height=True) as demo:
                 return predict_fn(**data)
 
             btn_pred.click(_predict_wrapper, inputs=inputs_in_order, outputs=out_pred)
-            btn_clear.click(lambda: _clear_all(), inputs=None, outputs=inputs_in_order)
+            btn_clear.click(lambda: _clear_all(), inputs=None, outputs=inputs_in_order).then(lambda: 0.0, outputs=out_pred)
             btn_demo.click(lambda: _fill_example(), inputs=None, outputs=inputs_in_order)
 
         # ------------------------- Literature Tab -------------------------
-        with gr.Tab("📚 Ask the Literature (Hybrid RAG + MMR)"):
+        with gr.Tab("📚 Ask the Literature (Hybrid RAG + MMR)", elem_id="rag-tab"):
             gr.Markdown(
                 "Upload PDFs into the repository folder <code>papers/</code> then reload the Space. "
-                "Answers cite (Doc.pdf, p.X). Toggle strict quotes or optional LLM paraphrasing."
+                "Answers cite (Doc.pdf, p.X)."
             )
             with gr.Row():
                 top_k = gr.Slider(5, 12, value=8, step=1, label="Top-K chunks")
                 n_sentences = gr.Slider(2, 6, value=4, step=1, label="Answer length (sentences)")
-                include_passages = gr.Checkbox(value=False, label="Include supporting passages")
+                include_passages = gr.Checkbox(value=False, label="Include supporting passages", interactive=True)
+
             with gr.Accordion("Retriever weights (advanced)", open=False):
                 w_tfidf = gr.Slider(0.0, 1.0, value=W_TFIDF_DEFAULT, step=0.05, label="TF-IDF weight")
                 w_bm25  = gr.Slider(0.0, 1.0, value=W_BM25_DEFAULT,  step=0.05, label="BM25 weight")
-                w_emb   = gr.Slider(0.0, 1.0, value=W_EMB_DEFAULT,   step=0.05, label="Dense weight (set 0 if disabled)")
-            with gr.Accordion("LLM & Controls", open=False):
-                strict_quotes_only = gr.Checkbox(value=False, label="Strict quotes only (no paraphrasing)")
-                use_llm     = gr.Checkbox(value=False, label="Use LLM to paraphrase selected sentences")
-                model_name  = gr.Textbox(value=os.getenv("OPENAI_MODEL", OPENAI_MODEL),
-                                         label="LLM model", placeholder="e.g., gpt-5 or gpt-5-mini")
-                temperature = gr.Slider(0.0, 1.0, value=0.2, step=0.05, label="Temperature")
+                w_emb   = gr.Slider(0.0, 1.0, value=(0.0 if not USE_DENSE else 0.40), step=0.05, label="Dense weight (set 0 if disabled)")
+
+            # ---- Hidden states for LLM behavior (no visible controls) ----
+            state_use_llm     = gr.State(LLM_AVAILABLE)   # True when key present; else False
+            state_model_name  = gr.State(os.getenv("OPENAI_MODEL", OPENAI_MODEL))
+            state_temperature = gr.State(0.2)
+            state_strict      = gr.State(False)           # hidden: default to not-strict
+
             gr.ChatInterface(
                 fn=rag_chat_fn,
-                additional_inputs=[top_k, n_sentences, include_passages, use_llm, model_name,
-                                   temperature, strict_quotes_only, w_tfidf, w_bm25, w_emb],
+                additional_inputs=[
+                    top_k, n_sentences, include_passages,
+                    state_use_llm, state_model_name, state_temperature, state_strict,
+                    w_tfidf, w_bm25, w_emb
+                ],
                 title="Literature Q&A",
-                description="Hybrid retrieval with diversity. Answers carry inline (Doc, p.X) citations. Toggle strict/LLM modes."
+                description="Hybrid retrieval with diversity. Answers carry inline (Doc, p.X) citations."
             )
 
 # ------------- Launch -------------
 if __name__ == "__main__":
-    # queue() helps HF Spaces with concurrency; show_error suggests upload PDFs if none
     demo.queue().launch()