Update app.py

app.py

@@ -1,52 +1,65 @@
-import gradio as gr
+# app.py ─ HF Space • MiniLM semantic FAQ search (CPU-only)
+
+import re
+from pathlib import Path
 import pandas as pd
+import gradio as gr
 from sentence_transformers import SentenceTransformer, util
 
-# ---------- Load data & model (all CPU-friendly) ----------
-faq_df = pd.read_csv("faqs.csv")
+# ─────────── config ───────────
+CSV_PATH   = Path("faqs.csv")
+MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2"
+
+# ─────────── load data/model ───────────
+faq_df    = pd.read_csv(CSV_PATH)
 questions = faq_df["question"].tolist()
 answers   = faq_df["answer"].tolist()
 
-model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
-question_embeddings = model.encode(questions, convert_to_tensor=True, normalize_embeddings=True)
-
-# ---------- Search function ----------
-def semantic_search(user_query, top_k=3):
-    query_embedding = model.encode(user_query, convert_to_tensor=True, normalize_embeddings=True)
-    scores = util.cos_sim(query_embedding, question_embeddings)[0]
-    top_k_idx = scores.topk(k=top_k).indices.cpu().numpy()
-    
-    results = []
-    for idx in top_k_idx:
-        results.append(
-            {
-                "FAQ Question": questions[idx],
-                "FAQ Answer"  : answers[idx],
-                "Similarity"  : f"{scores[idx]:.3f}"
-            }
-        )
-    return results
-
-# ---------- Gradio UI ----------
-with gr.Blocks(title="MiniLM Semantic FAQ Search") as demo:
-    gr.Markdown(
-        """
-        # 🔍 Semantic FAQ Search  
-        Enter a salon-related question. The model finds the closest FAQs and displays their answers.
-        """)
-    
+model = SentenceTransformer(MODEL_NAME)
+question_embs = model.encode(
+    questions, convert_to_tensor=True, normalize_embeddings=True
+)
+
+# ─────────── tiny emoji tagger ───────────
+EMOJI_RULES = {
+    r"\b(shampoo|conditioner|mask)\b"      : "🧴",
+    r"\b(hair\s?spray|spray)\b"            : "💨",
+    r"\b(vegan|botanical|organic)\b"       : "🌱",
+    r"\b(heat|thermal)\b"                 : "🔥",
+    r"\b(balayage|color|colour|dye)\b"     : "💇‍♀️",
+    r"\b(scissors|cut|trim)\b"             : "✂️",
+}
+def tag_emoji(text: str) -> str:
+    for pat, emo in EMOJI_RULES.items():
+        if re.search(pat, text, flags=re.I):
+            return emo
+    return "❓"
+
+# ─────────── search fn ───────────
+def search_faq(query: str, top_k: int):
+    if not query.strip():
+        return pd.DataFrame(columns=["Emoji", "Question", "Answer", "Score"])
+    q_emb    = model.encode(query, convert_to_tensor=True, normalize_embeddings=True)
+    scores   = util.cos_sim(q_emb, question_embs)[0]
+    idx_list = scores.topk(k=top_k).indices.cpu().tolist()
+    rows     = [
+        [tag_emoji(answers[i]), questions[i], answers[i], round(float(scores[i]), 3)]
+        for i in idx_list
+    ]
+    return pd.DataFrame(rows, columns=["Emoji", "Question", "Answer", "Score"])
+
+# ─────────── gradio ui ───────────
+with gr.Blocks(theme=gr.themes.Soft(), title="Semantic FAQ Search") as demo:
+    gr.Markdown("# 🔍 Semantic FAQ Search")
     with gr.Row():
-        query_box = gr.Textbox(
-            label="Ask a question",
-            placeholder="e.g. Which spray protects hair from heat?"
-        )
-        topk_slider = gr.Slider(
-            1, 5, value=3, step=1, label="Number of results"
-        )
-    search_btn = gr.Button("Search")
-    out = gr.Dataframe(headers=["FAQ Question", "FAQ Answer", "Similarity"], visible=True, wrap=True)
-    
-    search_btn.click(semantic_search, [query_box, topk_slider], out)
+        inp = gr.Textbox(label="Ask a question", lines=2,
+                         placeholder="e.g. Which spray protects hair from heat?")
+        k   = gr.Slider(1, 5, value=3, step=1, label="Number of results")
+    btn = gr.Button("Search", variant="primary")
+    table = gr.Dataframe(headers=["Emoji", "Question", "Answer", "Score"],
+                         datatype=["str", "str", "str", "number"],
+                         wrap=True, interactive=False)
+    btn.click(search_faq, [inp, k], table)
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", show_error=True)
+    demo.launch(server_name="0.0.0.0")