Update app.py

app.py

@@ -1,65 +1,83 @@
-# app.py ─ HF Space • MiniLM semantic FAQ search (CPU-only)
+# MiniLM Semantic FAQ Search – CPU-only HF Space
+# Works out-of-the-box with faqs.csv in the same folder.
 
 import re
 from pathlib import Path
-import pandas as pd
+
 import gradio as gr
+import pandas as pd
 from sentence_transformers import SentenceTransformer, util
 
-# ─────────── config ───────────
-CSV_PATH   = Path("faqs.csv")
+# ------- paths & model -------------------------------------------------
+BASE_DIR   = Path(__file__).parent
+CSV_FILE   = BASE_DIR / "faqs.csv"
 MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2"
 
-# ─────────── load data/model ───────────
-faq_df    = pd.read_csv(CSV_PATH)
+# ------- load FAQ data -------------------------------------------------
+if not CSV_FILE.exists():
+    raise FileNotFoundError(
+        f"{CSV_FILE} missing. Make sure faqs.csv is in the repo root."
+    )
+
+faq_df    = pd.read_csv(CSV_FILE)
 questions = faq_df["question"].tolist()
 answers   = faq_df["answer"].tolist()
 
+# ------- embed questions ----------------------------------------------
 model = SentenceTransformer(MODEL_NAME)
 question_embs = model.encode(
     questions, convert_to_tensor=True, normalize_embeddings=True
 )
 
-# ─────────── tiny emoji tagger ───────────
+# ------- 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"             : "✂️",
+    r"\b(shampoo|conditioner|mask)\b"        : "🧴",
+    r"\b(hair\s?spray|spray)\b"              : "💨",
+    r"\b(vegan|botanical|organic)\b"         : "🌱",
+    r"\b(heat|thermal|hot)\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):
+def emoji_for(text: str) -> str:
+    for pattern, emo in EMOJI_RULES.items():
+        if re.search(pattern, text, flags=re.I):
             return emo
     return "❓"
 
-# ─────────── search fn ───────────
+# ------- search function ----------------------------------------------
 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(
+            columns=["Emoji", "Question", "Answer", "Score"]
+        )
+    q_emb   = model.encode(query, convert_to_tensor=True, normalize_embeddings=True)
+    sims    = util.cos_sim(q_emb, question_embs)[0]
+    idx_top = sims.topk(k=top_k).indices.cpu().tolist()
+
+    rows = [
+        [emoji_for(answers[i]), questions[i], answers[i], round(float(sims[i]), 3)]
+        for i in idx_top
     ]
     return pd.DataFrame(rows, columns=["Emoji", "Question", "Answer", "Score"])
 
-# ─────────── gradio ui ───────────
+# ------- Gradio UI -----------------------------------------------------
 with gr.Blocks(theme=gr.themes.Soft(), title="Semantic FAQ Search") as demo:
     gr.Markdown("# 🔍 Semantic FAQ Search")
     with gr.Row():
-        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)
+        q_in = gr.Textbox(
+            label="Ask a question",
+            lines=2,
+            placeholder="e.g. Which spray protects hair from heat?"
+        )
+        k_in = gr.Slider(1, 5, value=3, step=1, label="Results")
+    search_btn = gr.Button("Search", variant="primary")
+    table_out  = gr.Dataframe(
+        headers=["Emoji", "Question", "Answer", "Score"],
+        datatype=["str", "str", "str", "number"],
+        wrap=True,
+        interactive=False
+    )
+    search_btn.click(search_faq, [q_in, k_in], table_out)
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0")