Update app.py

app.py

@@ -4,24 +4,22 @@ from sentence_transformers import SentenceTransformer, util
 import torch
 from itertools import chain
 
-raw_dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
-
-quotes = [item["quote"] for item in raw_dataset]
-authors = [item["author"] for item in raw_dataset]
-tags_list = [item["tags"] for item in raw_dataset]
-
-all_tags = list(set(chain.from_iterable(tags_list)))
-all_tags.sort()
-
+# Load dataset
+dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
+quotes = [item["quote"] for item in dataset]
+authors = [item["author"] for item in dataset]
+tags_list = [item["tags"] for item in dataset]
+all_tags = sorted(set(chain.from_iterable(tags_list)))
+
+# Load model
 model = SentenceTransformer("all-MiniLM-L6-v2")
 quote_embeddings = model.encode(quotes, convert_to_tensor=True)
 
+# Define recommendation logic
 def recommend_quote(mood_input, selected_tag):
-    filtered = [
-        (q, a, i) for i, (q, a, t) in enumerate(zip(quotes, authors, tags_list)) if selected_tag in t
-    ]
+    filtered = [(q, a, i) for i, (q, a, t) in enumerate(zip(quotes, authors, tags_list)) if selected_tag in t]
     if not filtered:
-        return "Sorry, no quotes found for that category."
+        return "😕 Sorry, no quotes found for that category."
 
     f_quotes = [q for q, _, _ in filtered]
     f_authors = [a for _, a, _ in filtered]
@@ -33,11 +31,12 @@ def recommend_quote(mood_input, selected_tag):
     top_k = torch.topk(similarities, k=min(3, len(f_quotes)))
 
     result = ""
-    for i in top_k.indices[0]:
-        result += f"{f_quotes[i]}\n– {f_authors[i]}\n\n"
+    for idx in top_k.indices[0]:
+        result += f"\"{f_quotes[idx]}\"\n— {f_authors[idx]}\n\n"
 
     return result.strip()
 
+# Gradio UI
 iface = gr.Interface(
     fn=recommend_quote,
     inputs=[