Update app.py

Final working version with motivational quote dataset

app.py

@@ -2,47 +2,59 @@ import gradio as gr
 from datasets import load_dataset
 from sentence_transformers import SentenceTransformer, util
 import torch
+from itertools import chain
+
+# Load dataset from Hugging Face
+raw_dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
+dataset = list(raw_dataset)
 
-# Load dataset
-dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
+# Print a sample to debug (optional – remove later if working)
+print(dataset[0])
 
-# Parse data
+# Extract quotes, authors, and safely handle missing tags
 quotes = [item["quote"] for item in dataset]
 authors = [item["author"] for item in dataset]
 
-# Since tags are stored as a **comma-separated string**, convert to list
-tags_list = [item["tags"].split(", ") if item["tags"] else [] for item in dataset]
+tags_list = []
+for item in dataset:
+    tags = item.get("tags")
+    if tags:
+        tags_list.append(tags.split(", "))
+    else:
+        tags_list.append([])
 
-# Get unique tag values
-from itertools import chain
+# Get unique tags for dropdown
 all_tags = sorted(set(chain.from_iterable(tags_list)))
 
-# Load embedding model
+# Load sentence transformer model for semantic similarity
 model = SentenceTransformer("all-MiniLM-L6-v2")
 quote_embeddings = model.encode(quotes, convert_to_tensor=True)
 
-# Recommendation function
+# Define quote recommendation function
 def recommend_quote(mood_input, selected_tag):
+    # Filter quotes by selected tag
     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]
     f_indices = [i for _, _, i in filtered]
     f_embeddings = quote_embeddings[f_indices]
 
+    # Encode user input and calculate similarity
     input_embedding = model.encode(mood_input, convert_to_tensor=True)
     similarities = util.pytorch_cos_sim(input_embedding, f_embeddings)
     top_k = torch.topk(similarities, k=min(3, len(f_quotes)))
 
+    # Format result
     result = ""
-    for idx in top_k.indices[0]:
-        result += f"\"{f_quotes[idx]}\"\n— {f_authors[idx]}\n\n"
+    for i in top_k.indices[0]:
+        result += f"\"{f_quotes[i]}\"\n— {f_authors[i]}\n\n"
 
     return result.strip()
 
-# Gradio app
+# Gradio interface
 iface = gr.Interface(
     fn=recommend_quote,
     inputs=[