Update app.py

Final working version with motivational quote dataset

app.py

@@ -1,71 +1,30 @@
 import gradio as gr
 from datasets import load_dataset
-from sentence_transformers import SentenceTransformer, util
-import torch
 from itertools import chain
 import random
 
-# Load dataset
 raw_dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
 dataset = list(raw_dataset)
 
-# Extract quotes, authors, and tags safely
 quotes = [item["quote"] for item in dataset]
 authors = [item["author"] for item in dataset]
-tags_list = []
+tags_list = [item["tags"].split(", ") if item["tags"] else [] for item in dataset]
 
-for item in dataset:
-    tags = item.get("tags")
-    if tags:
-        tags_list.append(tags.split(", "))
-    else:
-        tags_list.append([])
-
-# Define 5 fixed categories that actually exist in dataset
-fixed_categories = ["inspiration", "success", "life", "love", "courage"]
-
-# Load transformer model for semantic similarity
-model = SentenceTransformer("all-MiniLM-L6-v2")
-quote_embeddings = model.encode(quotes, convert_to_tensor=True)
-
-# Keep track of used quotes to avoid repetition
-used_quote_indices = set()
-
-# Recommendation function
-def recommend_quote(mood_input, selected_tag):
-    # Filter quotes by tag
-    filtered = [(i, q, a) for i, (q, a, t) in enumerate(zip(quotes, authors, tags_list)) if selected_tag in t]
+all_tags = sorted(set(chain.from_iterable(tags_list)))
 
+def recommend_by_category(selected_tag):
+    filtered = [(q, a) for (q, a, t) in zip(quotes, authors, tags_list) if selected_tag in t]
     if not filtered:
-        return "😔 Sorry, no quotes found for that category."
-
-    # Filter out used quotes if possible
-    unused = [item for item in filtered if item[0] not in used_quote_indices]
-    pool = unused if unused else filtered  # fallback to all if all used
-    f_indices, f_quotes, f_authors = zip(*pool)
-
-    # Embed input and compute similarity
-    input_embedding = model.encode(mood_input, convert_to_tensor=True)
-    f_embeddings = model.encode(f_quotes, convert_to_tensor=True)
-    similarities = util.pytorch_cos_sim(input_embedding, f_embeddings)
-    top_k = torch.topk(similarities, k=1)
-
-    top_index = top_k.indices[0][0].item()
-    quote_index = f_indices[top_index]
-    used_quote_indices.add(quote_index)
-
-    return f"“{f_quotes[top_index]}”\n– {f_authors[top_index]}"
+        return "😔 Sorry, no quotes found for that tag."
+    quote, author = random.choice(filtered)
+    return f"“{quote}”\n– {author}"
 
-# Gradio interface
 iface = gr.Interface(
-    fn=recommend_quote,
-    inputs=[
-        gr.Textbox(lines=2, label="What's your current mood or thought?"),
-        gr.Radio(choices=fixed_categories, label="Select a category")
-    ],
+    fn=recommend_by_category,
+    inputs=gr.Dropdown(choices=all_tags, label="Start typing a category", filterable=True),
     outputs="text",
-    title="MoodMatch – AI Quote Recommender",
-    description="Get inspiring quotes based on your mood and selected category."
+    title="MoodMatch",
+    description="Start typing a category like 'wisdom', 'success', or 'love' to receive an inspiring quote."
 )
 
 iface.launch()