Update app.py

app.py

@@ -1,39 +1,58 @@
 import gradio as gr
+from datasets import load_dataset
 from sentence_transformers import SentenceTransformer, util
 import torch
 
-# Sample quote dataset
-quotes = [
-    "You are stronger than you think.",
-    "It's okay to take a break.",
-    "Progress, not perfection.",
-    "Breathe. You’re doing better than you think.",
-    "Small steps still move you forward.",
-    "This feeling is temporary.",
-    "One day at a time.",
-    "You got this.",
-    "Your value is not measured by productivity.",
-    "Kindness starts with yourself."
-]
-
-# Load the embedding model
-model = SentenceTransformer('all-MiniLM-L6-v2')
+# Load the dataset from Hugging Face
+dataset = load_dataset("asuender/motivational-quotes", "quotes_extended", split="train")
+
+# Extract quotes, authors, and tags
+quotes = [item["quote"] for item in dataset]
+authors = [item["author"] for item in dataset]
+tags_list = [item["tags"] for item in dataset]
+
+# Flatten tags and remove duplicates for dropdown
+from itertools import chain
+all_tags = list(set(chain.from_iterable(tags_list)))
+all_tags.sort()
+
+# Load embedding model
+model = SentenceTransformer("all-MiniLM-L6-v2")
 quote_embeddings = model.encode(quotes, convert_to_tensor=True)
 
-# Recommendation function
-def recommend_quote(user_input):
-    user_embedding = model.encode(user_input, convert_to_tensor=True)
-    similarities = util.pytorch_cos_sim(user_embedding, quote_embeddings)
-    top_results = torch.topk(similarities, k=3)
-    recommended = [quotes[i] for i in top_results.indices[0]]
-    return "\n\n".join(recommended)
+# Main function
+def recommend_quote(mood_input, selected_tag):
+    # Filter quotes by 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 "No quotes found for that category."
+
+    f_quotes = [q for q, a, _ in filtered]
+    f_authors = [a for _, a, _ in filtered]
+    f_indices = [i for _, _, i in filtered]
+    f_embeddings = quote_embeddings[f_indices]
 
-# Gradio UI
-interface = gr.Interface(
+    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)))
+
+    results = []
+    for i in top_k.indices[0]:
+        results.append(f"“{f_quotes[i]}” — {f_authors[i]}")
+    
+    return "\n\n".join(results)
+
+# Gradio interface
+demo = gr.Interface(
     fn=recommend_quote,
-    inputs=gr.Textbox(placeholder="Type how you feel..."),
+    inputs=[
+        gr.Textbox(label="How are you feeling?", placeholder="e.g. I feel overwhelmed with school"),
+        gr.Dropdown(choices=all_tags, label="Choose a Category")
+    ],
     outputs="text",
-    title="MoodMatch",
-    description="Type how you feel. Get 3 uplifting quotes powered by AI.",
+    title="🧠 MoodMatch: Find Quotes that Fit Your Mood",
+    description="Get inspiring quotes based on how you feel and what kind of motivation you want."
 )
-interface.launch()
+
+demo.launch()
+