Update app.py

app.py

@@ -1,39 +1,53 @@
 import gradio as gr
-from sentence_transformers import SentenceTransformer, util
+from sentence_transformers import SentenceTransformer
 import pandas as pd
-from rapidfuzz import fuzz, process  # Importing valid functions for fuzzy matching
+from rapidfuzz import fuzz, process
 
-# Pre-download the model
+# Load the model
 model_name = "sentence-transformers/all-MiniLM-L6-v2"
 model = SentenceTransformer(model_name)
 
-# Load your data
-data_file = "train_1.csv"  # Replace with your actual file
+# Load CSV data
+data_file = "Luxury_Products_Apparel_Data.csv"  # Ensure this file is uploaded
 try:
     df = pd.read_csv(data_file, nrows=1000)  # Limit rows for testing
 except FileNotFoundError:
-    df = pd.DataFrame({"text": ["Sample data 1", "Sample data 2", "Sample data 3"]})  # Fallback data
+    df = pd.DataFrame({
+        "ProductName": ["Gucci Shoes", "Nike Sneakers", "Louis Vuitton Handbag"],
+        "Category": ["Shoes", "Bags"],
+        "SubCategory": ["Sneakers", "Totes"]
+    })  # Fallback sample data
 
-data = df['text'].dropna().tolist()
+# Extract relevant fields
+product_names = df["ProductName"].dropna().tolist()
+categories = df["Category"].dropna().unique().tolist()
+subcategories = df["SubCategory"].dropna().unique().tolist()
+
+# Merge into one dataset for autocomplete
+autocomplete_data = product_names + categories + subcategories
+
+# Clean data by removing unnecessary characters
+autocomplete_data = [str(item).strip('"') for item in autocomplete_data]
 
 # Autocomplete function
 def autocomplete(query):
     if not query.strip():
-        return []  # Return empty if query is blank
+        return []  # Avoid empty queries
+
+    # Fuzzy matching with typo tolerance
+    matches = process.extract(query, autocomplete_data, scorer=fuzz.partial_ratio, limit=5)
 
-    # Use fuzz.partial_ratio for fuzzy matching
-    matches = process.extract(query, data, scorer=fuzz.partial_ratio, limit=5)
-    return "\n".join([match[0] for match in matches])  # Return matches as a multi-line string
+    # Return only the best-matched product names, categories, or subcategories
+    return [match[0] for match in matches]
 
 # Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("### Typo-Tolerant Autocomplete")
+    gr.Markdown("### Improved Autocomplete for Luxury Products")
 
-    # Create a Textbox without live=True
     query = gr.Textbox(label="Start typing for autocomplete")
     autocomplete_output = gr.Textbox(label="Autocomplete Suggestions", lines=5)
 
-    # Trigger autocomplete on input submission
-    query.submit(fn=autocomplete, inputs=query, outputs=autocomplete_output)
+    # Trigger autocomplete on change
+    query.change(fn=autocomplete, inputs=query, outputs=autocomplete_output)
 
 demo.launch()