Update product_recommender.py

product_recommender.py

@@ -1,61 +1,41 @@
-import gradio as gr
-from typing import Dict, List
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForTokenClassification
+from sentence_transformers import SentenceTransformer
+import torch
+import numpy as np
+from typing import Dict, List, Optional
 import json
-import urllib.parse
-from product_recommender import ProductRecommender
 
-# Initialize the recommender
-recommender = ProductRecommender()
-
-# Sample product database - replace with your actual database
-product_database = [
-    {
-        "description": "FIFA 24 EA Sports Football Game",
-        "category": "games",
-        "features": ["sports", "multiplayer"],
-        "price": 4999
-    },
-    # Add more products
-]
-
-def get_recommendations(text: str) -> Dict:
-    try:
-        # Get recommendations using the multi-model system
-        recommendations = recommender.get_recommendations(text, product_database)
+class ProductRecommender:
+    def __init__(self):
+        self.model_analyzer = MultiModelAnalyzer()
         
-        # Format recommendations with shopping links
-        formatted_recommendations = []
-        for rec in recommendations:
-            query = urllib.parse.quote(rec['description'])
-            formatted_rec = {
-                "product": rec['description'],
-                "price": f"₹{rec['price']}",
-                "similarity_score": f"{rec.get('similarity', 0):.2f}",
-                "shopping_links": {
-                    "Amazon": f"https://www.amazon.in/s?k={query}",
-                    "Flipkart": f"https://www.flipkart.com/search?q={query}",
-                    "IGP": f"https://www.igp.com/search?q={query}"
-                }
-            }
-            formatted_recommendations.append(formatted_rec)
-        
-        return {
-            "recommendations": formatted_recommendations
-        }
-        
-    except Exception as e:
-        return {"error": str(e)}
-
-# Create Gradio interface
-demo = gr.Interface(
-    fn=get_recommendations,
-    inputs=gr.Textbox(lines=3),
-    outputs=gr.JSON(),
-    title="🎁 Smart Gift Recommender",
-    description="Get personalized gift suggestions with direct shopping links!"
-)
+    def get_recommendations(self, query: str, product_database: List[Dict]) -> List[Dict]:
+        try:
+            query_analysis = self.model_analyzer.analyze_text(query)
+            
+            # For testing, return a simple recommendation
+            return [{
+                "name": "Test Product",
+                "price": "₹999",
+                "category": "test",
+                "similarity": 0.95
+            }]
+        except Exception as e:
+            print(f"Error in recommendations: {str(e)}")
+            return []
 
-if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
-else:
-    app = demo.app
+class MultiModelAnalyzer:
+    def __init__(self):
+        try:
+            self.category_model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased")
+            self.category_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+            self.semantic_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+        except Exception as e:
+            print(f"Error initializing models: {str(e)}")
+    
+    def analyze_text(self, text: str) -> Dict:
+        return {
+            "category": "test",
+            "embedding": np.zeros(10),
+            "features": ["test"]
+        }