Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import json
 import hashlib
 import uuid
+import re
 from datetime import datetime
 from rapidfuzz import fuzz
 from transformers import pipeline
@@ -24,25 +25,35 @@ else:
     print(f"Warning: {DATA_FILE} not found! Please upload your data file to the space.")
 
 # ==========================================
-# 2. REAL AI MODEL SETUP (Zero-Shot Intent)
+# 2. AI MODEL SETUP (Zero-Shot Intent)
 # ==========================================
-print("Loading Real AI Model for Intent & Mood Prediction...")
-# Hum ek fast Zero-Shot model use kar rahe hain taaki batch processing tez ho.
-# Ye direct user intent samjhega.
+print("Loading AI Model for Smart Decision Making...")
 intent_classifier = pipeline(
     "zero-shot-classification", 
     model="typeform/distilbert-base-uncased-mnli" 
 )
-
 INTENT_LABELS = ["self-harm", "adult", "technology", "news", "entertainment", "sports", "information"]
 
 # ==========================================
-# 3. CORE BATCH SEARCH ALGORITHM
+# 3. HELPER FUNCTIONS
+# ==========================================
+def is_url(text):
+    # Check agar user ne direct URL daala hai
+    pattern = re.compile(r'^(https?://|www\.)\S+$', re.IGNORECASE)
+    return bool(pattern.match(text.strip()))
+
+def generate_user_id():
+    return f"user_{uuid.uuid4().hex[:10]}"
+
+# ==========================================
+# 4. CORE BATCH SEARCH ENGINE (AI + FUZZY)
 # ==========================================
-# 'batch=True' hone ki wajah se ye function ek list of queries lega
-# ex: queries = ["latest news", "adult video", "code tool"]
 def batch_search_engine(queries, limits, user_ids):
-    # Step A: Limit check (Max 30, Default 30)
+    # Returns 2 lists: one for JSON outputs, one for HTML (Redirections)
+    final_json_responses = []
+    final_html_responses = []
+    
+    # Check limits
     processed_limits = []
     for l in limits:
         try:
@@ -54,57 +65,69 @@ def batch_search_engine(queries, limits, user_ids):
         except:
             processed_limits.append(30)
             
-    # Step B: AI Processing in BATCH! (Ek sath saare users ka intent predict hoga)
-    # Pipeline automatically list of strings ko parallel process karta hai
-    print(f"Processing Batch of {len(queries)} queries simultaneously...")
-    ai_results = intent_classifier(queries, INTENT_LABELS)
-    
-    # Handle single element vs list response from pipeline
+    # Process batch with AI (Skip direct URLs for AI processing to save time)
+    ai_queries = [q if not is_url(q) else "bypass" for q in queries]
+    ai_results = intent_classifier(ai_queries, INTENT_LABELS)
     if isinstance(ai_results, dict):
         ai_results = [ai_results]
 
-    final_batch_responses = []
-
-    # Step C: Har query ke liye Fuzzy Match aur Privacy Logging apply karna
     for i in range(len(queries)):
-        query = queries[i]
+        query = str(queries[i]).strip()
         limit = processed_limits[i]
         user_id = user_ids[i]
-        top_intent = ai_results[i]['labels'][0]
         
+        # --- DIRECT URL REDIRECT LOGIC ---
+        if is_url(query):
+            url_to_open = query if query.startswith("http") else "http://" + query
+            # Redirect via HTML meta tag
+            redirect_html = f'<meta http-equiv="refresh" content="0; url={url_to_open}">'
+            final_html_responses.append(redirect_html)
+            
+            # Add small info in JSON
+            final_json_responses.append({
+                "status": "redirecting",
+                "message": f"Direct URL detected. Redirecting to {url_to_open}",
+                "url": url_to_open
+            })
+            continue
+            
         # --- PRIVACY LOGGING ---
-        # Query dikhegi nahi log me, sirf hash banega. User ki pehchaan UUID se hogi.
         query_hash = hashlib.sha256(query.encode()).hexdigest()[:16]
-        timestamp = datetime.utcnow().isoformat()
+        top_intent = ai_results[i]['labels'][0]
+        
         log_entry = {
             "user_id": user_id,
-            "query_id": query_hash,
-            "timestamp": timestamp,
-            "predicted_intent": top_intent
+            "query_hash": query_hash,
+            "timestamp": datetime.utcnow().isoformat(),
+            "ai_intent": top_intent
         }
-        print(f"SECURE LOG: {log_entry}")  # Ise database me save kar sakte ho future me
-
+        print(f"SECURE LOG: {log_entry}") 
+        
         # --- SELF HARM CHECK ---
         if top_intent == "self-harm":
-            final_batch_responses.append(json.dumps({
+            final_html_responses.append("<div></div>") # No HTML redirect
+            final_json_responses.append({
                 "status": "blocked",
-                "intent": "self-harm",
-                "message": "Safety Alert: We do not provide search results for self-harm. Please seek help.",
+                "ai_intent": "self-harm",
+                "message": "⚠️ Safety Alert: We do not provide search results for self-harm. Please seek help.",
                 "results": []
-            }, indent=2))
+            })
             continue
 
-        # --- FUZZY MATCH & INTENT BOOSTING ---
+        # --- AI + FUZZY MATCH LOGIC ---
         results_with_scores = []
         
         for item in search_db:
-            # RapidFuzz for high-speed fuzzy text matching
-            fuzzy_score = fuzz.token_set_ratio(query.lower(), item.get('search_index', '').lower())
+            text_to_search = item.get('search_index', '')
+            
+            # 1. Fuzzy Token Set Ratio (Keywords aage-peeche ho toh bhi chalega)
+            fuzzy_score = fuzz.token_set_ratio(query.lower(), text_to_search.lower())
             
-            # AI Intent Boosting: Agar intent domain se match kare toh data rank me upar aayega
+            # 2. AI Decision Boosting (Konsa dena hai)
             boost = 0
             domain = item.get('domain', '').lower()
             
+            # AI samajh raha hai ki user ko exact kis domain ka content chahiye
             if top_intent == "adult" and domain in ["xhname", "avideos", "redwap", "dlsite"]:
                 boost = 25
             elif top_intent == "technology" and domain in ["github", "scmp", "workspace", "bitdefender"]:
@@ -116,77 +139,76 @@ def batch_search_engine(queries, limits, user_ids):
                 
             final_score = fuzzy_score + boost
             
-            # Threshold Check (Kam se kam 30% relevancy honi chahiye)
+            # Minimum 30 score hona chahiye text match ka tabhi result aayega
             if final_score > 30:
                 results_with_scores.append({
                     "score": final_score,
                     "data": item
                 })
                 
-        # Highest score wale ko top pe rakhna (Rank sorting)
+        # Highest score (AI decides + Fuzzy match) will be on TOP
         results_with_scores.sort(key=lambda x: x["score"], reverse=True)
         
-        # Filter and extract Top Results up to Limit
+        # Limit the results (Max 30)
         final_data = [res["data"] for res in results_with_scores[:limit]]
         
-        # Prepare JSON response
-        response_json = {
-            "predicted_intent": top_intent,
+        final_html_responses.append("<div></div>") # Empty HTML for normal searches
+        
+        # Using Python Dictionary directly to avoid UI bug `{`
+        final_json_responses.append({
+            "status": "success",
+            "ai_predicted_intent": top_intent,
             "total_found": len(final_data),
-            "showing_results": len(final_data),
+            "limit_applied": limit,
             "results": final_data
-        }
-        final_batch_responses.append(json.dumps(response_json, indent=2, ensure_ascii=False))
+        })
 
-    # Return the processed batch to respective users
-    return final_batch_responses
+    # Return lists because batch=True requires list of outputs for each component
+    return final_json_responses, final_html_responses
 
 # ==========================================
-# 4. GRADIO UI & QUEUE SYSTEM
+# 5. GRADIO UI & QUEUE SYSTEM
 # ==========================================
-# Generate unique User ID for session
-def generate_user_id():
-    return f"user_{uuid.uuid4().hex[:10]}"
-
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🚀 AI Smart Search Engine")
-    gr.Markdown("Search for Tech, News, Adult, Sports, etc. Powered by True AI Intent & Fuzzy Match.")
+    gr.Markdown("# 🚀 Ultimate AI Search Engine")
+    gr.Markdown("Type your search query or paste a direct **URL**. Powered by AI Intent & Fuzzy Text Search.")
     
-    # State variable for user anonymity & tracking (Stored in user's browser session)
     session_user_id = gr.State(generate_user_id)
     
     with gr.Row():
-        query_input = gr.Textbox(label="Enter Search Query...", placeholder="What do you want to find?", scale=4)
-        limit_input = gr.Number(label="Results Limit (Max 30)", value=30, precision=0, scale=1)
+        query_input = gr.Textbox(label="Search Box", placeholder="Search anything or paste a URL (e.g. https://google.com)...", scale=4)
+        limit_input = gr.Number(label="Limit (Max 30)", value=30, precision=0, scale=1)
         
     search_btn = gr.Button("Search 🔍", variant="primary")
     
-    # Output section
-    output_display = gr.Code(label="Search Results", language="json")
+    # Fixed UI Issue: Using gr.JSON instead of gr.Code
+    output_json = gr.JSON(label="Search Results")
+    
+    # Hidden HTML component for URL redirection
+    redirect_html = gr.HTML(label="", visible=False)
     
-    # Event Listener with BATCHING ENABLED
+    # Link Button & Enter Key (Batch Mode enabled)
     search_btn.click(
         fn=batch_search_engine,
         inputs=[query_input, limit_input, session_user_id],
-        outputs=[output_display],
-        # Yaha pe magic hai! Batch=True ki wajah se Gradio requests ekathi karke AI ko bhejta hai.
+        outputs=[output_json, redirect_html],
         batch=True,          
-        max_batch_size=10,   # Ek time pe maximum 10 logo ki request AI ko sath bhejega
-        api_name="search"    # Log ise as an API "/api/search" bhi call kar sakte hain
+        max_batch_size=10,   
+        api_name="search"    
     )
 
     query_input.submit(
         fn=batch_search_engine,
         inputs=[query_input, limit_input, session_user_id],
-        outputs=[output_display],
+        outputs=[output_json, redirect_html],
         batch=True,
         max_batch_size=10
     )
 
-# Enable Queue for "First Come First Serve" logic
+# Queue System: First come first serve with concurrency
 demo.queue(
-    default_concurrency_limit=5, # Kitne concurrent batches chalenge
-    max_size=100                 # Queue me max kitne log wait kar sakte hain
+    default_concurrency_limit=5, 
+    max_size=200                 
 )
 
 if __name__ == "__main__":