update

src/recommendation_engine/chatbot_engine.py

@@ -1233,6 +1233,10 @@ Choose what you want:
 
             analysis["domain"] = detected
             analysis["intent"] = "idea"
+            
+            # Prevent treating the domain name as a weak project title
+            if "project_title" in analysis:
+                del analysis["project_title"]
 
         else:
 

src/recommendation_engine/context_builder.py

@@ -21,80 +21,48 @@ from src.recommendation_engine.config import (
 logger = logging.getLogger(__name__)
 
 DOMAIN_KEYWORDS = {
-    "artificial intelligence": [
-        "ai",
-        "artificial intelligence",
-        "machine learning",
-        "ml",
-        "deep learning",
-        "neural network",
-        "nlp",
-        "computer vision"
+    "AI & Machine Learning": [
+        "ai", "artificial intelligence", "machine learning", "ml", "deep learning",
+        "neural network", "nlp", "computer vision"
     ],
-
-    "healthcare": [
-        "hospital",
-        "health",
-        "medical",
-        "healthcare",
-        "clinic",
-        "patient"
+    "Business & Finance": [
+        "fintech", "finance", "bank", "payment", "crypto", "blockchain", "business", "trading"
     ],
-
-    "fintech": [
-        "fintech",
-        "finance",
-        "bank",
-        "payment",
-        "crypto",
-        "blockchain"
+    "Cloud & DevOps": [
+        "cloud", "devops", "aws", "azure", "docker", "kubernetes", "infrastructure"
     ],
-
-    "education": [
-        "education",
-        "school",
-        "learning",
-        "edtech",
-        "student",
-        "university"
+    "Cybersecurity": [
+        "security", "cyber", "cybersecurity", "threat", "attack", "malware", "hacking"
     ],
-
-    "ecommerce": [
-        "ecommerce",
-        "shopping",
-        "retail",
-        "store",
-        "marketplace"
+    "Education": [
+        "education", "school", "learning", "edtech", "student", "university", "academic"
     ],
-
-    "agriculture": [
-        "agriculture",
-        "farming",
-        "crop",
-        "livestock",
-        "smart farming"
+    "Healthcare": [
+        "hospital", "health", "medical", "healthcare", "clinic", "patient", "care"
     ],
-
-    "security": [
-        "security",
-        "cyber",
-        "cybersecurity",
-        "threat",
-        "attack",
-        "malware"
+    "IoT & Embedded Systems": [
+        "iot", "embedded", "hardware", "sensor", "arduino", "raspberry", "smart home"
     ],
-
-    "general": [
-        "general",
-        "random",
-        "anything",
-        "any",
-        "whatever",
-        "surprise me",
-        "mixed",
-        "all",
-        "open",
-        "everything"
+    "Web & Mobile Development": [
+        "web", "mobile", "app", "ios", "android", "frontend", "backend", "fullstack", "website"
+    ],
+    "Data Science & Analytics": [
+        "data", "analytics", "science", "big data", "dashboard", "statistics"
+    ],
+    "E-Commerce & Marketplaces": [
+        "ecommerce", "shopping", "retail", "store", "marketplace", "shop"
+    ],
+    "Smart Systems": [
+        "smart system", "automation", "smart city", "smart"
+    ],
+    "Networking & Communication": [
+        "networking", "communication", "telecom", "5g", "network"
+    ],
+    "Game Development": [
+        "game", "gaming", "unity", "unreal", "ar", "vr"
+    ],
+    "Others": [
+        "general", "random", "anything", "any", "whatever", "surprise me", "mixed", "all", "open", "everything", "other"
     ]
 }
 
@@ -222,7 +190,7 @@ def extract_domain(text: str) -> str:
 
                 return domain
 
-    return ""
+    return "Others"
 
 @lru_cache(maxsize=100)
 def cached_similarity(

src/recommendation_engine/validator.py

@@ -208,15 +208,11 @@ def smart_split(text: str) -> List[str]:
             if not p:
                 continue
 
-            
-            subparts = re.split(r"\s*[-•▪]\s*", p)
-
-            for sp in subparts:
-
-                sp = sp.strip()
+            # Remove leading bullets or hyphens instead of splitting the whole string
+            p = re.sub(r"^[-•▪*]\s*", "", p).strip()
 
-                if sp:
-                    lines.append(sp)
+            if p:
+                lines.append(p)
 
     return lines