context aware retireval

self_hosted_env/voice_agent/All_Curriculums_grouped.json

+{
+  "Grade 4 Arabic curriculum": {
+    "الوحدة الأولى: الأنظمة الحية": {
+      "مقدمة": [
+        9,
+        12
+      ],
+      "المفاهيم": {
+        "المفهوم 1.1: التكيف والبقاء": {},
+        "المفهوم 2.1: كيف تعمل الحواس؟": {},
+        "المفهوم 3.1: الضوء وحاسة البصر": {}
+      },
+      "مشروع الوحدة": [
+        63,
+        64
+      ],
+      "المشروع بيني التخصصات": [
+        65,
+        72
+      ],
+      "قيم تعلمك": [
+        73,
+        74
+      ]
+    },
+    "الوحدة الثانية: الحركة والطاقة": {
+      "مقدمة": [
+        75,
+        78
+      ],
+      "المفاهيم": {
+        "المفهوم 1.2: الحركة والتوقف": {},
+        "المفهوم 2.2: الطاقة والحركة": {},
+        "المفهوم 3.2: الطاقة والتصادم": {}
+      },
+      "مشروع الوحدة": [
+        121,
+        122
+      ],
+      "قيم تعلمك": [
+        123,
+        124
+      ],
+      "السلامة في فصول العلوم": [
+        125,
+        126
+      ]
+    }
+  },
+  "Grade 5 English curriculum": {
+    "Unit 1: Interactions of Organisms": {
+      "Get Started": [
+        10,
+        13
+      ],
+      "Concepts": {
+        "Concept 1.1 Plant Needs": {},
+        "Concept 1.2 Energy Flow in Ecosystems": {},
+        "Concept 1.3 Changes in Food Webs": {}
+      },
+      "Unit Project": [
+        59,
+        59
+      ],
+      "Interdisciplinary project": [
+        60,
+        67
+      ],
+      "Assess your learning": [
+        68,
+        69
+      ]
+    },
+    "Unit 2: Particles in Motion": {
+      "Get Started": [
+        70,
+        73
+      ],
+      "Concepts": {
+        "Concept 2.1 Matter in the World around Us": {},
+        "Concept 2.2 Describing and Measuring Matter": {},
+        "Concept 2.3 Comparing Changes in Matter": {}
+      },
+      "Unit Project": [
+        124,
+        125
+      ],
+      "Assess your learning": [
+        126,
+        127
+      ]
+    }
+  },
+  "Grade 6 Arabic curriculum": {
+    "الوحدة الأولى: ما النظام؟": {
+      "مقدمة": [
+        8,
+        11
+      ],
+      "المفاهيم": {
+        "المفهوم 1.1: الخليه كنظام": {},
+        "المفهوم 2.1: الجسم كنظام": {},
+        "المفهوم 3.1: الطاقة كنظام": {}
+      },
+      "مشروع الوحدة": [
+        73,
+        75
+      ],
+      "تقييم الوحدة": [
+        76,
+        79
+      ]
+    },
+    "الوحدة الثانية: الحصول على الطاقة": {
+      "مقدمة": [
+        80,
+        83
+      ],
+      "المفاهيم": {
+        "المفهوم 1.2: الطاقة الحرارية وحالات المادة": {},
+        "المفهوم 2.2: انتقال الحرارة": {}
+      },
+      "مشروع الوحدة": [
+        120,
+        121
+      ],
+      "المشروع بيني التخصصات": [
+        122,
+        130
+      ],
+      "تقييم الوحدة": [
+        131,
+        134
+      ]
+    }
+  },
+  "Grade 6 English curriculum": {
+    "Unit 1: What is system": {
+      "Get Started": [
+        9,
+        12
+      ],
+      "Concepts": {
+        "Concept 1.1 The cell as a system": {},
+        "Concept 1.2 The body as a system": {},
+        "Concept 1.3 Energy as a system": {}
+      },
+      "Unit Project": [
+        74,
+        76
+      ],
+      "Unit assessment": [
+        77,
+        80
+      ]
+    },
+    "Unit 2: Getting energy": {
+      "Get Started": [
+        81,
+        84
+      ],
+      "Concepts": {
+        "Concept 2.1 Thermal energy and states of matter": {},
+        "Concept 2.2 Heat transfer": {}
+      },
+      "Unit Project": [
+        121,
+        122
+      ],
+      "Interdisciplinary project": [
+        123,
+        131
+      ],
+      "Unit assessment": [
+        132,
+        135
+      ]
+    }
+  }
+}
\ No newline at end of file

self_hosted_env/voice_agent/core/__init__.py

-from .enums import MessageType, ResponseStatus, StudentNationality, Models
+from .enums import MessageType, ResponseStatus, StudentNationality, Models, StudyLanguage
 from .config import AppConfig
\ No newline at end of file

self_hosted_env/voice_agent/core/enums.py

@@ -21,3 +21,8 @@ class Models(str, Enum):
     tts = "gpt-4o-mini-tts"
     embedding = "text-embedding-3-small"
     transcription = "gpt-4o-transcribe"
+
+
+class StudyLanguage(Enum):
+    ARABIC = "ARABIC"
+    ENGLISH = "ENGLISH"
\ No newline at end of file

self_hosted_env/voice_agent/services/chat_database_service.py

@@ -4,11 +4,15 @@ from psycopg2.extras import RealDictCursor
 from typing import List, Dict, Optional, Tuple
 import logging
 from services.connection_pool import ConnectionPool
-
-
+from enum import Enum
+import sys
+import os
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+from core import StudyLanguage
 logger = logging.getLogger(__name__)
 
 
+
 class ChatDatabaseService:
     """Service for managing chat history using a shared, robust connection pool"""
 
@@ -27,7 +31,7 @@ class ChatDatabaseService:
                 return result["nationality"] if result else None
 
     def get_student_info(self, student_id: str) -> Optional[Dict]:
-        """Get complete student information from database"""
+        """Get complete student information with explicit language awareness"""
         with self.pool_handler.get_connection() as conn:
             with conn.cursor(cursor_factory=RealDictCursor) as cur:
                 cur.execute(
@@ -40,17 +44,20 @@ class ChatDatabaseService:
                 )
                 result = cur.fetchone()
                 if result:
+                    # Convert boolean to explicit language enum
+                    study_language = StudyLanguage.ARABIC if result['language'] else StudyLanguage.ENGLISH
                     return {
                         'student_id': result['student_id'],
                         'student_name': result['student_name'],
                         'grade': result['grade'],
-                        'is_arabic': result['language'],
+                        'study_language': study_language,  # Explicit language enum
+                        'is_arabic': result['language'],   # Keep for backward compatibility
                         'nationality': result['nationality']
                     }
                 return None
 
-    def get_student_grade_and_language(self, student_id: str) -> Optional[Tuple[int, bool]]:
-        """Get student grade and language preference"""
+    def get_student_grade_and_language(self, student_id: str) -> Optional[Tuple[int, bool, StudyLanguage]]:
+        """Get student grade, language preference, and explicit study language"""
         with self.pool_handler.get_connection() as conn:
             with conn.cursor(cursor_factory=RealDictCursor) as cur:
                 cur.execute(
@@ -59,7 +66,8 @@ class ChatDatabaseService:
                 )
                 result = cur.fetchone()
                 if result:
-                    return (result["grade"], result["language"])
+                    study_language = StudyLanguage.ARABIC if result['language'] else StudyLanguage.ENGLISH
+                    return (result["grade"], result["language"], study_language)
                 return None
 
     def get_chat_history(self, student_id: str, limit: int = 20) -> List[Dict[str, str]]:
@@ -153,6 +161,11 @@ class ChatDatabaseService:
                         params
                     )
                     conn.commit()
+                    
+                    # Log the language update explicitly
+                    if language is not None:
+                        study_language = StudyLanguage.ARABIC if language else StudyLanguage.ENGLISH
+                        logger.info(f"Updated student {student_id} language to {study_language.value}")
 
     def create_student(self, student_id: str, student_name: str, grade: int, 
                       language: bool, nationality: str = 'EGYPTIAN'):
@@ -168,3 +181,52 @@ class ChatDatabaseService:
                     (student_id, student_name, grade, language, nationality)
                 )
                 conn.commit()
+                
+                # Log the explicit language information
+                study_language = StudyLanguage.ARABIC if language else StudyLanguage.ENGLISH
+                logger.info(f"Created student {student_id} ({student_name}) - Grade: {grade}, Language: {study_language.value}, Nationality: {nationality}")
+
+    def get_student_language_summary(self, student_id: str) -> Optional[Dict[str, str]]:
+        """Get a human-readable summary of student's language settings"""
+        student_info = self.get_student_info(student_id)
+        if not student_info:
+            return None
+            
+        nationality_desc = "مصري" if student_info['nationality'].lower() == "egyptian" else "سعودي"
+        language_desc = "بالعربي" if student_info['study_language'] == StudyLanguage.ARABIC else "بالإنجليزي"
+        
+        return {
+            "student_id": student_id,
+            "student_name": student_info['student_name'],
+            "study_language": student_info['study_language'].value,
+            "nationality": student_info['nationality'],
+            "grade": str(student_info['grade']),
+            "description": f"طالب {nationality_desc} في الصف {student_info['grade']} يدرس {language_desc}"
+        }
+
+    def get_students_by_language(self, study_language: StudyLanguage) -> List[Dict]:
+        """Get all students who study in a specific language"""
+        language_bool = True if study_language == StudyLanguage.ARABIC else False
+        
+        with self.pool_handler.get_connection() as conn:
+            with conn.cursor(cursor_factory=RealDictCursor) as cur:
+                cur.execute(
+                    """
+                    SELECT student_id, student_name, grade, nationality
+                    FROM students 
+                    WHERE language = %s
+                    ORDER BY grade, student_name
+                    """,
+                    (language_bool,)
+                )
+                results = cur.fetchall()
+                return [
+                    {
+                        'student_id': row['student_id'],
+                        'student_name': row['student_name'],
+                        'grade': row['grade'],
+                        'nationality': row['nationality'],
+                        'study_language': study_language.value
+                    }
+                    for row in results
+                ]
\ No newline at end of file

self_hosted_env/voice_agent/start.sh

@@ -8,6 +8,8 @@ echo "Setting up schema and inserting data..."
 python apply_test_schema.py
 python insert_csv_embeddings.py
 echo "Database setup complete."
+python curriculum_structure.py
+echo "Curriculum structure setup complete."
 
 sleep 5
 # Start the web server and keep it as the main process