Update utils/database.py

utils/database.py

@@ -170,7 +170,7 @@ def verify_vector_store(vector_store):
         return False
 
 
-# utils/database.py
+
 
 def handle_document_upload(uploaded_files, **kwargs):
     """
@@ -323,6 +323,137 @@ def handle_document_upload(uploaded_files, **kwargs):
         st.session_state.chat_ready = False
         return False
 
+
+
+def get_all_documents(conn: sqlite3.Connection) -> List[Dict]:
+    """
+    Get all documents with their metadata and collection info.
+    
+    Args:
+        conn (sqlite3.Connection): Database connection
+        
+    Returns:
+        List[Dict]: List of documents with their metadata
+    """
+    try:
+        with conn_lock:
+            cursor = conn.cursor()
+            cursor.execute('''
+                SELECT 
+                    d.id,
+                    d.name,
+                    d.content,
+                    d.upload_date,
+                    GROUP_CONCAT(c.name) as collections
+                FROM documents d
+                LEFT JOIN document_collections dc ON d.id = dc.document_id
+                LEFT JOIN collections c ON dc.collection_id = c.id
+                GROUP BY d.id
+                ORDER BY d.upload_date DESC
+            ''')
+            
+            documents = []
+            for row in cursor.fetchall():
+                documents.append({
+                    'id': row[0],
+                    'name': row[1],
+                    'content': row[2],
+                    'upload_date': row[3],
+                    'collections': row[4].split(',') if row[4] else []
+                })
+            return documents
+            
+    except sqlite3.Error as e:
+        st.error(f"Error retrieving documents: {e}")
+        return []
+
+def get_document_by_id(conn: sqlite3.Connection, document_id: int) -> Optional[Dict]:
+    """
+    Get a single document by its ID.
+    
+    Args:
+        conn (sqlite3.Connection): Database connection
+        document_id (int): ID of the document to retrieve
+        
+    Returns:
+        Optional[Dict]: Document data if found, None otherwise
+    """
+    try:
+        with conn_lock:
+            cursor = conn.cursor()
+            cursor.execute('''
+                SELECT 
+                    d.id,
+                    d.name,
+                    d.content,
+                    d.upload_date,
+                    GROUP_CONCAT(c.name) as collections
+                FROM documents d
+                LEFT JOIN document_collections dc ON d.id = dc.document_id
+                LEFT JOIN collections c ON dc.collection_id = c.id
+                WHERE d.id = ?
+                GROUP BY d.id
+            ''', (document_id,))
+            
+            row = cursor.fetchone()
+            if row:
+                return {
+                    'id': row[0],
+                    'name': row[1],
+                    'content': row[2],
+                    'upload_date': row[3],
+                    'collections': row[4].split(',') if row[4] else []
+                }
+            return None
+            
+    except sqlite3.Error as e:
+        st.error(f"Error retrieving document: {e}")
+        return None
+
+def get_recent_documents(conn: sqlite3.Connection, limit: int = 5) -> List[Dict]:
+    """
+    Get most recently uploaded documents.
+    
+    Args:
+        conn (sqlite3.Connection): Database connection
+        limit (int): Maximum number of documents to return
+        
+    Returns:
+        List[Dict]: List of recent documents
+    """
+    try:
+        with conn_lock:
+            cursor = conn.cursor()
+            cursor.execute('''
+                SELECT 
+                    d.id,
+                    d.name,
+                    d.content,
+                    d.upload_date,
+                    GROUP_CONCAT(c.name) as collections
+                FROM documents d
+                LEFT JOIN document_collections dc ON d.id = dc.document_id
+                LEFT JOIN collections c ON dc.collection_id = c.id
+                GROUP BY d.id
+                ORDER BY d.upload_date DESC
+                LIMIT ?
+            ''', (limit,))
+            
+            documents = []
+            for row in cursor.fetchall():
+                documents.append({
+                    'id': row[0],
+                    'name': row[1],
+                    'content': row[2],
+                    'upload_date': row[3],
+                    'collections': row[4].split(',') if row[4] else []
+                })
+            return documents
+            
+    except sqlite3.Error as e:
+        st.error(f"Error retrieving recent documents: {e}")
+        return []
+
 def process_document(file_path):
     """
     Process a PDF document with proper chunking.