add data viewer

app/main.py

@@ -694,6 +694,65 @@ async def update_all_documents():
         logger.error(f"[API] Error in update_all_documents: {e}")
         raise HTTPException(status_code=500, detail=f"Lỗi: {str(e)}")
 
+@app.get("/api/document-chunks/view")
+@timing_decorator_async
+async def view_all_document_chunks():
+    """
+    API xem toàn bộ dữ liệu trong bảng document_chunks.
+    """
+    try:
+        logger.info("[API] Starting view all document chunks")
+        
+        # Lấy dữ liệu từ Supabase
+        chunks_data = supabase_client.get_all_document_chunks()
+        
+        # Thống kê cơ bản
+        total_chunks = len(chunks_data)
+        unique_documents = len(set(chunk.get('vanbanid') for chunk in chunks_data if chunk.get('vanbanid')))
+        
+        # Nhóm theo vanbanid để thống kê và tổ chức data
+        chunks_by_document = {}
+        for chunk in chunks_data:
+            vanbanid = chunk.get('vanbanid')
+            if vanbanid not in chunks_by_document:
+                chunks_by_document[vanbanid] = []
+            chunks_by_document[vanbanid].append(chunk)
+        
+        # Thống kê chi tiết
+        document_stats = []
+        grouped_data = []
+        
+        for vanbanid, chunks in chunks_by_document.items():
+            # Thống kê
+            document_stats.append({
+                "vanbanid": vanbanid,
+                "chunk_count": len(chunks),
+                "document_title": chunks[0].get('document_title', 'Unknown') if chunks else 'Unknown'
+            })
+            
+            # Nhóm data theo vanbanid
+            grouped_data.append({
+                "vanbanid": vanbanid,
+                "document_title": chunks[0].get('document_title', 'Unknown') if chunks else 'Unknown',
+                "chunk_count": len(chunks),
+                "chunks": chunks
+            })
+        
+        return {
+            "status": "success",
+            "message": f"Đã lấy {total_chunks} chunks từ {unique_documents} văn bản",
+            "summary": {
+                "total_chunks": total_chunks,
+                "unique_documents": unique_documents,
+                "document_stats": document_stats
+            },
+            "data": grouped_data
+        }
+        
+    except Exception as e:
+        logger.error(f"[API] Error in view_all_document_chunks: {e}")
+        raise HTTPException(status_code=500, detail=f"Lỗi: {str(e)}")
+
 @app.get("/api/document-chunks/status")
 @timing_decorator_async
 async def get_document_chunks_status():

app/supabase_db.py

@@ -176,4 +176,26 @@ class SupabaseClient:
             return True
         except Exception as e:
             logger.error(f"Error deleting chunks for vanbanid {vanbanid}: {e}")
-            return False 
+            return False
+
+    @timing_decorator_sync
+    def get_all_document_chunks(self) -> List[Dict[str, Any]]:
+        """
+        Lấy toàn bộ dữ liệu từ bảng document_chunks.
+        Output: List[Dict] - danh sách tất cả chunks
+        """
+        try:
+            logger.info("[SUPABASE] Fetching all document chunks")
+            
+            response = self.client.table('document_chunks').select('*').execute()
+            
+            if response.data:
+                logger.info(f"[SUPABASE] Successfully fetched {len(response.data)} document chunks")
+                return response.data
+            else:
+                logger.warning("[SUPABASE] No document chunks found")
+                return []
+                
+        except Exception as e:
+            logger.error(f"[SUPABASE] Error fetching document chunks: {e}")
+            return []