feat(cron): Add RAGflow Graph Build Cron for periodic status updates and new builds

services/ragflow_service.py

@@ -426,6 +426,66 @@ class RAGFlowService:
             self._log(f"📄 Document found: {result.get('name')} (run={result.get('run')})")
         return result
 
+    async def trace_graphrag(self, dataset_id: str) -> Optional[Dict]:
+        """
+        Gibt den aktuellen Status des Knowledge-Graph-Builds zurueck.
+        GET /api/v1/datasets/{dataset_id}/trace_graphrag
+
+        Returns:
+            Dict mit 'progress' (0.0-1.0), 'task_id', 'progress_msg' etc.
+            None wenn noch kein Graph-Build gestartet wurde.
+        """
+        import aiohttp
+        url = f"{self.base_url.rstrip('/')}/api/v1/datasets/{dataset_id}/trace_graphrag"
+        headers = {'Authorization': f'Bearer {self.api_key}'}
+        async with aiohttp.ClientSession() as session:
+            async with session.get(url, headers=headers) as resp:
+                if resp.status not in (200, 201):
+                    text = await resp.text()
+                    raise RuntimeError(
+                        f"trace_graphrag HTTP {resp.status} fuer dataset {dataset_id}: {text}"
+                    )
+                data = await resp.json()
+                task = data.get('data')
+                if not task:
+                    return None
+                return {
+                    'task_id':      task.get('id', ''),
+                    'progress':     float(task.get('progress', 0.0)),
+                    'progress_msg': task.get('progress_msg', ''),
+                    'begin_at':     task.get('begin_at'),
+                    'update_date':  task.get('update_date'),
+                }
+
+    async def run_graphrag(self, dataset_id: str) -> str:
+        """
+        Startet bzw. aktualisiert den Knowledge Graph eines Datasets
+        via POST /api/v1/datasets/{id}/run_graphrag.
+
+        Returns:
+            graphrag_task_id (str) – leer wenn der Server keinen zurueckgibt.
+        """
+        import aiohttp
+        url = f"{self.base_url.rstrip('/')}/api/v1/datasets/{dataset_id}/run_graphrag"
+        headers = {
+            'Authorization': f'Bearer {self.api_key}',
+            'Content-Type': 'application/json',
+        }
+        async with aiohttp.ClientSession() as session:
+            async with session.post(url, headers=headers, json={}) as resp:
+                if resp.status not in (200, 201):
+                    text = await resp.text()
+                    raise RuntimeError(
+                        f"run_graphrag HTTP {resp.status} fuer dataset {dataset_id}: {text}"
+                    )
+                data = await resp.json()
+                task_id = (data.get('data') or {}).get('graphrag_task_id', '')
+                self._log(
+                    f"🔗 run_graphrag angestossen fuer {dataset_id[:16]}…"
+                    + (f" task_id={task_id}" if task_id else "")
+                )
+                return task_id
+
     async def wait_for_parsing(
         self,
         dataset_id: str,