Feat: add foundational support for RAPTOR dataset pipeline logs (#10277)

### What problem does this PR solve?

Add foundational support for RAPTOR dataset pipeline logs.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

api/db/db_models.py

@@ -651,6 +651,7 @@ class Knowledgebase(DataBaseModel):
     pagerank = IntegerField(default=0, index=False)
 
     graphrag_task_id = CharField(max_length=32, null=True, help_text="Graph RAG task ID", index=True)
+    raptor_task_id = CharField(max_length=32, null=True, help_text="RAPTOR task ID", index=True)
 
     status = CharField(max_length=1, null=True, help_text="is it validate(0: wasted, 1: validate)", default="1", index=True)
 
@@ -1079,4 +1080,8 @@ def migrate_db():
         migrate(migrator.add_column("knowledgebase", "graphrag_task_id", CharField(max_length=32, null=True, help_text="Gragh RAG task ID", index=True)))
     except Exception:
         pass
+    try:
+        migrate(migrator.add_column("knowledgebase", "raptor_task_id", CharField(max_length=32, null=True, help_text="RAPTOR task ID", index=True)))
+    except Exception:
+        pass
     logging.disable(logging.NOTSET)

api/db/services/document_service.py

@@ -342,8 +342,7 @@ class DocumentService(CommonService):
                                process_duration=cls.model.process_duration + duration).where(
             cls.model.id == doc_id).execute()
         if num == 0:
-            raise LookupError(
-                "Document not found which is supposed to be there")
+            logging.warning("Document not found which is supposed to be there")
         num = Knowledgebase.update(
             token_num=Knowledgebase.token_num +
                       token_num,
@@ -781,8 +780,9 @@ def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[])
     task["digest"] = hasher.hexdigest()
     bulk_insert_into_db(Task, [task], True)
 
-    if ty == "graphrag":
+    if ty in ["graphrag", "raptor"]:
         task["doc_ids"] = doc_ids
+        DocumentService.begin2parse(doc["id"])
     assert REDIS_CONN.queue_product(get_svr_queue_name(priority), message=task), "Can't access Redis. Please check the Redis' status."
     return task["id"]