From 65c3f0406c101cd836570d8842e5c4ea978213a5 Mon Sep 17 00:00:00 2001
From: Yongteng Lei <yongtengrey@outlook.com>
Date: Mon, 13 Oct 2025 11:53:48 +0800
Subject: [PATCH] Fix: maintain backward compatibility for KB tasks (#10508)

### What problem does this PR solve?

Maintain backward compatibility for KB tasks

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 api/apps/kb_app.py       | 16 ++++++++++++----
 rag/svr/task_executor.py | 41 +++++++++++++++++++++++++++++++++++-----
 2 files changed, 48 insertions(+), 9 deletions(-)

diff --git a/api/apps/kb_app.py b/api/apps/kb_app.py
index bca28fb6f..141f1f5d4 100644
--- a/api/apps/kb_app.py
+++ b/api/apps/kb_app.py
@@ -36,6 +36,7 @@ from api import settings
 from rag.nlp import search
 from api.constants import DATASET_NAME_LIMIT
 from rag.settings import PAGERANK_FLD
+from rag.utils.redis_conn import REDIS_CONN
 from rag.utils.storage_factory import STORAGE_IMPL
 
 
@@ -760,18 +761,25 @@ def delete_kb_task():
     match pipeline_task_type:
         case PipelineTaskType.GRAPH_RAG:
             settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]}, search.index_name(kb.tenant_id), kb_id)
-            kb_task_id = "graphrag_task_id"
+            kb_task_id_field = "graphrag_task_id"
+            task_id = kb.graphrag_task_id
             kb_task_finish_at = "graphrag_task_finish_at"
         case PipelineTaskType.RAPTOR:
-            kb_task_id = "raptor_task_id"
+            kb_task_id_field = "raptor_task_id"
+            task_id = kb.raptor_task_id
             kb_task_finish_at = "raptor_task_finish_at"
         case PipelineTaskType.MINDMAP:
-            kb_task_id = "mindmap_task_id"
+            kb_task_id_field = "mindmap_task_id"
+            task_id = kb.mindmap_task_id
             kb_task_finish_at = "mindmap_task_finish_at"
         case _:
             return get_error_data_result(message="Internal Error: Invalid task type")
 
-    ok = KnowledgebaseService.update_by_id(kb_id, {kb_task_id: "", kb_task_finish_at: None})
+    def cancel_task(task_id):
+        REDIS_CONN.set(f"{task_id}-cancel", "x")
+    cancel_task(task_id)
+
+    ok = KnowledgebaseService.update_by_id(kb_id, {kb_task_id_field: "", kb_task_finish_at: None})
     if not ok:
         return server_error_response(f"Internal error: cannot delete task {pipeline_task_type}")
 
diff --git a/rag/svr/task_executor.py b/rag/svr/task_executor.py
index c0b1d2c51..9801b53dd 100644
--- a/rag/svr/task_executor.py
+++ b/rag/svr/task_executor.py
@@ -691,7 +691,7 @@ async def run_raptor_for_kb(row, kb_parser_config, chat_mdl, embd_mdl, vector_si
         raptor_config["threshold"],
     )
     original_length = len(chunks)
-    chunks = await raptor(chunks, row["kb_parser_config"]["raptor"]["random_seed"], callback)
+    chunks = await raptor(chunks, kb_parser_config["raptor"]["random_seed"], callback)
     doc = {
         "doc_id": fake_doc_id,
         "kb_id": [str(row["kb_id"])],
@@ -814,8 +814,22 @@ async def do_handle_task(task):
 
         kb_parser_config = kb.parser_config
         if not kb_parser_config.get("raptor", {}).get("use_raptor", False):
-            progress_callback(prog=-1.0, msg="Internal error: Invalid RAPTOR configuration")
-            return
+            kb_parser_config.update(
+                {
+                    "raptor": {
+                        "use_raptor": True,
+                        "prompt": "Please summarize the following paragraphs. Be careful with the numbers, do not make things up. Paragraphs as following:\n      {cluster_content}\nThe above is the content you need to summarize.",
+                        "max_token": 256,
+                        "threshold": 0.1,
+                        "max_cluster": 64,
+                        "random_seed": 0,
+                    },
+                }
+            )
+            if not KnowledgebaseService.update_by_id(kb.id, {"parser_config":kb_parser_config}):
+                progress_callback(prog=-1.0, msg="Internal error: Invalid RAPTOR configuration")
+                return
+
         # bind LLM for raptor
         chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
         # run RAPTOR
@@ -838,8 +852,25 @@ async def do_handle_task(task):
 
         kb_parser_config = kb.parser_config
         if not kb_parser_config.get("graphrag", {}).get("use_graphrag", False):
-            progress_callback(prog=-1.0, msg="Internal error: Invalid GraphRAG configuration")
-            return
+            kb_parser_config.update(
+                {
+                    "graphrag": {
+                        "use_graphrag": True,
+                        "entity_types": [
+                            "organization",
+                            "person",
+                            "geo",
+                            "event",
+                            "category",
+                        ],
+                        "method": "light",
+                    }
+                }
+            )
+            if not KnowledgebaseService.update_by_id(kb.id, {"parser_config":kb_parser_config}):
+                progress_callback(prog=-1.0, msg="Internal error: Invalid GraphRAG configuration")
+                return
+
 
         graphrag_conf = kb_parser_config.get("graphrag", {})
         start_ts = timer()