zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-06-29 15:31:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(api): use dataset-owner tenant for legacy /chunks docstore cleanup (#15961)

Browse Source
This commit is contained in:
kpdev
2026-06-23 23:24:40 -07:00
committed by GitHub
parent ede46e0bb8
commit 68d2ca0ff1
2 changed files with 83 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
api/apps/restful_apis/chunk_api.py
View File

@@ -162,6 +162,9 @@ def _enrich_chunks_with_document_metadata(chunks: list[dict], metadata_fields=No
async def parse(tenant_id, dataset_id):
if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
dataset_tenant_id = _get_dataset_tenant_id(dataset_id)
if not dataset_tenant_id:
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
req = await get_request_json()
if not req.get("document_ids"):
return get_error_data_result("`document_ids` is required")
@@ -190,15 +193,15 @@ async def parse(tenant_id, dataset_id):
== 0
):
return get_error_data_result("Can't parse document that is currently being processed")
index_name = search.index_name(tenant_id)
if settings.docStoreConn.index_exist(index_name, dataset_id):
settings.docStoreConn.delete({"doc_id": id}, index_name, dataset_id)
index_name = search.index_name(dataset_tenant_id)
if settings.docStoreConn.index_exist(index_name, doc[0].kb_id):
settings.docStoreConn.delete({"doc_id": id}, index_name, doc[0].kb_id)
else:
logging.info(
"Skipping chunk delete during parse for doc %s: index %s/%s does not exist",
id,
index_name,
dataset_id,
doc[0].kb_id,
)
TaskService.filter_delete([Task.doc_id == id])
e, doc = DocumentService.get_by_id(id)
@@ -227,6 +230,9 @@ async def parse(tenant_id, dataset_id):
async def stop_parsing(tenant_id, dataset_id):
if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
dataset_tenant_id = _get_dataset_tenant_id(dataset_id)
if not dataset_tenant_id:
return get_error_data_result(message=f"You don't own the dataset {dataset_id}.")
req = await get_request_json()
if not req.get("document_ids"):
@@ -249,15 +255,15 @@ async def stop_parsing(tenant_id, dataset_id):
cancel_all_task_of(id)
info = {"run": "2", "progress": 0, "chunk_num": 0}
DocumentService.update_by_id(id, info)
index_name = search.index_name(tenant_id)
if settings.docStoreConn.index_exist(index_name, dataset_id):
settings.docStoreConn.delete({"doc_id": doc[0].id}, index_name, dataset_id)
index_name = search.index_name(dataset_tenant_id)
if settings.docStoreConn.index_exist(index_name, doc[0].kb_id):
settings.docStoreConn.delete({"doc_id": doc[0].id}, index_name, doc[0].kb_id)
else:
logging.info(
"Skipping chunk delete during stop_parsing for doc %s: index %s/%s does not exist",
doc[0].id,
index_name,
dataset_id,
doc[0].kb_id,
)
success_count += 1
if duplicate_messages: