Feat/support parent child chunk (#12092)

2024-12-25 19:49:07 +08:00 · 2024-12-25 19:49:07 +08:00 · 9231fdbf4c
commit 9231fdbf4c
parent 017d7538ae
54 changed files with 2578 additions and 808 deletions
--- a/api/tasks/clean_dataset_task.py
+++ b/api/tasks/clean_dataset_task.py
@ -62,7 +62,7 @@ def clean_dataset_task(
            if doc_form is None:
                raise ValueError("Index type must be specified.")
            index_processor = IndexProcessorFactory(doc_form).init_index_processor()
-            index_processor.clean(dataset, None)
+            index_processor.clean(dataset, None, with_keywords=True, delete_child_chunks=True)

            for document in documents:
                db.session.delete(document)