fix image files not deleted on indexing_estimate #9541 (#10798)

Co-authored-by: root <root@localhost.localdomain>
langgenius · Nov 21, 2024 · 94c9cad · 94c9cad
1 parent 2ae6460
commit 94c9cad
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 0 deletions.
diff --git a/api/core/indexing_runner.py b/api/core/indexing_runner.py
@@ -30,6 +30,7 @@
 )
 from core.rag.splitter.text_splitter import TextSplitter
 from core.tools.utils.text_processing_utils import remove_leading_symbols
+from core.tools.utils.web_reader_tool import get_image_upload_file_ids
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
 from extensions.ext_storage import storage
@@ -279,6 +280,19 @@ def indexing_estimate(
                 if len(preview_texts) < 5:
                     preview_texts.append(document.page_content)
 
+                # delete image files and related db records
+                image_upload_file_ids = get_image_upload_file_ids(document.page_content)
+                for upload_file_id in image_upload_file_ids:
+                    image_file = db.session.query(UploadFile).filter(UploadFile.id == upload_file_id).first()
+                    try:
+                        storage.delete(image_file.key)
+                    except Exception:
+                        logging.exception(
+                            "Delete image_files failed while indexing_estimate, \
+                                          image_upload_file_is: {}".format(upload_file_id)
+                        )
+                    db.session.delete(image_file)
+
         if doc_form and doc_form == "qa_model":
             if len(preview_texts) > 0:
                 # qa model document

diff --git a/api/tasks/clean_dataset_task.py b/api/tasks/clean_dataset_task.py
@@ -78,6 +78,7 @@ def clean_dataset_task(
                             "Delete image_files failed when storage deleted, \
                                           image_upload_file_is: {}".format(upload_file_id)
                         )
+                    db.session.delete(image_file)
                 db.session.delete(segment)
 
         db.session.query(DatasetProcessRule).filter(DatasetProcessRule.dataset_id == dataset_id).delete()

diff --git a/api/tasks/clean_document_task.py b/api/tasks/clean_document_task.py
@@ -51,6 +51,7 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
                             "Delete image_files failed when storage deleted, \
                                           image_upload_file_is: {}".format(upload_file_id)
                         )
+                    db.session.delete(image_file)
                 db.session.delete(segment)
 
             db.session.commit()