fix: replace get_byte() with get_bytes() for consistency in file handling

This commit is contained in:
CaptainB 2025-06-25 10:53:43 +08:00
parent 93530e0a9b
commit 758f424000
4 changed files with 6 additions and 5 deletions

View File

@ -66,7 +66,7 @@ class BaseDocumentExtractNode(IDocumentExtractNode):
for doc in document:
file = QuerySet(File).filter(id=doc['file_id']).first()
buffer = io.BytesIO(file.get_byte().tobytes())
buffer = io.BytesIO(file.get_bytes().tobytes())
buffer.name = doc['name'] # this is the important line
for split_handle in (parse_table_handle_list + split_handles):

View File

@ -59,7 +59,7 @@ def write_context(node_variable: Dict, workflow_variable: Dict, node: INode, wor
def file_id_to_base64(file_id: str):
file = QuerySet(File).filter(id=file_id).first()
file_bytes = file.get_byte()
file_bytes = file.get_bytes()
base64_image = base64.b64encode(file_bytes).decode("utf-8")
return [base64_image, what(None, file_bytes.tobytes())]
@ -171,7 +171,7 @@ class BaseImageUnderstandNode(IImageUnderstandNode):
for img in image:
file_id = img['file_id']
file = QuerySet(File).filter(id=file_id).first()
image_bytes = file.get_byte()
image_bytes = file.get_bytes()
base64_image = base64.b64encode(image_bytes).decode("utf-8")
image_format = what(None, image_bytes.tobytes())
images.append(

View File

@ -30,7 +30,7 @@ class BaseSpeechToTextNode(ISpeechToTextNode):
# 根据file_name 吧文件转成mp3格式
file_format = file.file_name.split('.')[-1]
with tempfile.NamedTemporaryFile(delete=False, suffix=f'.{file_format}') as temp_file:
temp_file.write(file.get_byte().tobytes())
temp_file.write(file.get_bytes().tobytes())
temp_file_path = temp_file.name
with tempfile.NamedTemporaryFile(delete=False, suffix='.mp3') as temp_amr_file:
temp_mp3_path = temp_amr_file.name

View File

@ -558,7 +558,8 @@ class DocumentSerializers(serializers.Serializer):
def download_source_file(self):
self.is_valid(raise_exception=True)
return FileSerializer.Operate(id=self.data.get('knowledge_id')).get(with_valid=True)
file = QuerySet(File).filter(source_id=self.data.get('document_id')).first()
return FileSerializer.Operate(id=file.id).get(with_valid=True)
def one(self, with_valid=False):
if with_valid: