youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-23 12:16:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Merge branch 'deploy/dev' into feat/knowledgebase-summaryIndex"

Browse Source 
This reverts commit ce304f2da7, reversing
changes made to 334888dac9.
This commit is contained in:
FFXN
2026-01-28 17:59:41 +08:00
parent 07415e8ef9
commit b2d0afb14c
8 changed files with 12 additions and 1369 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
api/core/workflow/nodes/document_extractor/node.py
View File

@ -62,21 +62,6 @@ class DocumentExtractorNode(Node[DocumentExtractorNodeData]):
inputs = {"variable_selector": variable_selector}
process_data = {"documents": value if isinstance(value, list) else [value]}
# Ensure storage_key is loaded for File objects
files_to_check = value if isinstance(value, list) else [value]
files_needing_storage_key = [
f for f in files_to_check if isinstance(f, File) and not f.storage_key and f.related_id
]
if files_needing_storage_key:
from sqlalchemy.orm import Session
from extensions.ext_database import db
from factories.file_factory import StorageKeyLoader
with Session(bind=db.engine) as session:
storage_key_loader = StorageKeyLoader(session, tenant_id=self.tenant_id)
storage_key_loader.load_storage_keys(files_needing_storage_key)
try:
if isinstance(value, list):
extracted_text_list = list(map(_extract_text_from_file, value))
@ -430,16 +415,6 @@ def _download_file_content(file: File) -> bytes:
response.raise_for_status()
return response.content
else:
# Check if storage_key is set
if not file.storage_key:
raise FileDownloadError(f"File storage_key is missing for file: {file.filename}")
# Check if file exists before downloading
from extensions.ext_storage import storage
if not storage.exists(file.storage_key):
raise FileDownloadError(f"File not found in storage: {file.storage_key}")
return file_manager.download(file)
except Exception as e:
raise FileDownloadError(f"Error downloading file: {str(e)}") from e

69
api/migrations/versions/2026_01_12_1358-562dcce7d77c_add_summaryindex_feature.py
View File

@ -1,69 +0,0 @@
"""add SummaryIndex feature
Revision ID: 562dcce7d77c
Revises: 03ea244985ce
Create Date: 2026-01-12 13:58:40.584802
"""
from alembic import op
import models as models
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = '562dcce7d77c'
down_revision = '03ea244985ce'
branch_labels = None
depends_on = None
def upgrade():
# ### commands auto generated by Alembic - please adjust! ###
op.create_table('document_segment_summary',
sa.Column('id', models.types.StringUUID(), nullable=False),
sa.Column('dataset_id', models.types.StringUUID(), nullable=False),
sa.Column('document_id', models.types.StringUUID(), nullable=False),
sa.Column('chunk_id', models.types.StringUUID(), nullable=False),
sa.Column('summary_content', models.types.LongText(), nullable=True),
sa.Column('summary_index_node_id', sa.String(length=255), nullable=True),
sa.Column('summary_index_node_hash', sa.String(length=255), nullable=True),
sa.Column('status', sa.String(length=32), server_default=sa.text("'generating'"), nullable=False),
sa.Column('error', models.types.LongText(), nullable=True),
sa.Column('enabled', sa.Boolean(), server_default=sa.text('true'), nullable=False),
sa.Column('disabled_at', sa.DateTime(), nullable=True),
sa.Column('disabled_by', models.types.StringUUID(), nullable=True),
sa.Column('created_at', sa.DateTime(), server_default=sa.text('CURRENT_TIMESTAMP'), nullable=False),
sa.Column('updated_at', sa.DateTime(), server_default=sa.text('CURRENT_TIMESTAMP'), nullable=False),
sa.PrimaryKeyConstraint('id', name='document_segment_summary_pkey')
)
with op.batch_alter_table('document_segment_summary', schema=None) as batch_op:
batch_op.create_index('document_segment_summary_chunk_id_idx', ['chunk_id'], unique=False)
batch_op.create_index('document_segment_summary_dataset_id_idx', ['dataset_id'], unique=False)
batch_op.create_index('document_segment_summary_document_id_idx', ['document_id'], unique=False)
batch_op.create_index('document_segment_summary_status_idx', ['status'], unique=False)
with op.batch_alter_table('datasets', schema=None) as batch_op:
batch_op.add_column(sa.Column('summary_index_setting', models.types.AdjustedJSON(), nullable=True))
with op.batch_alter_table('documents', schema=None) as batch_op:
batch_op.add_column(sa.Column('need_summary', sa.Boolean(), server_default=sa.text('false'), nullable=True))
# ### end Alembic commands ###
def downgrade():
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table('documents', schema=None) as batch_op:
batch_op.drop_column('need_summary')
with op.batch_alter_table('datasets', schema=None) as batch_op:
batch_op.drop_column('summary_index_setting')
with op.batch_alter_table('document_segment_summary', schema=None) as batch_op:
batch_op.drop_index('document_segment_summary_status_idx')
batch_op.drop_index('document_segment_summary_document_id_idx')
batch_op.drop_index('document_segment_summary_dataset_id_idx')
batch_op.drop_index('document_segment_summary_chunk_id_idx')
op.drop_table('document_segment_summary')
# ### end Alembic commands ###