jprdonnelly/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2025-12-19 17:27:16 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add segments max number limit for SegmentApi.post (#27745)

Browse Source
This commit is contained in:
Ponder
2025-11-04 10:27:58 +08:00
committed by GitHub
parent c8e9edc024
commit b610cf9a11
5 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
api/.env.example
View File

@@ -608,3 +608,6 @@ SWAGGER_UI_PATH=/swagger-ui.html
# Whether to encrypt dataset IDs when exporting DSL files (default: true)
# Set to false to export dataset IDs as plain text for easier cross-environment import
DSL_EXPORT_ENCRYPT_DATASET_ID=true
# Maximum number of segments for dataset segments API (0 for unlimited)
DATASET_MAX_SEGMENTS_PER_REQUEST=0

5
api/configs/feature/__init__.py
View File

@@ -920,6 +920,11 @@ class DataSetConfig(BaseSettings):
default=True,
)
DATASET_MAX_SEGMENTS_PER_REQUEST: NonNegativeInt = Field(
description="Maximum number of segments for dataset segments API (0 for unlimited)",
default=0,
)
class WorkspaceConfig(BaseSettings):
"""

5
api/controllers/service_api/dataset/segment.py
View File

@@ -2,6 +2,7 @@ from flask import request
from flask_restx import marshal, reqparse
from werkzeug.exceptions import NotFound
from configs import dify_config
from controllers.service_api import service_api_ns
from controllers.service_api.app.error import ProviderNotInitializeError
from controllers.service_api.wraps import (
@@ -107,6 +108,10 @@ class SegmentApi(DatasetApiResource):
# validate args
args = segment_create_parser.parse_args()
if args["segments"] is not None:
segments_limit = dify_config.DATASET_MAX_SEGMENTS_PER_REQUEST
if segments_limit > 0 and len(args["segments"]) > segments_limit:
raise ValueError(f"Exceeded maximum segments limit of {segments_limit}.")
for args_item in args["segments"]:
SegmentService.segment_create_args_validate(args_item, document)
segments = SegmentService.multi_create_segment(args["segments"], document, dataset)

3
docker/.env.example
View File

@@ -1351,6 +1351,9 @@ SWAGGER_UI_PATH=/swagger-ui.html
# Set to false to export dataset IDs as plain text for easier cross-environment import
DSL_EXPORT_ENCRYPT_DATASET_ID=true
# Maximum number of segments for dataset segments API (0 for unlimited)
DATASET_MAX_SEGMENTS_PER_REQUEST=0
# Celery schedule tasks configuration
ENABLE_CLEAN_EMBEDDING_CACHE_TASK=false
ENABLE_CLEAN_UNUSED_DATASETS_TASK=false

1
docker/docker-compose.yaml
View File

@@ -603,6 +603,7 @@ x-shared-env: &shared-api-worker-env
SWAGGER_UI_ENABLED: ${SWAGGER_UI_ENABLED:-true}
SWAGGER_UI_PATH: ${SWAGGER_UI_PATH:-/swagger-ui.html}
DSL_EXPORT_ENCRYPT_DATASET_ID: ${DSL_EXPORT_ENCRYPT_DATASET_ID:-true}
DATASET_MAX_SEGMENTS_PER_REQUEST: ${DATASET_MAX_SEGMENTS_PER_REQUEST:-0}
ENABLE_CLEAN_EMBEDDING_CACHE_TASK: ${ENABLE_CLEAN_EMBEDDING_CACHE_TASK:-false}
ENABLE_CLEAN_UNUSED_DATASETS_TASK: ${ENABLE_CLEAN_UNUSED_DATASETS_TASK:-false}
ENABLE_CREATE_TIDB_SERVERLESS_TASK: ${ENABLE_CREATE_TIDB_SERVERLESS_TASK:-false}