feat: Add labeling template (#72)

* feat: Enhance annotation module with template management and validation

- Added DatasetMappingCreateRequest and DatasetMappingUpdateRequest schemas to handle dataset mapping requests with camelCase and snake_case support.
- Introduced Annotation Template schemas including CreateAnnotationTemplateRequest, UpdateAnnotationTemplateRequest, and AnnotationTemplateResponse for managing annotation templates.
- Implemented AnnotationTemplateService for creating, updating, retrieving, and deleting annotation templates, including validation of configurations and XML generation.
- Added utility class LabelStudioConfigValidator for validating Label Studio configurations and XML formats.
- Updated database schema for annotation templates and labeling projects to include new fields and constraints.
- Seeded initial annotation templates for various use cases including image classification, object detection, and text classification.

* feat: Enhance TemplateForm with improved validation and dynamic field rendering; update LabelStudio config validation for camelCase support

* feat: Update docker-compose.yml to mark datamate dataset volume and network as external
This commit is contained in:
Jason Wang
2025-11-11 09:14:14 +08:00
committed by GitHub
parent 451d3c8207
commit c5ccc56cca
24 changed files with 2794 additions and 253 deletions

View File

@@ -3,25 +3,32 @@ Tables of Annotation Management Module
"""
import uuid
from sqlalchemy import Column, String, BigInteger, Boolean, TIMESTAMP, Text, Integer, JSON, Date
from sqlalchemy import Column, String, BigInteger, Boolean, TIMESTAMP, Text, Integer, JSON, Date, ForeignKey
from sqlalchemy.sql import func
from app.db.session import Base
class AnnotationTemplate(Base):
"""标注模板模型"""
"""标注配置模板模型"""
__tablename__ = "t_dm_annotation_templates"
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID主键ID")
name = Column(String(32), nullable=False, comment="模板名称")
description = Column(String(255), nullable=True, comment="模板描述")
configuration = Column(JSON, nullable=True, comment="配置信息(JSON格式)")
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
name = Column(String(100), nullable=False, comment="模板名称")
description = Column(String(500), nullable=True, comment="模板描述")
data_type = Column(String(50), nullable=False, comment="数据类型: image/text/audio/video/timeseries")
labeling_type = Column(String(50), nullable=False, comment="标注类型: classification/detection/segmentation/ner/relation/etc")
configuration = Column(JSON, nullable=False, comment="标注配置(包含labels定义等)")
style = Column(String(32), nullable=False, comment="样式配置: horizontal/vertical")
category = Column(String(50), default='custom', comment="模板分类: medical/general/custom/system")
built_in = Column(Boolean, default=False, comment="是否系统内置模板")
version = Column(String(20), default='1.0', comment="模板版本")
created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间(软删除)")
def __repr__(self):
return f"<AnnotationTemplate(id={self.id}, name={self.name})>"
return f"<AnnotationTemplate(id={self.id}, name={self.name}, data_type={self.data_type})>"
@property
def is_deleted(self) -> bool:
@@ -29,21 +36,23 @@ class AnnotationTemplate(Base):
return self.deleted_at is not None
class LabelingProject(Base):
"""标注工程表"""
"""标注项目模型"""
__tablename__ = "t_dm_labeling_projects"
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID主键ID")
id = Column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID")
dataset_id = Column(String(36), nullable=False, comment="数据集ID")
name = Column(String(32), nullable=False, comment="项目名称")
name = Column(String(100), nullable=False, comment="项目名称")
labeling_project_id = Column(String(8), nullable=False, comment="Label Studio项目ID")
configuration = Column(JSON, nullable=True, comment="标签配置")
progress = Column(JSON, nullable=True, comment="标注进度统计")
template_id = Column(String(36), ForeignKey('t_dm_annotation_templates.id', ondelete='SET NULL'), nullable=True, comment="使用的模板ID")
configuration = Column(JSON, nullable=True, comment="项目配置(可能包含对模板的自定义修改)")
progress = Column(JSON, nullable=True, comment="项目进度信息")
created_at = Column(TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间")
updated_at = Column(TIMESTAMP, server_default=func.current_timestamp(), onupdate=func.current_timestamp(), comment="更新时间")
deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间(软删除)")
def __repr__(self):
return f"<LabelingProject(id={self.id}, dataset_id={self.dataset_id}, name={self.name})>"
return f"<LabelingProject(id={self.id}, name={self.name}, dataset_id={self.dataset_id})>"
@property
def is_deleted(self) -> bool: