YG-Datasets/backend/app/models/models.py

"""
Database Models for YG-Dataset
"""
from sqlalchemy import Column, String, Text, Integer, BigInteger, ForeignKey, JSON
from sqlalchemy.dialects.postgresql import UUID
from sqlalchemy.orm import relationship
from app.core.database import Base
from app.models.base import UUIDMixin, TimestampMixin


class Project(Base, UUIDMixin, TimestampMixin):
    """Project model"""
    __tablename__ = "projects"

    name = Column(String(255), nullable=False)
    description = Column(Text)

    # Relationships
    files = relationship("File", back_populates="project", cascade="all, delete-orphan")
    chunks = relationship("Chunk", back_populates="project", cascade="all, delete-orphan")
    tags = relationship("Tag", back_populates="project", cascade="all, delete-orphan")
    datasets = relationship("Dataset", back_populates="project", cascade="all, delete-orphan")
    eval_datasets = relationship("EvalDataset", back_populates="project", cascade="all, delete-orphan")
    model_configs = relationship("ModelConfig", back_populates="project", cascade="all, delete-orphan")
    tasks = relationship("Task", back_populates="project", cascade="all, delete-orphan")


class File(Base, UUIDMixin, TimestampMixin):
    """File model for uploaded documents"""
    __tablename__ = "files"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    filename = Column(String(255), nullable=False)
    file_type = Column(String(50), nullable=False)  # pdf, docx, xlsx, csv, epub, md, txt
    file_path = Column(String(500))
    size = Column(BigInteger)  # file size in bytes
    status = Column(String(20), default="pending")  # pending, processing, completed, failed

    # Relationships
    project = relationship("Project", back_populates="files")
    chunks = relationship("Chunk", back_populates="file", cascade="all, delete-orphan")


class Chunk(Base, UUIDMixin, TimestampMixin):
    """Text chunk model after splitting"""
    __tablename__ = "chunks"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    file_id = Column(UUID(as_uuid=True), ForeignKey("files.id", ondelete="CASCADE"))
    name = Column(String(255))
    content = Column(Text, nullable=False)
    summary = Column(Text)
    word_count = Column(Integer)
    extra_data = Column(JSON)  # store additional info like headings, page numbers

    # Relationships
    project = relationship("Project", back_populates="chunks")
    file = relationship("File", back_populates="chunks")
    questions = relationship("Question", back_populates="chunk", cascade="all, delete-orphan")
    chunk_tags = relationship("ChunkTag", back_populates="chunk", cascade="all, delete-orphan")


class Tag(Base, UUIDMixin, TimestampMixin):
    """Tag/Label model for categorizing content"""
    __tablename__ = "tags"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    label = Column(String(255), nullable=False)
    parent_id = Column(UUID(as_uuid=True), ForeignKey("tags.id", ondelete="CASCADE"))
    color = Column(String(20))  # hex color code

    # Relationships
    project = relationship("Project", back_populates="tags")
    parent = relationship("Tag", remote_side="Tag.id", back_populates="children")
    children = relationship("Tag", back_populates="parent")
    chunk_tags = relationship("ChunkTag", back_populates="tag")


class ChunkTag(Base, UUIDMixin):
    """Many-to-many relationship between chunks and tags"""
    __tablename__ = "chunk_tags"

    chunk_id = Column(UUID(as_uuid=True), ForeignKey("chunks.id", ondelete="CASCADE"), nullable=False)
    tag_id = Column(UUID(as_uuid=True), ForeignKey("tags.id", ondelete="CASCADE"), nullable=False)

    # Relationships
    chunk = relationship("Chunk", back_populates="chunk_tags")
    tag = relationship("Tag", back_populates="chunk_tags")


class Question(Base, UUIDMixin, TimestampMixin):
    """Question/QA pair model"""
    __tablename__ = "questions"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    chunk_id = Column(UUID(as_uuid=True), ForeignKey("chunks.id", ondelete="CASCADE"))
    content = Column(Text, nullable=False)  # question content
    answer = Column(Text)  # answer content
    question_type = Column(String(50))  # fact, summary, reasoning, etc.
    source = Column(String(50), default="manual")  # manual, generated

    # Relationships
    project = relationship("Project")
    chunk = relationship("Chunk", back_populates="questions")


class Dataset(Base, UUIDMixin, TimestampMixin):
    """Dataset model"""
    __tablename__ = "datasets"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    name = Column(String(255), nullable=False)
    description = Column(Text)
    dataset_type = Column(String(50))  # qa, conversation, instruction
    extra_data = Column(JSON)

    # Relationships
    project = relationship("Project", back_populates="datasets")


class EvalDataset(Base, UUIDMixin, TimestampMixin):
    """Evaluation dataset model"""
    __tablename__ = "eval_datasets"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    name = Column(String(255), nullable=False)
    question_type = Column(String(50))  # mixed, fact, reasoning
    extra_data = Column(JSON)

    # Relationships
    project = relationship("Project", back_populates="eval_datasets")


class ModelConfig(Base, UUIDMixin, TimestampMixin):
    """Model configuration for LLM providers"""
    __tablename__ = "model_configs"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"), nullable=False)
    provider = Column(String(50), nullable=False)  # openai, anthropic, ollama, custom
    model_name = Column(String(100))
    api_key = Column(String(500))
    api_base = Column(String(500))
    is_default = Column(String(10), default="false")

    # Relationships
    project = relationship("Project", back_populates="model_configs")


class Task(Base, UUIDMixin, TimestampMixin):
    """Task model for background jobs"""
    __tablename__ = "tasks"

    project_id = Column(UUID(as_uuid=True), ForeignKey("projects.id", ondelete="CASCADE"))
    task_type = Column(String(50))  # split, generate, eval, export
    status = Column(String(20), default="pending")  # pending, running, completed, failed
    progress = Column(Integer, default=0)  # 0-100
    result = Column(JSON)
    error = Column(Text)

    # Relationships
    project = relationship("Project", back_populates="tasks")