nex_docus/backend/app/models/document_vector.py

"""
文档向量化模型
"""
from sqlalchemy import Column, BigInteger, Integer, String, DateTime, Index, Text
from sqlalchemy.sql import func
from app.core.database import Base


class DocumentVector(Base):
    """文档向量表模型"""

    __tablename__ = "document_vector"

    id = Column(BigInteger, primary_key=True, autoincrement=True, comment="向量ID")
    project_id = Column(BigInteger, nullable=False, index=True, comment="项目ID")
    file_path = Column(String(500), nullable=False, comment="文件相对路径")
    chunk_index = Column(Integer, nullable=False, default=0, comment="分块序号（0起），同一文件可有多个分块")
    chunk_text = Column(Text, comment="分块首段文本，作为点击引用时的定位锚点")
    content_hash = Column(String(64), comment="整个文件内容哈希值，用于判断文件是否变更")
    zvec_id = Column(String(256), comment="ZVec返回的向量ID（每个分块独立）")
    zvec_response = Column(Text, comment="ZVec完整响应JSON")
    status = Column(String(32), nullable=False, default="success", comment="向量化状态：success/failed/pending")
    error_message = Column(String(500), comment="错误信息")
    created_at = Column(DateTime, server_default=func.now(), comment="创建时间")
    updated_at = Column(DateTime, server_default=func.now(), onupdate=func.now(), comment="更新时间")

    __table_args__ = (
        Index("idx_project_file", "project_id", "file_path"),
        Index("idx_project_file_chunk", "project_id", "file_path", "chunk_index"),
    )

    def __repr__(self):
        return (
            f"<DocumentVector(id={self.id}, project_id={self.project_id}, "
            f"file_path='{self.file_path}', chunk_index={self.chunk_index}, status='{self.status}')>"
        )