RAG/data_models/content_chunks.py

from sqlalchemy import Column, Text, BigInteger, TIMESTAMP, Integer, Float
from sqlalchemy.dialects.mysql import VARCHAR
from sqlalchemy.orm import declarative_base

Base = declarative_base()


class ContentChunks(Base):
    __tablename__ = "content_chunks"

    id = Column(BigInteger, primary_key=True, autoincrement=True, comment="主键id")
    chunk_id = Column(Integer)
    doc_id = Column(VARCHAR(64))
    text = Column(Text)
    tokens = Column(Integer)
    summary = Column(Text)
    topic = Column(VARCHAR(255))
    domain = Column(VARCHAR(100))
    task_type = Column(VARCHAR(100))
    topic_purity = Column(Float)
    keywords = Column(Text)
    concepts = Column(Text)
    questions = Column(Text)
    created_at = Column(TIMESTAMP)
    updated_at = Column(TIMESTAMP)
    chunk_status = Column(Integer, default=0)
    es_status = Column(Integer, default=0)
    embedding_status = Column(Integer, default=0)
    entities = Column(Text)
    version = Column(Integer, default=1)
    text_type = Column(Integer, default=1)
    dataset_id = Column(Integer)
    status = Column(Integer, default=1)