feat: add sqlite persistence model

2026-07-13 11:28:09 +08:00
parent 44e01e2f93
commit eebcd5d6a7
11 changed files with 793 additions and 0 deletions
@@ -0,0 +1,92 @@
+from datetime import datetime
+from uuid import uuid4
+
+from sqlalchemy import (
+    CheckConstraint,
+    DateTime,
+    ForeignKey,
+    Index,
+    Integer,
+    String,
+    Text,
+    UniqueConstraint,
+)
+from sqlalchemy.orm import Mapped, mapped_column
+
+from kbqa.database import Base, utc_now
+
+
+def new_uuid() -> str:
+    return str(uuid4())
+
+
+class Document(Base):
+    __tablename__ = "documents"
+    __table_args__ = (
+        CheckConstraint(
+            "status IN ('pending','indexing','indexed','failed','deleting')",
+            name="ck_documents_status",
+        ),
+        Index("ix_documents_status_updated_at", "status", "updated_at"),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
+    filename: Mapped[str] = mapped_column(Text, nullable=False)
+    stored_path: Mapped[str] = mapped_column(Text, nullable=False)
+    file_type: Mapped[str] = mapped_column(String(16), nullable=False)
+    mime_type: Mapped[str] = mapped_column(String(128), nullable=False)
+    file_size: Mapped[int] = mapped_column(Integer, nullable=False)
+    sha256: Mapped[str] = mapped_column(String(64), nullable=False)
+    status: Mapped[str] = mapped_column(String(16), nullable=False, default="pending")
+    chunk_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    error_code: Mapped[str | None] = mapped_column(String(64))
+    error_message: Mapped[str | None] = mapped_column(Text)
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=utc_now
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=utc_now, onupdate=utc_now
+    )
+
+
+class IndexJob(Base):
+    __tablename__ = "index_jobs"
+    __table_args__ = (
+        CheckConstraint(
+            "status IN ('queued','running','succeeded','failed')",
+            name="ck_index_jobs_status",
+        ),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_uuid)
+    document_id: Mapped[str] = mapped_column(
+        String(36), ForeignKey("documents.id", ondelete="CASCADE"), nullable=False, unique=True
+    )
+    status: Mapped[str] = mapped_column(String(16), nullable=False, default="queued")
+    attempt_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    last_error: Mapped[str | None] = mapped_column(Text)
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=utc_now
+    )
+    started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
+    finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
+
+
+class Chunk(Base):
+    __tablename__ = "chunks"
+    __table_args__ = (
+        UniqueConstraint("document_id", "order_index", name="uq_chunks_document_order"),
+        Index("ix_chunks_document_id", "document_id"),
+    )
+
+    id: Mapped[str] = mapped_column(String(36), primary_key=True)
+    document_id: Mapped[str] = mapped_column(
+        String(36), ForeignKey("documents.id", ondelete="CASCADE"), nullable=False
+    )
+    order_index: Mapped[int] = mapped_column(Integer, nullable=False)
+    content: Mapped[str] = mapped_column(Text, nullable=False)
+    page_number: Mapped[int | None] = mapped_column(Integer)
+    char_count: Mapped[int] = mapped_column(Integer, nullable=False)
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, default=utc_now
+    )