feat: improve assistant knowledge import and database compatibility

This commit is contained in:
吉鑫升 committed 2026-09-02 17:55:17 +08:00
1 parent fbd8dec48f
commit 6b724bd00d
51 files changed
+4393 -1021

No files matched your search

@@ -1,10 +1,10 @@
"""ORM model for the single global DeerFlow assistant knowledge base."""
"""ORM model for DeerFlow-native assistant knowledge bases."""
from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Float, Integer, String, UniqueConstraint
from sqlalchemy import Float, Index, Integer, LargeBinary, String, UniqueConstraint
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
@@ -19,7 +19,12 @@ class AssistantKnowledgeBaseRow(Base):
__tablename__ = "assistant_knowledge_base"
id: Mapped[str] = mapped_column(String(36), primary_key=True)
name: Mapped[str] = mapped_column(String(255), default="知识梳理")
status: Mapped[str] = mapped_column(String(24), default="active", unique=True)
description: Mapped[str | None] = mapped_column(String(2048), nullable=True)
# ``global`` is the full-library aggregation base. ``custom`` bases are
# user-created assistant knowledge bases fed from WeKnora export packages.
# Nullable keeps startup column reconciliation safe for existing databases.
base_kind: Mapped[str | None] = mapped_column(String(24), nullable=True, index=True)
status: Mapped[str] = mapped_column(String(64), default="active")
created_by: Mapped[str | None] = mapped_column(String(64), nullable=True)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=_now)
updated_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=_now, onupdate=_now)
@@ -91,6 +96,32 @@ class AssistantKnowledgeWikiRevisionRow(Base):
published_at: Mapped[datetime | None] = mapped_column(BeijingDateTime(), nullable=True)
class AssistantKnowledgeVectorRow(Base):
__tablename__ = "assistant_knowledge_vectors"
__table_args__ = (
Index("ix_assistant_knowledge_vector_base_fingerprint", "base_id", "embedding_fingerprint"),
Index("ix_assistant_knowledge_vector_page", "page_id"),
Index("ix_assistant_knowledge_vector_source", "source_id"),
)
id: Mapped[str] = mapped_column(String(36), primary_key=True)
base_id: Mapped[str] = mapped_column(String(36), index=True)
page_id: Mapped[str] = mapped_column(String(36), index=True)
source_id: Mapped[str] = mapped_column(String(36), index=True)
import_job_id: Mapped[str] = mapped_column(String(36), index=True)
source_vector_id: Mapped[str | None] = mapped_column(String(255), nullable=True)
source_chunk_id: Mapped[str | None] = mapped_column(String(255), nullable=True)
section_index: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
heading: Mapped[str | None] = mapped_column(String(1024), nullable=True)
section_content: Mapped[str] = mapped_column(PortableLongText(), nullable=False, default="")
content_hash: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
embedding_model: Mapped[str | None] = mapped_column(String(255), nullable=True)
embedding_fingerprint: Mapped[str | None] = mapped_column(String(64), nullable=True, index=True)
embedding_dimensions: Mapped[int] = mapped_column(Integer, nullable=False)
vector_blob: Mapped[bytes] = mapped_column(LargeBinary, nullable=False)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), default=_now)
class AssistantKnowledgeEntityRow(Base):
__tablename__ = "assistant_knowledge_entities"
__table_args__ = (UniqueConstraint("base_id", "entity_type", "normalized_name", name="uq_assistant_entity"),)