Files
AstrBot/astrbot/core/knowledge_base/models.py
エイカク a9c16febf4 fix: 工程化收敛并移除 ASYNC230/ASYNC240 忽略 (#5729)
* test(skills): align sandbox cache tests with readonly behavior

* ci(release): enforce core quality gate before publish

* ci: enforce locked dependency installs in workflows

* security: remove curl-pipe-shell installs

* chore: align project python baseline to 3.12

* ci(dashboard): add explicit typecheck gate

* chore(pre-commit): align ruff hook version with project

* ci(codeql): add javascript-typescript analysis

* chore(ruff): defer py312 migration lint rules

* fix: resolve ruff violations without new ignores

* fix: resolve ASYNC230 and ASYNC240 without ignores

* fix(auth): replace utcnow with timezone-aware UTC now

* fix: avoid blocking file read in file_to_base64
2026-03-04 13:51:00 +09:00

121 lines
3.8 KiB
Python

import uuid
from datetime import UTC, datetime
from sqlmodel import Field, MetaData, SQLModel, Text, UniqueConstraint
class BaseKBModel(SQLModel, table=False):
metadata = MetaData()
class KnowledgeBase(BaseKBModel, table=True):
"""知识库表
存储知识库的基本信息和统计数据。
"""
__tablename__ = "knowledge_bases" # type: ignore
id: int | None = Field(
primary_key=True,
sa_column_kwargs={"autoincrement": True},
default=None,
)
kb_id: str = Field(
max_length=36,
nullable=False,
unique=True,
default_factory=lambda: str(uuid.uuid4()),
index=True,
)
kb_name: str = Field(max_length=100, nullable=False)
description: str | None = Field(default=None, sa_type=Text)
emoji: str | None = Field(default="📚", max_length=10)
embedding_provider_id: str | None = Field(default=None, max_length=100)
rerank_provider_id: str | None = Field(default=None, max_length=100)
# 分块配置参数
chunk_size: int | None = Field(default=512, nullable=True)
chunk_overlap: int | None = Field(default=50, nullable=True)
# 检索配置参数
top_k_dense: int | None = Field(default=50, nullable=True)
top_k_sparse: int | None = Field(default=50, nullable=True)
top_m_final: int | None = Field(default=5, nullable=True)
created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
updated_at: datetime = Field(
default_factory=lambda: datetime.now(UTC),
sa_column_kwargs={"onupdate": datetime.now(UTC)},
)
doc_count: int = Field(default=0, nullable=False)
chunk_count: int = Field(default=0, nullable=False)
__table_args__ = (
UniqueConstraint(
"kb_name",
name="uix_kb_name",
),
)
class KBDocument(BaseKBModel, table=True):
"""文档表
存储上传到知识库的文档元数据。
"""
__tablename__ = "kb_documents" # type: ignore
id: int | None = Field(
primary_key=True,
sa_column_kwargs={"autoincrement": True},
default=None,
)
doc_id: str = Field(
max_length=36,
nullable=False,
unique=True,
default_factory=lambda: str(uuid.uuid4()),
index=True,
)
kb_id: str = Field(max_length=36, nullable=False, index=True)
doc_name: str = Field(max_length=255, nullable=False)
file_type: str = Field(max_length=20, nullable=False)
file_size: int = Field(nullable=False)
file_path: str = Field(max_length=512, nullable=False)
chunk_count: int = Field(default=0, nullable=False)
media_count: int = Field(default=0, nullable=False)
created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))
updated_at: datetime = Field(
default_factory=lambda: datetime.now(UTC),
sa_column_kwargs={"onupdate": datetime.now(UTC)},
)
class KBMedia(BaseKBModel, table=True):
"""多媒体资源表
存储从文档中提取的图片、视频等多媒体资源。
"""
__tablename__ = "kb_media" # type: ignore
id: int | None = Field(
primary_key=True,
sa_column_kwargs={"autoincrement": True},
default=None,
)
media_id: str = Field(
max_length=36,
nullable=False,
unique=True,
default_factory=lambda: str(uuid.uuid4()),
index=True,
)
doc_id: str = Field(max_length=36, nullable=False, index=True)
kb_id: str = Field(max_length=36, nullable=False, index=True)
media_type: str = Field(max_length=20, nullable=False)
file_name: str = Field(max_length=255, nullable=False)
file_path: str = Field(max_length=512, nullable=False)
file_size: int = Field(nullable=False)
mime_type: str = Field(max_length=100, nullable=False)
created_at: datetime = Field(default_factory=lambda: datetime.now(UTC))