youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-04 01:18:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add summary index for knowledge. (#31625)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yansong Zhang <916125788@qq.com>
Co-authored-by: hj24 <mambahj24@gmail.com>
Co-authored-by: CodingOnStar <hanxujiang@dify.ai>
Co-authored-by: CodingOnStar <hanxujiang@dify.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
FFXN
2026-01-29 13:47:35 +08:00
committed by GitHub
parent 5ce3a04a2c
commit c2473d85dc
51 changed files with 3797 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
api/models/dataset.py
View File

@ -72,6 +72,7 @@ class Dataset(Base):
keyword_number = mapped_column(sa.Integer, nullable=True, server_default=sa.text("10"))
collection_binding_id = mapped_column(StringUUID, nullable=True)
retrieval_model = mapped_column(AdjustedJSON, nullable=True)
summary_index_setting = mapped_column(AdjustedJSON, nullable=True)
built_in_field_enabled = mapped_column(sa.Boolean, nullable=False, server_default=sa.text("false"))
icon_info = mapped_column(AdjustedJSON, nullable=True)
runtime_mode = mapped_column(sa.String(255), nullable=True, server_default=sa.text("'general'"))
@ -419,6 +420,7 @@ class Document(Base):
doc_metadata = mapped_column(AdjustedJSON, nullable=True)
doc_form = mapped_column(String(255), nullable=False, server_default=sa.text("'text_model'"))
doc_language = mapped_column(String(255), nullable=True)
need_summary: Mapped[bool | None] = mapped_column(sa.Boolean, nullable=True, server_default=sa.text("false"))
DATA_SOURCES = ["upload_file", "notion_import", "website_crawl"]
@ -1575,3 +1577,36 @@ class SegmentAttachmentBinding(Base):
segment_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
attachment_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
created_at: Mapped[datetime] = mapped_column(sa.DateTime, nullable=False, server_default=func.current_timestamp())
class DocumentSegmentSummary(Base):
__tablename__ = "document_segment_summaries"
__table_args__ = (
sa.PrimaryKeyConstraint("id", name="document_segment_summaries_pkey"),
sa.Index("document_segment_summaries_dataset_id_idx", "dataset_id"),
sa.Index("document_segment_summaries_document_id_idx", "document_id"),
sa.Index("document_segment_summaries_chunk_id_idx", "chunk_id"),
sa.Index("document_segment_summaries_status_idx", "status"),
)
id: Mapped[str] = mapped_column(StringUUID, nullable=False, default=lambda: str(uuid4()))
dataset_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
document_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
# corresponds to DocumentSegment.id or parent chunk id
chunk_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
summary_content: Mapped[str] = mapped_column(LongText, nullable=True)
summary_index_node_id: Mapped[str] = mapped_column(String(255), nullable=True)
summary_index_node_hash: Mapped[str] = mapped_column(String(255), nullable=True)
tokens: Mapped[int | None] = mapped_column(sa.Integer, nullable=True)
status: Mapped[str] = mapped_column(String(32), nullable=False, server_default=sa.text("'generating'"))
error: Mapped[str] = mapped_column(LongText, nullable=True)
enabled: Mapped[bool] = mapped_column(sa.Boolean, nullable=False, server_default=sa.text("true"))
disabled_at: Mapped[datetime | None] = mapped_column(DateTime, nullable=True)
disabled_by = mapped_column(StringUUID, nullable=True)
created_at: Mapped[datetime] = mapped_column(DateTime, nullable=False, server_default=func.current_timestamp())
updated_at: Mapped[datetime] = mapped_column(
DateTime, nullable=False, server_default=func.current_timestamp(), onupdate=func.current_timestamp()
)
def __repr__(self):
return f"<DocumentSegmentSummary id={self.id} chunk_id={self.chunk_id} status={self.status}>"