46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
"""document summaries: documents.summary + chunks.is_summary
|
||
|
||
Revision ID: 0004
|
||
Revises: 0003
|
||
Create Date: 2026-08-25
|
||
|
||
Phase 30 (document-summaries story, A13 — two additive, reversible
|
||
columns, no table rework):
|
||
|
||
* ``documents.summary`` — TEXT, nullable. Natural-language summary of the
|
||
document produced at import time by the aipi ``lite`` model (non-markdown
|
||
A9 documents only). NULL for markdown docs and for documents imported
|
||
before summaries existed (or whose summary generation failed — the
|
||
fail-soft path still indexes the document without a summary).
|
||
* ``chunks.is_summary`` — BOOLEAN NOT NULL DEFAULT false. Marks the single
|
||
extra summary chunk (position -1) that mirrors ``documents.summary`` into
|
||
the embedding space, so hybrid search has a well-embedding
|
||
natural-language target for badly-formatted raw text. The default keeps
|
||
every pre-0004 row valid; the summary chunk flows through the unchanged
|
||
A7 retrieval path (cosine ∪ FTS ∪ RRF) and the existing chunk→document
|
||
mapping resolves a summary hit to its full source document.
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import sqlalchemy as sa
|
||
|
||
from alembic import op
|
||
|
||
revision = "0004"
|
||
down_revision = "0003"
|
||
branch_labels = None
|
||
depends_on = None
|
||
|
||
|
||
def upgrade() -> None:
|
||
op.add_column("documents", sa.Column("summary", sa.Text(), nullable=True))
|
||
op.add_column(
|
||
"chunks",
|
||
sa.Column("is_summary", sa.Boolean(), nullable=False, server_default=sa.text("false")),
|
||
)
|
||
|
||
|
||
def downgrade() -> None:
|
||
op.drop_column("chunks", "is_summary")
|
||
op.drop_column("documents", "summary")
|