bvandeusen
513019786e
Move semantic_search_notes off the full-table Python cosine scan onto a native pgvector column: indexed ORDER BY embedding <=> :q LIMIT k (HNSW, cosine). Migration 0067 enables the extension, converts the JSONB embedding column to vector(384) (stale-dim rows dropped and regenerated by the startup backfill), and builds the HNSW cosine index. Postgres image moves postgres:16-alpine -> pgvector/pgvector:pg17 across prod, quickstart, and CI. Scribe: project 2, milestone 93, task 1031. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Xz4j1H7pjYSjKsEpgcNH5E
32 lines
1.1 KiB
Python
32 lines
1.1 KiB
Python
from datetime import datetime, timezone
|
|
|
|
from pgvector.sqlalchemy import Vector
|
|
from sqlalchemy import DateTime, ForeignKey, Integer
|
|
from sqlalchemy.orm import Mapped, mapped_column
|
|
|
|
from scribe.models import Base
|
|
|
|
# bge-small-en-v1.5 produces 384-dim unit-normalized vectors. The column is a
|
|
# native pgvector `vector(384)` (see migration 0067) so similarity search runs
|
|
# as an indexed `ORDER BY embedding <=> :q LIMIT k` in Postgres rather than a
|
|
# full-table Python cosine scan.
|
|
EMBEDDING_DIM = 384
|
|
|
|
|
|
class NoteEmbedding(Base):
|
|
"""Stores the embedding vector for a note, used for semantic search."""
|
|
|
|
__tablename__ = "note_embeddings"
|
|
|
|
note_id: Mapped[int] = mapped_column(
|
|
Integer,
|
|
ForeignKey("notes.id", ondelete="CASCADE"),
|
|
primary_key=True,
|
|
)
|
|
user_id: Mapped[int] = mapped_column(Integer, nullable=False, index=True)
|
|
embedding: Mapped[list] = mapped_column(Vector(EMBEDDING_DIM), nullable=False)
|
|
updated_at: Mapped[datetime] = mapped_column(
|
|
DateTime(timezone=True),
|
|
default=lambda: datetime.now(timezone.utc),
|
|
)
|