25109d756d
Retrieval generalised beyond questions
`_text_for_question`, `embed_question` and `hybrid_question_ids` all hardcoded
the questions table, so there was nothing to call for an article or a card. That
layer is now corpus-agnostic:
- `Embeddable` mixin gives articles and flashcards the same embedding,
embedding_model and embedded_at columns questions have, plus a weighted
full-text vector (migration u3a4b5c6d7e8).
- `embed_record(row, kind)` is one code path for all three — they share an
embedding space, so they must share the model and provenance rules too.
- `hybrid_ids(db, query, kind)` ranks any corpus; `hybrid_question_ids` stays as
a thin alias for existing callers.
- Article and flashcard search moved off `ILIKE '%term%'`, which could not find
a jaundice article from "yellow newborn".
- The retry task and full regeneration now sweep every corpus, and the health
report breaks down current/stale/missing per kind.
- Articles embed on create and on edit, with failures left to the retry task.
Quoted phrases replace the keyword-only mode
`websearch_to_tsquery` already gives "absence seizure" exact-phrase semantics,
and the semantic ranker sits out a quoted query. That covers the one case a
keyword-only toggle was for — exact lookup — per query rather than as a sticky
setting whose every position returns a subset of the default.
Full-page question editor (/questions/new, /questions/:id)
Editing happened in a cramped modal. There is now a page with room for the stem,
per-option explanations, a searchable category picker with primary plus extras,
difficulty, and images. It shows the question's id with a copy button, and
Duplicate creates a variant without retyping the stem. `GET /questions/detail/{id}`
backs it, pathed under /detail/ so it cannot shadow the static routes.
Question bank filter bar restyled — the toggle and count read as one control
instead of two grey pills crowding the result count.
Tests: 101 backend green.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PpfzbZ1QTLMeVYxM2kyq8m
29 lines
926 B
Python
29 lines
926 B
Python
from datetime import datetime
|
|
|
|
from pgvector.sqlalchemy import Vector
|
|
from sqlalchemy import Column, DateTime, String
|
|
from sqlalchemy.orm import declared_attr, deferred
|
|
|
|
from app.config import settings
|
|
|
|
|
|
class Embeddable:
|
|
"""Retrieval columns shared by every searchable corpus.
|
|
|
|
`embedding_model` is what makes a model change detectable: vectors from two
|
|
models share no space, so a mixed corpus returns meaningless distances.
|
|
Deferred because a vector is large and never wanted in a list query.
|
|
"""
|
|
|
|
# Mixin columns must be declared attributes, one per mapped class.
|
|
@declared_attr
|
|
def embedding(cls):
|
|
return deferred(Column(Vector(settings.EMBEDDING_DIMENSIONS), nullable=True))
|
|
|
|
@declared_attr
|
|
def embedding_model(cls):
|
|
return Column(String(120), nullable=True, index=True)
|
|
|
|
@declared_attr
|
|
def embedded_at(cls):
|
|
return Column(DateTime, nullable=True)
|