pyr0ball
89a58ec9b0
Bi-encoder embeddings collapse a whole query into one vector, losing multi-part reasoning structure — queries like "the procedure for setting an IP on an AVC-X" or "what is the action economy for a fighter casting a spell while prone" lose nuance. Agent-ModernColBERT is a late-interaction retriever: per-token embeddings, scored via MaxSim at query time, built specifically for agentic/multi-hop queries. Implements Option A from the issue (in-process, via `pylate`) rather than Option B (managed cf-orch service) — cf-orch already has `agent-moderncolbert` registered in model_registry.yaml with a `pagepiper/retrieve` assignment in assignments.yaml pointing at it and referencing this issue directly, someone had already pre-wired that side. - app/services/colbert_index.py: new ColBERTIndex class, mirrors BM25Index's dirty-flag/rebuild-from-SQLite pattern exactly — no separate per-shelve indexing step needed, just mark_dirty() on the same callback that already marks BM25 dirty. - app/services/retriever.py: hybrid_search's semantic half now merges BM25 with ColBERT MaxSim scores (min-max normalized per-batch, since MaxSim is unbounded unlike the old sqlite-vec L2-distance path) instead of Ollama-embed + sqlite-vec cosine. BM25 merge/rank/per-doc-cap/ adjacent-chunk-window logic is unchanged. - app/main.py / app/deps.py: per-user ColBERTIndex registry, same pattern as the existing per-user BM25Index registry. - Existing BYOK tier gate preserved exactly (llm is None check) — this is a retrieval-technology swap, not a tier/licensing change. The ColBERT model runs locally via pylate with no Ollama dependency, but gating still follows product tiering. - 12 new tests. pylate is intentionally NOT installed in the dev/test env — see the cf-sysadmin skill's "Known Gotchas" for why (installing it directly into the shared `cf` conda env broke several other services' torch/transformers pins on 2026-07-10). Tests inject fake pylate modules via sys.modules instead. Known follow-up (not addressed here): shelve scripts still compute and store Ollama embeddings into `page_vecs` at shelve time — that table is no longer read by search/chat now that retrieval uses the ColBERT index. Removing the now-redundant embedding step is separate cleanup. Closes: #8
72 lines
2.2 KiB
Python
72 lines
2.2 KiB
Python
# tests/conftest.py
|
|
"""Shared fixtures for pagepiper test suite."""
|
|
from __future__ import annotations
|
|
|
|
import sqlite3
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
|
|
@pytest.fixture
|
|
def test_db(tmp_path) -> str:
|
|
db_path = str(tmp_path / "test.db")
|
|
schema = Path("migrations/001_initial_schema.sql").read_text()
|
|
conn = sqlite3.connect(db_path)
|
|
conn.executescript(schema)
|
|
conn.commit()
|
|
conn.close()
|
|
return db_path
|
|
|
|
|
|
@pytest.fixture
|
|
def client(test_db, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("PAGEPIPER_DATA_DIR", str(tmp_path))
|
|
monkeypatch.setenv("PAGEPIPER_WATCH_DIR", str(tmp_path / "books"))
|
|
(tmp_path / "books").mkdir(exist_ok=True)
|
|
|
|
import app.main as _main_module
|
|
from app.config import LOCAL_USER_ID
|
|
from app.deps import UserCtx, get_db, get_user_ctx
|
|
from app.main import app
|
|
from app.services.bm25_index import BM25Index
|
|
from app.services.colbert_index import ColBERTIndex
|
|
from app.startup import apply_migrations, check_and_rebuild_vec_schema
|
|
|
|
monkeypatch.setattr(_main_module, "_apply_migrations", lambda: None, raising=False)
|
|
monkeypatch.setattr(
|
|
"app.startup.apply_migrations", lambda *a, **kw: None
|
|
)
|
|
monkeypatch.setattr(
|
|
"app.startup.check_and_rebuild_vec_schema", lambda *a, **kw: None
|
|
)
|
|
|
|
test_bm25 = BM25Index()
|
|
test_bm25.mark_dirty()
|
|
test_colbert = ColBERTIndex(index_dir=str(tmp_path / "colbert_index"))
|
|
|
|
def override_user_ctx():
|
|
return UserCtx(
|
|
user_id=LOCAL_USER_ID,
|
|
db_path=test_db,
|
|
vec_db_path=str(tmp_path / "test_vecs.db"),
|
|
data_dir=Path(tmp_path),
|
|
watch_dir=Path(tmp_path) / "books",
|
|
bm25=test_bm25,
|
|
colbert=test_colbert,
|
|
)
|
|
|
|
def override_db():
|
|
conn = sqlite3.connect(test_db)
|
|
conn.execute("PRAGMA foreign_keys = ON")
|
|
conn.row_factory = sqlite3.Row
|
|
try:
|
|
yield conn
|
|
finally:
|
|
conn.close()
|
|
|
|
app.dependency_overrides[get_user_ctx] = override_user_ctx
|
|
app.dependency_overrides[get_db] = override_db
|
|
yield TestClient(app)
|
|
app.dependency_overrides.clear()
|