Chris CoutinhoandClaude Opus 4.8
a0bb5642cb
Round-1 claude-review findings: - 🔴 Multi-doc_type search billed N embedding calls as 1. nc_semantic_search loops search() once per doc_type on one BM25HybridSearchAlgorithm instance, and each call re-embedded the query, so only the last query_token_count was recorded. Cache the dense embedding per query on the (per-request) instance so the query is embedded — and metered — exactly once regardless of how many doc_types are searched. This also removes the redundant per-type embed work and avoids billing a user N× for one logical query. - 🟡 Ollama embed() now delegates to embed_with_usage() so single and batch embeds use the same /api/embed endpoint (was the legacy /api/embeddings), keeping _detect_dimension and other embed() callers consistent. - 🟢 round() instead of truncating int() when coercing provider-reported token counts (forward-compatible if a provider ever returns a float). Tests: per-instance query-embedding cache (embedded once across 3 doc_types; re-embeds on a different query). Deferred (stated on the PR): mistral/openai single-embed dual path (changes tested error/request semantics on the cloud-critical path — separate refactor), bedrock boto3 sync-in-async (pre-existing; no new invoke_model calls per doc). Deck #67. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
126 lines
4.1 KiB
Python
126 lines
4.1 KiB
Python
"""Unit tests for BM25 hybrid search algorithm."""
|
||
|
||
from unittest.mock import AsyncMock, MagicMock
|
||
|
||
import pytest
|
||
from qdrant_client import models
|
||
|
||
from nextcloud_mcp_server.search.bm25_hybrid import BM25HybridSearchAlgorithm
|
||
|
||
|
||
@pytest.mark.unit
|
||
def test_bm25_hybrid_initialization_default():
|
||
"""Test BM25HybridSearchAlgorithm initializes with default RRF fusion."""
|
||
algo = BM25HybridSearchAlgorithm()
|
||
|
||
assert algo.score_threshold == 0.0
|
||
assert algo.fusion == models.Fusion.RRF
|
||
assert algo.fusion_name == "rrf"
|
||
assert algo.name == "bm25_hybrid"
|
||
|
||
|
||
@pytest.mark.unit
|
||
def test_bm25_hybrid_initialization_with_rrf():
|
||
"""Test BM25HybridSearchAlgorithm initializes with explicit RRF fusion."""
|
||
algo = BM25HybridSearchAlgorithm(score_threshold=0.5, fusion="rrf")
|
||
|
||
assert algo.score_threshold == 0.5
|
||
assert algo.fusion == models.Fusion.RRF
|
||
assert algo.fusion_name == "rrf"
|
||
|
||
|
||
@pytest.mark.unit
|
||
def test_bm25_hybrid_initialization_with_dbsf():
|
||
"""Test BM25HybridSearchAlgorithm initializes with DBSF fusion."""
|
||
algo = BM25HybridSearchAlgorithm(score_threshold=0.7, fusion="dbsf")
|
||
|
||
assert algo.score_threshold == 0.7
|
||
assert algo.fusion == models.Fusion.DBSF
|
||
assert algo.fusion_name == "dbsf"
|
||
|
||
|
||
@pytest.mark.unit
|
||
def test_bm25_hybrid_invalid_fusion_raises_error():
|
||
"""Test BM25HybridSearchAlgorithm raises ValueError for invalid fusion."""
|
||
with pytest.raises(ValueError) as exc_info:
|
||
BM25HybridSearchAlgorithm(fusion="invalid")
|
||
|
||
assert "Invalid fusion algorithm 'invalid'" in str(exc_info.value)
|
||
assert "Must be 'rrf' or 'dbsf'" in str(exc_info.value)
|
||
|
||
|
||
@pytest.mark.unit
|
||
def test_bm25_hybrid_requires_vector_db():
|
||
"""Test BM25HybridSearchAlgorithm reports it requires vector database."""
|
||
algo = BM25HybridSearchAlgorithm()
|
||
assert algo.requires_vector_db is True
|
||
|
||
|
||
@pytest.fixture
|
||
def patched_search(monkeypatch):
|
||
"""Stub the embedding / BM25 / Qdrant deps of search() and return the
|
||
embed_with_usage mock so tests can assert how often the query was embedded."""
|
||
embed = AsyncMock(return_value=([0.1, 0.2, 0.3], 7))
|
||
svc = MagicMock()
|
||
svc.embed_with_usage = embed
|
||
monkeypatch.setattr(
|
||
"nextcloud_mcp_server.search.bm25_hybrid.get_embedding_service", lambda: svc
|
||
)
|
||
|
||
bm25 = MagicMock()
|
||
bm25.encode_async = AsyncMock(return_value={"indices": [1], "values": [0.5]})
|
||
monkeypatch.setattr(
|
||
"nextcloud_mcp_server.search.bm25_hybrid.get_bm25_service",
|
||
AsyncMock(return_value=bm25),
|
||
)
|
||
|
||
qdrant = MagicMock()
|
||
empty = MagicMock()
|
||
empty.points = []
|
||
qdrant.query_points = AsyncMock(return_value=empty)
|
||
monkeypatch.setattr(
|
||
"nextcloud_mcp_server.search.bm25_hybrid.get_qdrant_client",
|
||
AsyncMock(return_value=qdrant),
|
||
)
|
||
|
||
settings = MagicMock()
|
||
settings.get_collection_name.return_value = "test_collection"
|
||
monkeypatch.setattr(
|
||
"nextcloud_mcp_server.search.bm25_hybrid.get_settings", lambda: settings
|
||
)
|
||
monkeypatch.setattr(
|
||
"nextcloud_mcp_server.search.bm25_hybrid.build_base_filter_conditions",
|
||
lambda **kwargs: [],
|
||
)
|
||
return embed
|
||
|
||
|
||
@pytest.mark.unit
|
||
async def test_query_embedded_and_metered_once_across_doc_types(patched_search):
|
||
"""nc_semantic_search calls search() once per doc_type on one instance with
|
||
the same query; the dense embedding (and its billed token count) must be
|
||
computed exactly once, not once per type."""
|
||
embed = patched_search
|
||
algo = BM25HybridSearchAlgorithm()
|
||
|
||
for dtype in ("note", "file", "deck_card"):
|
||
await algo.search(query="hello", user_id="alice", doc_type=dtype)
|
||
|
||
assert embed.await_count == 1 # embedded once, not 3×
|
||
assert (
|
||
algo.query_token_count == 7
|
||
) # single query's token count, not summed/overwritten
|
||
assert algo.query_embedding == [0.1, 0.2, 0.3]
|
||
|
||
|
||
@pytest.mark.unit
|
||
async def test_different_query_invalidates_cache(patched_search):
|
||
"""A different query string re-embeds (and re-meters)."""
|
||
embed = patched_search
|
||
algo = BM25HybridSearchAlgorithm()
|
||
|
||
await algo.search(query="hello", user_id="alice")
|
||
await algo.search(query="world", user_id="alice")
|
||
|
||
assert embed.await_count == 2
|