M25: expose provenance-aware knowledge statistics

This commit is contained in:
NuklearRabbit
2026-08-10 16:04:39 +02:00
parent 0935901f11
commit 90cc3cf378
22 changed files with 238 additions and 10 deletions
+25 -1
View File
@@ -100,6 +100,30 @@ def record_feedback(
@router.get("/status", response_model=KnowledgeHealth)
def knowledge_status(
language: SupportedLanguage = "en-GB",
db: Session = Depends(get_db),
_user: CurrentUser = Depends(get_current_user),
) -> KnowledgeHealth:
return get_knowledge_provider().health(language)
health = get_knowledge_provider().health(language)
if health.provider != "ragcore":
return health
latest_sync = db.scalar(
select(AuditEvent)
.where(AuditEvent.action == "n8n_procedures_synced")
.order_by(AuditEvent.occurred_at.desc())
.limit(1)
)
if latest_sync is None:
return health
reported = latest_sync.after_json or {}
synced = reported.get("synced")
failed = reported.get("failed")
return health.model_copy(
update={
"reported_synced_document_count": synced if isinstance(synced, int) else None,
"reported_failed_document_count": failed if isinstance(failed, int) else None,
"last_sync_at": latest_sync.occurred_at,
"statistics_state": "sync_reported",
}
)
@@ -1,5 +1,6 @@
from __future__ import annotations
from datetime import datetime
from functools import lru_cache
from typing import Literal, Protocol
@@ -8,6 +9,7 @@ from pydantic import BaseModel
from app.core.config import get_settings
EvidenceState = Literal["grounded", "insufficient", "unavailable"]
KnowledgeStatisticsState = Literal["verified", "sync_reported", "not_reported"]
class SourceCard(BaseModel):
@@ -36,6 +38,11 @@ class KnowledgeHealth(BaseModel):
# A provider may be healthy without exposing a corpus-size endpoint. `None` means
# unknown, never "zero procedures".
document_count: int | None
source_document_count: int
reported_synced_document_count: int | None
reported_failed_document_count: int | None
last_sync_at: datetime | None
statistics_state: KnowledgeStatisticsState
class KnowledgeProvider(Protocol):
+5
View File
@@ -322,6 +322,11 @@ class DemoKnowledgeProvider:
workspace=self._settings.ragcore_workspace,
collection=self._settings.ragcore_collection,
document_count=self._document_count_by_language[language],
source_document_count=self._document_count_by_language[language],
reported_synced_document_count=None,
reported_failed_document_count=None,
last_sync_at=None,
statistics_state="verified",
)
def _score(
+12
View File
@@ -1,9 +1,12 @@
from __future__ import annotations
from pathlib import Path
import httpx
from app.core.config import get_settings
from app.services.knowledge import EvidenceState, GroundedAnswer, KnowledgeHealth, SourceCard
from app.services.knowledge.procedures import iter_procedure_documents
_GROUNDED_ANSWERABILITY = {"answerable", "partially_answerable"}
@@ -140,6 +143,10 @@ class RAGcoreKnowledgeProvider:
except (httpx.HTTPError, ValueError) as exc:
available = False
detail = f"RAGcore unavailable: {type(exc).__name__}: {exc}"
source_document_count = sum(
document.language == language
for document in iter_procedure_documents(Path(self._settings.knowledge_dir))
)
return KnowledgeHealth(
provider=self.name,
available=available,
@@ -150,6 +157,11 @@ class RAGcoreKnowledgeProvider:
# RAGcore's retrieval API has no corpus-size endpoint. Unknown is explicit
# so the UI never turns this into the misleading claim "0 procedures".
document_count=None,
source_document_count=source_document_count,
reported_synced_document_count=None,
reported_failed_document_count=None,
last_sync_at=None,
statistics_state="not_reported",
)
def ask(self, question: str, correlation_id: str, language: str = "en-GB") -> GroundedAnswer:
+47
View File
@@ -5,7 +5,9 @@ from pathlib import Path
import httpx
from app.api.routers import knowledge as knowledge_router
from app.core.config import get_settings
from app.services.knowledge import KnowledgeHealth
from app.services.knowledge.demo import DemoKnowledgeProvider
from app.services.knowledge.ragcore import RAGcoreKnowledgeProvider
@@ -73,6 +75,8 @@ def test_demo_provider_health_reports_document_count():
assert health.provider == "demo"
assert health.available is True
assert health.document_count == 11
assert health.source_document_count == 11
assert health.statistics_state == "verified"
def test_demo_provider_health_reports_document_count_per_language():
@@ -154,6 +158,46 @@ def test_knowledge_status_endpoint(ops_client):
assert response.json()["provider"] == "demo"
def test_ragcore_status_separates_sync_report_from_unverifiable_index(
client, ops_client, monkeypatch
):
class FakeRagcoreProvider:
def health(self, language="en-GB"):
return KnowledgeHealth(
provider="ragcore",
available=True,
detail="ready",
tenant="fleet-ops",
workspace="operations",
collection="internal-procedures",
document_count=None,
source_document_count=11,
reported_synced_document_count=None,
reported_failed_document_count=None,
last_sync_at=None,
statistics_state="not_reported",
)
monkeypatch.setattr(knowledge_router, "get_knowledge_provider", FakeRagcoreProvider)
settings = get_settings()
sync = client.post(
"/api/v1/integrations/n8n/procedures-sync-result",
json={"execution_id": "rag-statistics-test", "synced": 32, "failed": 1},
headers={"X-Service-Token": settings.n8n_callback_token},
)
assert sync.status_code == 200
response = ops_client.get("/api/v1/knowledge/status?language=nl-BE")
assert response.status_code == 200
status = response.json()
assert status["document_count"] is None
assert status["source_document_count"] == 11
assert status["reported_synced_document_count"] == 32
assert status["reported_failed_document_count"] == 1
assert status["last_sync_at"] is not None
assert status["statistics_state"] == "sync_reported"
class _FakeResponse:
def __init__(self, status_code: int, body: dict):
self.status_code = status_code
@@ -224,6 +268,9 @@ def test_ragcore_provider_health_reports_ready_status(monkeypatch):
health = provider.health()
assert health.provider == "ragcore"
assert health.available is True
assert health.document_count is None
assert health.source_document_count == 11
assert health.statistics_state == "not_reported"
def test_ragcore_provider_health_reports_degraded_status(monkeypatch):