Celes Renata
a72f336ad1
Multi-stage evidence-grounded inference architecture replacing the monolithic 9B model extraction pipeline. CPU-first specialist services handle routine extraction while the 9B vLLM model is preserved for semantic adjudication of ambiguous cases. Key components: - Capability-aware inference gateway (OpenAI-compatible + Ollama) - Endpoint registry with DB migrations and REST API - Sentence-aware document segmenter (property tests) - Deterministic financial parsing with offset integrity - Symbol resolution with ambiguity detection - Specialist service (GLiNER2, dynamic batching, K8s deployment) - Company-specific sentiment (FinBERT, calibration) - Retrieval-based novelty and duplicate detection - Confidence calibration pipeline - Deterministic routing engine (property tests) - 9B adjudication layer with VRAM gating - Stock-specific impact model (features, labels, baseline, trained) - Pipeline orchestrator (state machine, queues, leases, feature flags) - Bounded parallelism (async workers, semaphore, load shedding) - Observability (tracing, metrics, alerts) - Compatibility adapter (v3→v2 golden mapping tests) - Shadow/canary promotion framework - Active learning and fine-tuning pipeline Test results: 1,161 tests pass, ruff lint clean. All 282 spec tasks completed.
82 lines
2.5 KiB
Python
82 lines
2.5 KiB
Python
"""Audit record storage with filtering and retrieval.
|
|
|
|
In production, this would be backed by PostgreSQL.
|
|
This implementation provides the storage interface for testing.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from uuid import UUID
|
|
|
|
from services.intelligence_pipeline_v3.audit.models import (
|
|
AuditRecord,
|
|
CorrectionEvent,
|
|
ReviewFilter,
|
|
)
|
|
|
|
|
|
@dataclass
|
|
class AuditStore:
|
|
"""In-memory audit record store with filtering.
|
|
|
|
Provides storage, retrieval, and filtering of audit records and
|
|
their immutable correction events.
|
|
"""
|
|
|
|
_records: dict[UUID, AuditRecord] = field(default_factory=dict)
|
|
_corrections: list[CorrectionEvent] = field(default_factory=list)
|
|
|
|
def store(self, record: AuditRecord) -> None:
|
|
"""Store an audit record."""
|
|
self._records[record.record_id] = record
|
|
|
|
def get(self, record_id: UUID) -> AuditRecord | None:
|
|
"""Retrieve a record by ID."""
|
|
return self._records.get(record_id)
|
|
|
|
def get_by_document(self, document_id: str) -> list[AuditRecord]:
|
|
"""Get all records for a document."""
|
|
return [
|
|
r for r in self._records.values() if r.document_id == document_id
|
|
]
|
|
|
|
def get_by_run(self, run_id: UUID) -> AuditRecord | None:
|
|
"""Get the record for a pipeline run."""
|
|
for r in self._records.values():
|
|
if r.run_id == run_id:
|
|
return r
|
|
return None
|
|
|
|
def add_correction(
|
|
self, record_id: UUID, correction: CorrectionEvent
|
|
) -> bool:
|
|
"""Add a correction to a record. Returns False if record not found."""
|
|
record = self._records.get(record_id)
|
|
if record is None:
|
|
return False
|
|
record.add_correction(correction)
|
|
self._corrections.append(correction)
|
|
return True
|
|
|
|
def filter(self, criteria: ReviewFilter) -> list[AuditRecord]:
|
|
"""Filter records by criteria."""
|
|
return [
|
|
r for r in self._records.values() if criteria.matches(r)
|
|
]
|
|
|
|
def get_corrections(self, record_id: UUID) -> list[CorrectionEvent]:
|
|
"""Get all corrections for a record."""
|
|
record = self._records.get(record_id)
|
|
if record is None:
|
|
return []
|
|
return list(record.corrections)
|
|
|
|
def count(self) -> int:
|
|
"""Total stored records."""
|
|
return len(self._records)
|
|
|
|
def correction_count(self) -> int:
|
|
"""Total correction events across all records."""
|
|
return len(self._corrections)
|