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.
29 lines
639 B
Python
29 lines
639 B
Python
"""Offline replay module for Gold Corpus comparison.
|
|
|
|
Runs pipeline configurations against the Gold Corpus, produces field-level
|
|
and calibration reports, compares v2 baseline vs v3, and enforces
|
|
safety-critical promotion gates.
|
|
"""
|
|
|
|
from services.intelligence_pipeline_v3.replay.reports import (
|
|
FieldReport,
|
|
GateStatus,
|
|
PromotionGate,
|
|
ReplayReport,
|
|
)
|
|
from services.intelligence_pipeline_v3.replay.runner import (
|
|
ReplayConfig,
|
|
ReplayResult,
|
|
ReplayRunner,
|
|
)
|
|
|
|
__all__ = [
|
|
"FieldReport",
|
|
"GateStatus",
|
|
"PromotionGate",
|
|
"ReplayConfig",
|
|
"ReplayReport",
|
|
"ReplayResult",
|
|
"ReplayRunner",
|
|
]
|