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.
33 lines
988 B
Python
33 lines
988 B
Python
"""Deterministic routing engine for Intelligence Pipeline v3.
|
|
|
|
Routes documents to fast-path or adjudication based on hard ambiguity/conflict
|
|
rules and calibrated confidence thresholds. Every routing decision is stored
|
|
with the full feature snapshot for audit and calibration feedback.
|
|
"""
|
|
|
|
from services.intelligence_pipeline_v3.routing.reasons import (
|
|
RouteDecision,
|
|
RoutingReason,
|
|
)
|
|
from services.intelligence_pipeline_v3.routing.router import (
|
|
RoutingDecision,
|
|
RoutingEngine,
|
|
)
|
|
from services.intelligence_pipeline_v3.routing.rules import evaluate_hard_rules
|
|
from services.intelligence_pipeline_v3.routing.store import RoutingDecisionStore
|
|
from services.intelligence_pipeline_v3.routing.thresholds import (
|
|
FastPathThresholds,
|
|
evaluate_thresholds,
|
|
)
|
|
|
|
__all__ = [
|
|
"FastPathThresholds",
|
|
"RouteDecision",
|
|
"RoutingDecision",
|
|
"RoutingEngine",
|
|
"RoutingReason",
|
|
"RoutingDecisionStore",
|
|
"evaluate_hard_rules",
|
|
"evaluate_thresholds",
|
|
]
|