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.
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
"""Evidence verification and grounding for Intelligence Pipeline v3.
|
|
|
|
This package provides:
|
|
- Offset, entity association, and numeric consistency verification
|
|
- Rejected-candidate storage with structured reason codes
|
|
- A compact entailment verifier scaffold (keyword-overlap baseline)
|
|
- Evidence coverage and unsupported-claim metrics
|
|
- Aggregated verification metrics for dashboards and promotion gates
|
|
"""
|
|
|
|
from services.intelligence_pipeline_v3.verification.coverage import (
|
|
CoverageMetrics,
|
|
FieldEvidence,
|
|
compute_coverage,
|
|
)
|
|
from services.intelligence_pipeline_v3.verification.entailment import (
|
|
EntailmentResult,
|
|
EntailmentVerifier,
|
|
)
|
|
from services.intelligence_pipeline_v3.verification.metrics import (
|
|
VerificationMetrics,
|
|
compute_verification_metrics,
|
|
)
|
|
from services.intelligence_pipeline_v3.verification.models import (
|
|
AssociationVerification,
|
|
NumericVerification,
|
|
OffsetVerification,
|
|
RejectedCandidate,
|
|
RejectionReason,
|
|
VerificationReport,
|
|
)
|
|
from services.intelligence_pipeline_v3.verification.rejected_store import (
|
|
RejectedCandidateStore,
|
|
)
|
|
from services.intelligence_pipeline_v3.verification.verifier import EvidenceVerifier
|
|
|
|
__all__ = [
|
|
"AssociationVerification",
|
|
"CoverageMetrics",
|
|
"EntailmentResult",
|
|
"EntailmentVerifier",
|
|
"EvidenceVerifier",
|
|
"FieldEvidence",
|
|
"NumericVerification",
|
|
"OffsetVerification",
|
|
"RejectedCandidate",
|
|
"RejectedCandidateStore",
|
|
"RejectionReason",
|
|
"VerificationMetrics",
|
|
"VerificationReport",
|
|
"compute_coverage",
|
|
"compute_verification_metrics",
|
|
]
|