feat: Intelligence Pipeline v3 — full implementation
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.
This commit is contained in:
@@ -0,0 +1,40 @@
|
||||
"""Symbol resolution package for Intelligence Pipeline v3.
|
||||
|
||||
Resolves company mentions in documents to canonical identifiers using the
|
||||
symbol registry, supporting alias matching, ambiguity detection, and
|
||||
separation of explicit mentions from inferred exposures.
|
||||
"""
|
||||
|
||||
from services.intelligence_pipeline_v3.resolution.alias_index import (
|
||||
AliasIndex,
|
||||
build_alias_index,
|
||||
)
|
||||
from services.intelligence_pipeline_v3.resolution.explicit_vs_inferred import (
|
||||
ClassifiedMentionType,
|
||||
classify_mention,
|
||||
to_mention_type,
|
||||
)
|
||||
from services.intelligence_pipeline_v3.resolution.models import (
|
||||
MatchType,
|
||||
MentionType,
|
||||
ResolutionCandidate,
|
||||
ResolutionResult,
|
||||
UnresolvedMention,
|
||||
UnresolvedReason,
|
||||
)
|
||||
from services.intelligence_pipeline_v3.resolution.symbol_resolver import SymbolResolver
|
||||
|
||||
__all__ = [
|
||||
"AliasIndex",
|
||||
"ClassifiedMentionType",
|
||||
"MatchType",
|
||||
"MentionType",
|
||||
"ResolutionCandidate",
|
||||
"ResolutionResult",
|
||||
"SymbolResolver",
|
||||
"UnresolvedMention",
|
||||
"UnresolvedReason",
|
||||
"build_alias_index",
|
||||
"classify_mention",
|
||||
"to_mention_type",
|
||||
]
|
||||
Reference in New Issue
Block a user