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.
13 lines
568 B
Python
13 lines
568 B
Python
"""Specialist inference service — CPU-first NER, classification, and extraction.
|
|
|
|
Provides batch endpoints for entity extraction, event classification,
|
|
relation extraction, and structured fact extraction. Uses GLiNER2 Large
|
|
as the initial model candidate with a mock fallback for testing.
|
|
|
|
Endpoints:
|
|
POST /api/specialist/entities — batch entity extraction
|
|
POST /api/specialist/classify — batch event classification
|
|
POST /api/specialist/relations — batch relation extraction
|
|
POST /api/specialist/extract — batch structured extraction
|
|
"""
|