06443947bf
신규 파일: - classifier_service.py: exaone binary classifier (sufficient/insufficient) parallel with evidence, circuit breaker, timeout 5s - refusal_gate.py: multi-signal fusion (score + classifier) AND 조건, conservative fallback 3-tier (classifier 부재 시) - grounding_check.py: strong/weak flag 분리 strong: fabricated_number + intent_misalignment(important keywords) weak: uncited_claim + low_overlap + intent_misalignment(generic) re-gate: 2+ strong → refuse, 1 strong → partial - sentence_splitter.py: regex 기반 (Phase 3.5b KSS 업그레이드) - classifier.txt: exaone Y+ prompt (calibration examples 포함) - search_synthesis_partial.txt: partial answer 전용 프롬프트 - 102_ask_events.sql: /ask 관측 테이블 (completeness 3-분리 지표) - queries.yaml: Phase 3.5 smoke test 평가셋 10개 수정 파일: - search.py /ask: classifier parallel + refusal gate + grounding re-gate + defense_layers 로깅 + AskResponse completeness/aspects/confirmed_items - config.yaml: classifier model 섹션 (exaone3.5:7.8b GPU Ollama) - config.py: classifier optional 파싱 - AskAnswer.svelte: 4분기 렌더 (full/partial/insufficient/loading) - ask.ts: Completeness + ConfirmedItem 타입 P1 실측: exaone ternary 불안정 → binary gate 축소. partial은 grounding이 담당. 토론 9라운드 확정. plan: quiet-meandering-nova.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
115 lines
3.0 KiB
YAML
115 lines
3.0 KiB
YAML
# hyungi_Document_Server 설정
|
|
|
|
ai:
|
|
gateway:
|
|
endpoint: "http://ai-gateway:8080"
|
|
|
|
models:
|
|
primary:
|
|
endpoint: "http://100.76.254.116:8801/v1/chat/completions"
|
|
model: "mlx-community/gemma-4-26b-a4b-it-8bit"
|
|
max_tokens: 4096
|
|
timeout: 60
|
|
|
|
fallback:
|
|
endpoint: "http://ollama:11434/v1/chat/completions"
|
|
model: "qwen3.5:9b-q8_0"
|
|
max_tokens: 4096
|
|
timeout: 120
|
|
|
|
premium:
|
|
endpoint: "https://api.anthropic.com/v1/messages"
|
|
model: "claude-sonnet-4-20250514"
|
|
max_tokens: 8192
|
|
daily_budget_usd: 5.00
|
|
require_explicit_trigger: true
|
|
|
|
embedding:
|
|
endpoint: "http://ollama:11434/api/embeddings"
|
|
model: "bge-m3"
|
|
|
|
vision:
|
|
endpoint: "http://ollama:11434/api/generate"
|
|
model: "Qwen2.5-VL-7B"
|
|
|
|
rerank:
|
|
endpoint: "http://ollama:11434/api/rerank"
|
|
model: "bge-reranker-v2-m3"
|
|
# Phase 3.5a: exaone answerability classifier (GPU Ollama, concurrent OK)
|
|
classifier:
|
|
endpoint: "http://ollama:11434/v1/chat/completions"
|
|
model: "exaone3.5:7.8b-instruct-q8_0"
|
|
max_tokens: 512
|
|
timeout: 10
|
|
|
|
nas:
|
|
mount_path: "/documents"
|
|
pkm_root: "/documents/PKM"
|
|
|
|
# ─── 문서 분류 체계 ───
|
|
taxonomy:
|
|
Philosophy:
|
|
Ethics: []
|
|
Metaphysics: []
|
|
Epistemology: []
|
|
Logic: []
|
|
Aesthetics: []
|
|
Eastern_Philosophy: []
|
|
Western_Philosophy: []
|
|
Language:
|
|
Korean: []
|
|
English: []
|
|
Japanese: []
|
|
Translation: []
|
|
Linguistics: []
|
|
Engineering:
|
|
Mechanical: [Piping, HVAC, Equipment]
|
|
Electrical: [Power, Instrumentation]
|
|
Chemical: [Process, Material]
|
|
Civil: []
|
|
Network: [Server, Security, Infrastructure]
|
|
Industrial_Safety:
|
|
Legislation: [Act, Decree, Foreign_Law, Korea_Law_Archive, Enforcement_Rule, Public_Notice, SAPA]
|
|
Theory: [Industrial_Safety_General, Safety_Health_Fundamentals]
|
|
Academic_Papers: [Safety_General, Risk_Assessment_Research]
|
|
Cases: [Domestic, International]
|
|
Practice: [Checklist, Contractor_Management, Safety_Education, Emergency_Plan, Patrol_Inspection, Permit_to_Work, PPE, Safety_Plan]
|
|
Risk_Assessment: [KRAS, JSA, Checklist_Method]
|
|
Safety_Manager: [Appointment, Duty_Record, Improvement, Inspection, Meeting]
|
|
Health_Manager: [Appointment, Duty_Record, Ergonomics, Health_Checkup, Mental_Health, MSDS, Work_Environment]
|
|
Programming:
|
|
Programming_Language: [Python, JavaScript, Go, Rust]
|
|
Framework: [FastAPI, SvelteKit, React]
|
|
DevOps: [Docker, CI_CD, Linux_Administration]
|
|
AI_ML: [Large_Language_Model, Computer_Vision, Data_Science]
|
|
Database: []
|
|
Software_Architecture: []
|
|
General:
|
|
Reading_Notes: []
|
|
Self_Development: []
|
|
Business: []
|
|
Science: []
|
|
History: []
|
|
|
|
document_types:
|
|
- Reference
|
|
- Standard
|
|
- Manual
|
|
- Drawing
|
|
- Template
|
|
- Note
|
|
- Academic_Paper
|
|
- Law_Document
|
|
- Report
|
|
- Memo
|
|
- Checklist
|
|
- Meeting_Minutes
|
|
- Specification
|
|
|
|
schedule:
|
|
law_monitor: "07:00"
|
|
mailplus_archive: ["07:00", "18:00"]
|
|
daily_digest: "20:00"
|
|
file_watcher_interval_minutes: 5
|
|
queue_consumer_interval_minutes: 10
|