Commit Graph

4 Commits

Author SHA1 Message Date
shinalok 0b50444e43 IDEA-2/1/5/7: 스마트 알림, 대화 기반 RAG, CRAG, 파라미터 자동 튜닝
- IDEA-2 스마트 알림: td_reminders 테이블, set_reminder/list_reminders 도구,
  SchedulerService(asyncio 60초 루프, D-7/D-1/D-0 Telegram push),
  FastAPI lifespan 연동, GET /reminders/{user_id} 엔드포인트

- IDEA-1 대화 기반 RAG: IngestionService.store_text() 추가,
  AgentService._maybe_index_conversation() — 응답 후 LLM 판단 → Qdrant 저장
  (CONV_RAG_ENABLED=true 활성화, background task로 응답 속도 무관)

- IDEA-5 CRAG: AgentState에 crag_fallback_used 플래그 추가,
  crag_check LangGraph 노드 — search_documents 결과 없으면 web_search 자동 주입,
  route_after_crag으로 fallback 1회 루프 제어 (CRAG_ENABLED=true 활성화)

- IDEA-7 RAG Auto-Eval: eval/auto_tune.py — API 서버 없이 파라미터 조합별
  context_precision/recall 비교, 최적 설정 추천

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-04 10:04:05 +09:00
shinalok bdb6fd83c4 Fix RAGAS eval: increase timeout for local LLM, safe score extraction
- RunConfig(timeout=600, max_workers=1): local Qwen3 needs more than 60s/call
- Extract scores from df.mean() instead of result[key] to handle NaN safely

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 19:41:32 +09:00
shinalok a2dff825ad Fix: use Container class (not container instance) in eval script
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 17:43:51 +09:00
shinalok 3faf8b09ce Phase 20: RAGAS evaluation suite
- eval/run_ragas.py: collect contexts (RetrieverService) + answers (/chat API),
  evaluate with faithfulness / answer_relevancy / context_recall / context_precision
- eval/dataset.jsonl: 5 Korean Q&A pairs for initial evaluation
- eval/requirements.txt: ragas==0.2.9, datasets, langchain-google-vertexai
- Evaluator LLM priority: OpenAI > Anthropic > local Qwen3
- Runtime shim for ragas 0.2 / langchain-community 0.4+ vertexai incompatibility

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-01 17:11:00 +09:00