evalvault 1.57.1__py3-none-any.whl → 1.59.0__py3-none-any.whl

evalvault-1.59.0.dist-info/METADATA

@@ -0,0 +1,327 @@
+Metadata-Version: 2.4
+Name: evalvault
+Version: 1.59.0
+Summary: RAG evaluation system using Ragas with Phoenix/Langfuse tracing
+Project-URL: Homepage, https://github.com/ntts9990/EvalVault
+Project-URL: Documentation, https://github.com/ntts9990/EvalVault#readme
+Project-URL: Repository, https://github.com/ntts9990/EvalVault.git
+Project-URL: Issues, https://github.com/ntts9990/EvalVault/issues
+Project-URL: Changelog, https://github.com/ntts9990/EvalVault/releases
+Author: EvalVault Contributors
+Maintainer: EvalVault Contributors
+License: Apache-2.0
+License-File: LICENSE.md
+Keywords: ai,evaluation,langfuse,llm,machine-learning,nlp,observability,opentelemetry,phoenix,rag,ragas,retrieval-augmented-generation,testing
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Testing
+Classifier: Typing :: Typed
+Requires-Python: >=3.12
+Requires-Dist: chardet
+Requires-Dist: fastapi>=0.128.0
+Requires-Dist: instructor
+Requires-Dist: langchain-openai
+Requires-Dist: langfuse
+Requires-Dist: matplotlib<3.9.0,>=3.8.0
+Requires-Dist: networkx
+Requires-Dist: openai
+Requires-Dist: openpyxl
+Requires-Dist: pandas
+Requires-Dist: pydantic
+Requires-Dist: pydantic-settings
+Requires-Dist: python-multipart
+Requires-Dist: ragas==0.4.2
+Requires-Dist: rich
+Requires-Dist: truststore>=0.10.4
+Requires-Dist: typer
+Requires-Dist: uvicorn>=0.40.0
+Requires-Dist: xlrd
+Provides-Extra: analysis
+Requires-Dist: scikit-learn>=1.3.0; extra == 'analysis'
+Provides-Extra: anthropic
+Requires-Dist: anthropic; extra == 'anthropic'
+Requires-Dist: langchain-anthropic; extra == 'anthropic'
+Provides-Extra: benchmark
+Requires-Dist: datasets>=2.0.0; extra == 'benchmark'
+Requires-Dist: lm-eval[api]>=0.4.0; extra == 'benchmark'
+Provides-Extra: dashboard
+Requires-Dist: matplotlib<3.9.0,>=3.8.0; extra == 'dashboard'
+Provides-Extra: dev
+Requires-Dist: anthropic; extra == 'dev'
+Requires-Dist: arize-phoenix>=8.0.0; extra == 'dev'
+Requires-Dist: datasets>=2.0.0; extra == 'dev'
+Requires-Dist: faiss-cpu>=1.8.0; extra == 'dev'
+Requires-Dist: ijson>=3.3.0; extra == 'dev'
+Requires-Dist: kiwipiepy>=0.18.0; extra == 'dev'
+Requires-Dist: langchain-anthropic; extra == 'dev'
+Requires-Dist: lm-eval[api]>=0.4.0; extra == 'dev'
+Requires-Dist: mkdocs-material>=9.5.0; extra == 'dev'
+Requires-Dist: mkdocs>=1.5.0; extra == 'dev'
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == 'dev'
+Requires-Dist: mlflow>=2.0.0; extra == 'dev'
+Requires-Dist: openinference-instrumentation-langchain>=0.1.0; extra == 'dev'
+Requires-Dist: opentelemetry-api>=1.20.0; extra == 'dev'
+Requires-Dist: opentelemetry-exporter-otlp>=1.20.0; extra == 'dev'
+Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'dev'
+Requires-Dist: psycopg[binary]>=3.0.0; extra == 'dev'
+Requires-Dist: pydeps>=3.0.1; extra == 'dev'
+Requires-Dist: pymdown-extensions>=10.7.0; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Requires-Dist: pytest-asyncio; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest-html; extra == 'dev'
+Requires-Dist: pytest-mock; extra == 'dev'
+Requires-Dist: pytest-rerunfailures; extra == 'dev'
+Requires-Dist: pytest-xdist; extra == 'dev'
+Requires-Dist: python-multipart; extra == 'dev'
+Requires-Dist: rank-bm25>=0.2.2; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Requires-Dist: scikit-learn<1.4.0,>=1.3.0; extra == 'dev'
+Requires-Dist: sentence-transformers>=5.2.0; extra == 'dev'
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9.5.0; extra == 'docs'
+Requires-Dist: mkdocs>=1.5.0; extra == 'docs'
+Requires-Dist: mkdocstrings[python]>=0.24.0; extra == 'docs'
+Requires-Dist: pymdown-extensions>=10.7.0; extra == 'docs'
+Provides-Extra: korean
+Requires-Dist: kiwipiepy>=0.18.0; extra == 'korean'
+Requires-Dist: rank-bm25>=0.2.2; extra == 'korean'
+Requires-Dist: sentence-transformers>=5.2.0; extra == 'korean'
+Provides-Extra: mlflow
+Requires-Dist: mlflow>=2.0.0; extra == 'mlflow'
+Provides-Extra: perf
+Requires-Dist: faiss-cpu>=1.8.0; extra == 'perf'
+Requires-Dist: ijson>=3.3.0; extra == 'perf'
+Provides-Extra: phoenix
+Requires-Dist: arize-phoenix>=8.0.0; extra == 'phoenix'
+Requires-Dist: openinference-instrumentation-langchain>=0.1.0; extra == 'phoenix'
+Requires-Dist: opentelemetry-api>=1.20.0; extra == 'phoenix'
+Requires-Dist: opentelemetry-exporter-otlp>=1.20.0; extra == 'phoenix'
+Requires-Dist: opentelemetry-sdk>=1.20.0; extra == 'phoenix'
+Provides-Extra: postgres
+Requires-Dist: psycopg[binary]>=3.0.0; extra == 'postgres'
+Provides-Extra: timeseries
+Requires-Dist: aeon>=1.3.0; extra == 'timeseries'
+Requires-Dist: numba>=0.55.0; extra == 'timeseries'
+Provides-Extra: web
+Description-Content-Type: text/markdown
+
+# EvalVault
+
+RAG(Retrieval-Augmented Generation) 시스템을 대상으로 **평가(Eval) → 분석(Analysis) → 추적(Tracing) → 개선 루프**를 하나의 워크플로로 묶는 CLI + Web UI 플랫폼입니다.
+
+[![PyPI](https://img.shields.io/pypi/v/evalvault.svg)](https://pypi.org/project/evalvault/)
+[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
+[![CI](https://github.com/ntts9990/EvalVault/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/ntts9990/EvalVault/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE.md)
+
+English version? See `README.en.md`.
+
+---
+
+## Quick Links
+
+- 문서 허브: `docs/INDEX.md`
+- 사용자 가이드: `docs/guides/USER_GUIDE.md`
+- 개발 가이드: `docs/guides/DEV_GUIDE.md`
+- 상태/로드맵: `docs/STATUS.md`, `docs/ROADMAP.md`
+- 개발 백서(설계/운영/품질 기준): `docs/new_whitepaper/INDEX.md`
+- Open RAG Trace: `docs/architecture/open-rag-trace-spec.md`
+
+---
+
+## EvalVault가 해결하는 문제
+
+RAG를 운영하다 보면 결국 아래 질문으로 귀결됩니다.
+
+- “모델/프롬프트/리트리버를 바꿨는데, **진짜 좋아졌나?**”
+- “좋아졌다면 **왜** 좋아졌고, 나빠졌다면 **어디서** 깨졌나?”
+- “이 결론을 **재현 가능하게** 팀/CI에서 계속 검증할 수 있나?”
+
+EvalVault는 위 질문을 **데이터셋 + 메트릭 + (선택)트레이싱** 관점에서 한 번에 답할 수 있게 설계했습니다.
+
+---
+
+## 핵심 개념
+
+- **Run 단위**: 평가/분석/아티팩트/트레이스가 하나의 `run_id`로 묶입니다.
+- **Dataset 중심**: threshold(합격 기준)는 데이터셋에 포함되어 “도메인별 합격 기준”을 유지합니다.
+- **Artifacts-first**: 보고서(요약)뿐 아니라, 분석 모듈별 원본 결과(아티팩트)를 구조화된 디렉터리에 보존합니다.
+- **Observability 옵션화**: Phoenix/Langfuse/MLflow는 “필요할 때 켜는” 방식으로, 실행 경로는 최대한 단순하게 유지합니다.
+
+---
+
+## 3분 Quickstart (CLI)
+
+```bash
+uv sync --extra dev
+cp .env.example .env
+
+uv run evalvault run --mode simple tests/fixtures/e2e/insurance_qa_korean.json \
+  --metrics faithfulness,answer_relevancy \
+  --profile dev \
+  --db data/db/evalvault.db \
+  --auto-analyze
+```
+
+- 결과는 `--db`에 저장되어 `history`, Web UI, 비교 분석에서 재사용됩니다.
+- `--auto-analyze`는 요약 리포트 + 모듈별 아티팩트를 함께 생성합니다.
+
+---
+
+## Web UI (FastAPI + React)
+
+```bash
+# API
+uv run evalvault serve-api --reload
+
+# Frontend
+cd frontend
+npm install
+npm run dev
+```
+
+브라우저에서 `http://localhost:5173` 접속 후, Evaluation Studio에서 실행/히스토리/리포트를 확인합니다.
+
+---
+
+## 산출물(Artifacts) 경로
+
+- 단일 실행 자동 분석:
+  - 요약 JSON: `reports/analysis/analysis_<RUN_ID>.json`
+  - 보고서: `reports/analysis/analysis_<RUN_ID>.md`
+  - 아티팩트 인덱스: `reports/analysis/artifacts/analysis_<RUN_ID>/index.json`
+  - 노드별 결과: `reports/analysis/artifacts/analysis_<RUN_ID>/<node_id>.json`
+
+- A/B 비교 분석:
+  - 요약 JSON: `reports/comparison/comparison_<RUN_A>_<RUN_B>.json`
+  - 보고서: `reports/comparison/comparison_<RUN_A>_<RUN_B>.md`
+
+---
+
+## 데이터셋 포맷(요약)
+
+```json
+{
+  "name": "insurance-qa",
+  "version": "1.0.0",
+  "thresholds": { "faithfulness": 0.8 },
+  "test_cases": [
+    {
+      "id": "tc-001",
+      "question": "...",
+      "answer": "...",
+      "contexts": ["..."]
+    }
+  ]
+}
+```
+
+- 필수 필드: `id`, `question`, `answer`, `contexts`
+- `ground_truth`는 일부 메트릭에서 필요합니다.
+- 템플릿: `docs/templates/dataset_template.json`, `docs/templates/dataset_template.csv`, `docs/templates/dataset_template.xlsx`
+- 관련 문서: `docs/guides/USER_GUIDE.md`
+
+---
+
+## 지원 메트릭(대표)
+
+- Ragas 계열: `faithfulness`, `answer_relevancy`, `context_precision`, `context_recall`, `factual_correctness`, `semantic_similarity`
+- 커스텀 예시(도메인): `insurance_term_accuracy`
+
+정확한 옵션/운영 레시피는 `docs/guides/USER_GUIDE.md`를 기준으로 최신화합니다.
+
+---
+
+## RAGAS 0.4.2 데이터 전처리/후처리 (중요)
+
+아래 항목은 **RAGAS 0.4.2 기준**으로 EvalVault가 데이터와 점수를 안정화하기 위해 수행하는 처리들입니다. 모두 재현성과 품질 저하 방지를 위해 의도적으로 설계되었습니다.
+
+### 1) 데이터 전처리 (입력 안정화)
+- **빈 질문/답변/컨텍스트 제거**: 평가 불가능한 케이스를 사전에 제거합니다. (`src/evalvault/domain/services/dataset_preprocessor.py`)
+- **컨텍스트 정규화**: 공백 정리, 중복 제거, 길이 제한을 통해 컨텍스트 품질을 표준화합니다. (`src/evalvault/domain/services/dataset_preprocessor.py`)
+- **레퍼런스 보완**: 레퍼런스가 필요한 메트릭에서 부족할 경우 질문/답변/컨텍스트 기반으로 보완합니다. (`src/evalvault/domain/services/dataset_preprocessor.py`)
+
+**이유**: 입력 품질 편차로 인해 RAGAS 점수 분산이 커지는 것을 방지하고, 메트릭 실행 실패/왜곡을 줄입니다.
+
+### 2) 한국어/비영어권 대응 (프롬프트 언어 정렬)
+- **한국어 데이터셋 자동 감지** 후 `answer_relevancy`, `factual_correctness`에 한국어 프롬프트를 기본 적용합니다. (`src/evalvault/domain/services/evaluator.py`)
+- **사용자 프롬프트 오버라이드 지원**: 필요 시 YAML로 메트릭별 프롬프트를 덮어쓸 수 있습니다. (`src/evalvault/domain/services/ragas_prompt_overrides.py`)
+- **외부 근거(비영어권 이슈)**:
+  - https://github.com/explodinggradients/ragas/issues/1829
+  - https://github.com/explodinggradients/ragas/issues/402
+- **공식 문서(언어 이슈 직접 언급)**:
+  - https://docs.ragas.io/en/stable/howtos/customizations/metrics/_metrics_language_adaptation/
+
+**이유**: 질문 생성/판정 프롬프트가 영어에 고정될 경우, 비영어 입력에서 언어 불일치로 점수 왜곡이 발생할 수 있으므로 이를 최소화합니다.
+
+### 3) 점수 후처리 (안정성 확보)
+- **비숫자/NaN 점수는 0.0 처리**: 메트릭 실패가 전체 파이프라인을 중단시키지 않도록 방어합니다. (`src/evalvault/domain/services/evaluator.py`)
+- **Faithfulness 폴백**: RAGAS가 실패하거나 한국어 텍스트에서 불안정할 경우, 한국어 전용 claim-level 분석으로 점수를 재구성합니다. (`src/evalvault/domain/services/evaluator.py`)
+
+**이유**: LLM/임베딩 실패나 NaN으로 인해 결과가 끊기는 문제를 방지하고, 한국어에서 최소한의 신뢰도를 확보하기 위해서입니다.
+
+### 4) 요약/시각화 후처리 (비교 가능성 강화)
+- **임계값 기준 정규화**: threshold를 0점 기준으로 정규화하여 성능 개선/악화를 직관적으로 표시합니다. (`src/evalvault/domain/services/visual_space_service.py`)
+- **가중 합산**: `faithfulness`, `factual_correctness`, `answer_relevancy` 등을 가중 결합하여 축/지표로 요약합니다. (`src/evalvault/domain/services/visual_space_service.py`)
+
+**이유**: 단일 지표만으로는 해석이 어려운 경우가 많아, 정책적 기준(임계값)과 함께 비교 가능한 요약 점수로 제공하기 위함입니다.
+
+---
+
+## 모델/프로필 설정(요약)
+
+- 프로필 정의: `config/models.yaml`
+- 공통 환경 변수(예):
+  - `EVALVAULT_PROFILE`
+  - `EVALVAULT_DB_PATH`
+  - `OPENAI_API_KEY` 또는 `OLLAMA_BASE_URL` 등
+- 관련 문서: `docs/guides/USER_GUIDE.md`, `docs/guides/DEV_GUIDE.md`, `config/models.yaml`
+
+---
+
+## Open RAG Trace (외부 RAG 시스템까지 통합)
+
+EvalVault는 OpenTelemetry + OpenInference 기반의 **Open RAG Trace** 스키마를 제공해, 외부/내부 RAG 시스템을 동일한 방식으로 계측/수집/분석할 수 있게 합니다.
+
+- 스펙: `docs/architecture/open-rag-trace-spec.md`
+- Collector: `docs/architecture/open-rag-trace-collector.md`
+- 샘플/내부 래퍼: `docs/guides/open-rag-trace-samples.md`, `docs/guides/open-rag-trace-internal-adapter.md`
+- 관련 문서: `docs/INDEX.md`, `docs/architecture/open-rag-trace-collector.md`
+
+---
+
+## 개발/기여
+
+```bash
+uv run ruff check src/ tests/
+uv run ruff format src/ tests/
+uv run pytest tests -v
+```
+
+- 기여 가이드: `CONTRIBUTING.md`
+- 개발 루틴: `docs/guides/DEV_GUIDE.md`
+- 관련 문서: `docs/STATUS.md`, `docs/ROADMAP.md`
+
+---
+
+## 문서
+
+- `docs/INDEX.md`: 문서 허브
+- `docs/STATUS.md`, `docs/ROADMAP.md`: 현재 상태/방향
+- `docs/guides/USER_GUIDE.md`: 사용/운영 종합
+- `docs/new_whitepaper/INDEX.md`: 설계/운영/품질 기준(전문가 관점)
+
+---
+
+## License
+
+EvalVault is licensed under the [Apache 2.0](LICENSE.md) license.

{evalvault-1.57.1.dist-info → evalvault-1.59.0.dist-info}/RECORD

@@ -12,13 +12,13 @@ evalvault/adapters/inbound/api/routers/benchmark.py,sha256=yevntbZcNtMvbVODsITUB
 evalvault/adapters/inbound/api/routers/config.py,sha256=CN-FH2cn0Ive-BD3WacWY6PFfuMtZEHP5_out3fvST4,3957
 evalvault/adapters/inbound/api/routers/domain.py,sha256=RsR7GIFMjccDN7vpG1uDyk9n1DnCTH18JDGAX7o4Qqc,3648
 evalvault/adapters/inbound/api/routers/knowledge.py,sha256=7mgyoUM1PepFb4X8_Ntn0vd7ZZYcNbM3_9nyD10g4Aw,5307
-evalvault/adapters/inbound/api/routers/pipeline.py,sha256=GKQaeR6FZVs_ManVMCn3vVBBONzA4rKHmvhLDxr5s5c,14702
+evalvault/adapters/inbound/api/routers/pipeline.py,sha256=tWuXwM-AH_NVDzemtsxbi5Dyn5kYyc1vPFS1sg2TPuw,16655
 evalvault/adapters/inbound/api/routers/runs.py,sha256=W3QaSMN3ByqNLynh_uWkMv0_-NvsVKedbuKsEAAoZr0,33160
 evalvault/adapters/inbound/cli/__init__.py,sha256=a42flC5NK-VfbdbBrE49IrUL5zAyKdXZYJVM6E3NTE0,675
 evalvault/adapters/inbound/cli/app.py,sha256=Gf_VWXK2aUzVL63F5ulqPd88MgO1n823uISGhGHsdEI,1813
 evalvault/adapters/inbound/cli/commands/__init__.py,sha256=ciIHbHgP0gtasVi4l5cHjVojERrb-uipga_E0EwCrqM,3431
 evalvault/adapters/inbound/cli/commands/agent.py,sha256=YlOYMEzzS1aSKDKD_a7UK3St18X6GXGkdTatrzyd8Zc,7555
-evalvault/adapters/inbound/cli/commands/analyze.py,sha256=DDel6Yz99Yau-Ypnufrx6ldErTdNDE3GTqEZp47664M,37240
+evalvault/adapters/inbound/cli/commands/analyze.py,sha256=aMi1BEDOX3yhN-ppBftDssPQLB5TdzIfpx9U7CZEgWo,48932
 evalvault/adapters/inbound/cli/commands/api.py,sha256=YdbJ_-QEajnFcjTa7P2heLMjFKpeQ4nWP_p-HvfYkEo,1943
 evalvault/adapters/inbound/cli/commands/benchmark.py,sha256=RZ4nRTF7d6hDZug-Pw8dGcFEyWdOKclwqkvS-gN4VWo,41097
 evalvault/adapters/inbound/cli/commands/config.py,sha256=r3DH2a0-PgJIzpyB7teiykDulhUwUJUkiFWLrbjhF6k,7148
@@ -33,22 +33,22 @@ evalvault/adapters/inbound/cli/commands/kg.py,sha256=ycV9Xj6SUUJLTyTfLZcjXDVLcZq
 evalvault/adapters/inbound/cli/commands/langfuse.py,sha256=aExhZ5WYT0FzJI4v1sF-a1jqy9b1BF46_HBtfiQjVGI,4085
 evalvault/adapters/inbound/cli/commands/method.py,sha256=K1UacoKwV9w8sLeQK8qHyTuZqFZrlcj6yS_y2izfRlo,18853
 evalvault/adapters/inbound/cli/commands/phoenix.py,sha256=LQi3KTLq1ybjjBuz92oQ6lYyBS3mHrCHk0qe-7bqB4U,15611
-evalvault/adapters/inbound/cli/commands/pipeline.py,sha256=w-qcI88wxrWup63HKhj16jvqTev_nRPG7eMQQWQ8h08,7788
+evalvault/adapters/inbound/cli/commands/pipeline.py,sha256=Hg3A2LGTLw_rjd6ZgT5lOVsTASXIyq2DimUna24FRv0,7936
 evalvault/adapters/inbound/cli/commands/prompts.py,sha256=6UwQtKJf3JYhcNI4tQqjjsL-sp_cmu2VV7gETkCcmkk,5490
-evalvault/adapters/inbound/cli/commands/run.py,sha256=o5xY9jOWcNI-eZM1XwwiWk4QKYjh58tQ5bjqyT-eylc,92472
-evalvault/adapters/inbound/cli/commands/run_helpers.py,sha256=Wy4nJmAuVWHmhltKOMOKFNK4k8oZxbc9Gq6Ejb2FJC4,39696
+evalvault/adapters/inbound/cli/commands/run.py,sha256=6d_AnONUiroNMF1xZt8O1sbtqb5HcE53ZMAU-UOp1cA,115469
+evalvault/adapters/inbound/cli/commands/run_helpers.py,sha256=50nYzf4DUniJd7fQgT2cyh_FWVTWZzW0UMXCg-EHBuY,39764
 evalvault/adapters/inbound/cli/commands/stage.py,sha256=oRC9c5CysLX90Iy5Ba1pc_00DaOBS78lcBvzkbdrGRM,17123
 evalvault/adapters/inbound/cli/utils/__init__.py,sha256=QPNKneZS-Z-tTnYYxtgJXgcJWY6puUlRQcKrn7Mlv1M,685
-evalvault/adapters/inbound/cli/utils/analysis_io.py,sha256=kVjEBaYqQ6GBTNJ9W-xpExyy4y1-jpz_m7S5y6i5eQs,13395
+evalvault/adapters/inbound/cli/utils/analysis_io.py,sha256=RHkKEq4e-PtbtRDlXAJWU80RYHNPw-O5V9_GujdaGfc,13393
 evalvault/adapters/inbound/cli/utils/console.py,sha256=uikQ7igql04HH6zSpCk_uA9HpQmD0IcJxEAo3K9_FsE,1787
 evalvault/adapters/inbound/cli/utils/errors.py,sha256=RXLJZHadvENXDQ4ZzDyaL_0Z5IEfb_x0MxQba8dD20g,4908
 evalvault/adapters/inbound/cli/utils/formatters.py,sha256=-n1slpbvJxRv-NNbbXCFZ1da52GySA3bC3E6wdaAPE0,946
 evalvault/adapters/inbound/cli/utils/options.py,sha256=0vBmbpil1DCdO7Pktz_G1D-yMopNr0EcyOZgEE8-T2E,1799
 evalvault/adapters/inbound/cli/utils/presets.py,sha256=6XNVBnkkWpYwK-_UYd7AdVRPdgRNcbLZX22fF7gNlZY,3255
-evalvault/adapters/inbound/cli/utils/progress.py,sha256=cr2vT4u8dfBf7iI08-GfeRGFpZBEFACasNhzyu_k-eQ,11112
+evalvault/adapters/inbound/cli/utils/progress.py,sha256=2kFKKZ4AWNvo9IcSLhu8qbslKfPHqKWLxYOImHVecqA,11136
 evalvault/adapters/inbound/cli/utils/validators.py,sha256=OnjNvi_iLtxjWBIrqtbGWAmx2d4zNm_-qi0Ce-3KHZk,1436
 evalvault/adapters/outbound/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalvault/adapters/outbound/analysis/__init__.py,sha256=hMycj6XMvXk0BKU8--42FP1dP7Fx8rowTYFZLpiwt-8,5796
+evalvault/adapters/outbound/analysis/__init__.py,sha256=TLuS-eKfXg97_Db5td1nTZkD3BErRLZLic1v2EAM2sA,6185
 evalvault/adapters/outbound/analysis/analysis_report_module.py,sha256=xah3wgJErHD_Hpb1YAwWRsxr8xaC8SW--CpNA7IgfxI,3957
 evalvault/adapters/outbound/analysis/base_module.py,sha256=eUN77SSD2KR4WKU7gLY8TlVewETx_YIZvPT4LUnBv4o,2523
 evalvault/adapters/outbound/analysis/bm25_searcher_module.py,sha256=I8BsXrHaOVxgRTEVUVumSvEpSZ_sT6zsbTd2rlyW6x8,3701
@@ -59,25 +59,27 @@ evalvault/adapters/outbound/analysis/comparison_report_module.py,sha256=0tTMZB5q
 evalvault/adapters/outbound/analysis/data_loader_module.py,sha256=6X0-ZcFtEfonQnbJ0POqmHXstJ1Wq1NvpijtbKSeEm0,3749
 evalvault/adapters/outbound/analysis/detailed_report_module.py,sha256=59CjuNQthlroJyGEhQap3PgahWfzXciKx_DD10gHXjM,3897
 evalvault/adapters/outbound/analysis/diagnostic_playbook_module.py,sha256=qMgcBlwr2_a-pgth7zV1CWdGeUrzTeZjB4K9uyDnKcc,3993
-evalvault/adapters/outbound/analysis/embedding_analyzer_module.py,sha256=u52OrJhxTuSKqi8EaHgGy3EweOiC8J1e2L2ocOGjNps,7269
+evalvault/adapters/outbound/analysis/embedding_analyzer_module.py,sha256=-lxNC-h4HUr1co9mNRHGO-gM3MgArT2LNBvjQoR_UkE,7286
 evalvault/adapters/outbound/analysis/embedding_distribution_module.py,sha256=AdCOFnmCk4luKw8NT6VBlrxaetYcNmhLTgKhjYxmDDg,2581
-evalvault/adapters/outbound/analysis/embedding_searcher_module.py,sha256=7_fwpBD571siKUWaFoKBPfkJkLWgy-C5NMfv2EkPZpM,4858
+evalvault/adapters/outbound/analysis/embedding_searcher_module.py,sha256=j6w_jIGG9rbmVuAUtx2uEAX6wPXPjqmQyW0sy7R97dQ,4875
 evalvault/adapters/outbound/analysis/hybrid_rrf_module.py,sha256=kaHSc7z3Jg_KrRLBqPMTV_9XXsL6v1dmbz-3dDO6IMw,3255
 evalvault/adapters/outbound/analysis/hybrid_weighted_module.py,sha256=AO-7thmnFGerUDWd8l9ydxeAkHkACo7Raf9O0RfW_nE,3671
-evalvault/adapters/outbound/analysis/llm_report_module.py,sha256=MMMxlNk34MBlT8j44Lwj7g0op6eyMY5u8ISA9Kj4_OQ,38782
+evalvault/adapters/outbound/analysis/hypothesis_generator_module.py,sha256=tx9fWgS0rBoK5eJPmwK5POoV78yN03hkFmWhCx71Ln0,13337
+evalvault/adapters/outbound/analysis/llm_report_module.py,sha256=KjIM2MET6gl9jUpxRo0rDVIzqSXFw-I4y0QoG_TULFA,38773
 evalvault/adapters/outbound/analysis/low_performer_extractor_module.py,sha256=Pt0Tmtc5Etqp_3SBDCPAzqWI2EF9woSg0mmBucEHlQw,1291
 evalvault/adapters/outbound/analysis/model_analyzer_module.py,sha256=28rHdXBXYIFpLHixbbZcv6-j2QVgl3yaGN0vU1Q0gFc,2682
 evalvault/adapters/outbound/analysis/morpheme_analyzer_module.py,sha256=Hrh4mluMsOhQHPrliD2w0FVKokJpfikXOFKT6sNwk74,4158
 evalvault/adapters/outbound/analysis/morpheme_quality_checker_module.py,sha256=_uRKDXdwGbfYduf_3XT77vF8X3-_zW3stHYc3HKYQTE,2216
+evalvault/adapters/outbound/analysis/network_analyzer_module.py,sha256=ITUVnt_CI5pHy5SAESBSi004yMtiAhGFsbhC61VTezk,8475
 evalvault/adapters/outbound/analysis/nlp_adapter.py,sha256=U7verYM4XTSPLTlb2z0b7yYzTP4kkNFl5LQ91XhXu_A,27432
 evalvault/adapters/outbound/analysis/nlp_analyzer_module.py,sha256=KtoMJNa4NE-91iTEpEWIid-mciaezwmhU2xlKbYl4fg,8221
 evalvault/adapters/outbound/analysis/pattern_detector_module.py,sha256=SyCDO_VS-r-tjGh8WrW-t1GCSC9ouxirdVk4NizFPXo,1882
-evalvault/adapters/outbound/analysis/pipeline_factory.py,sha256=T-seKrYmyNifZgoPUaiJE0ioTFexVp0qQfb1jkCOorA,3474
-evalvault/adapters/outbound/analysis/pipeline_helpers.py,sha256=aIyDV04YPSsxNzCYHG7UW8y7mQRBszrJebTUZ2wnny4,5756
-evalvault/adapters/outbound/analysis/priority_summary_module.py,sha256=OPX1DsUto4MjTFSzwdSan-xRPlT0FNCC1djWVu2oZT0,10803
+evalvault/adapters/outbound/analysis/pipeline_factory.py,sha256=XvcCbKCN_otv1pGUzk0oE76RV19yFga8r6RngBvgEFo,3691
+evalvault/adapters/outbound/analysis/pipeline_helpers.py,sha256=8E8IrYI5JvRrpnjxe0DS7srbPzB0XAxxXhLLYgfwsgU,5756
+evalvault/adapters/outbound/analysis/priority_summary_module.py,sha256=o8Y0rfHjYYE9WNTwKtpJulwfvLA3MNMhYjdSg15Vacc,10802
 evalvault/adapters/outbound/analysis/ragas_evaluator_module.py,sha256=KQd8zdyMGKklZane077RRNPDOf6kqVDbj_R9Qbq-quA,7275
 evalvault/adapters/outbound/analysis/retrieval_analyzer_module.py,sha256=D24GTaKabHacSBI-UqCd_jy61hnne8-QG1p4rqW1Bzk,5748
-evalvault/adapters/outbound/analysis/retrieval_benchmark_module.py,sha256=9rxrwAp6kakJJuMreQm9OorwE6eXmirMtOK7SO4B8mQ,9296
+evalvault/adapters/outbound/analysis/retrieval_benchmark_module.py,sha256=_duIBlYhAsFygEpC7DuwoAqfTbVG2xgp70JjW1LJAGE,9312
 evalvault/adapters/outbound/analysis/retrieval_quality_checker_module.py,sha256=K1IJn4bvvz-BfqQmhd5Ik9oATjq_-G7V1AZSW8zKtSE,3121
 evalvault/adapters/outbound/analysis/root_cause_analyzer_module.py,sha256=UagHWb2d1vD7aCH0vLl3tSJx86gkkxNarrF-rwtEBhU,2811
 evalvault/adapters/outbound/analysis/run_analyzer_module.py,sha256=oTle2vHiNFFajCe8vQaB1SbKthbUxtd7oDGoPdW9JJY,2172
@@ -91,10 +93,11 @@ evalvault/adapters/outbound/analysis/statistical_analyzer_module.py,sha256=FzM6T
 evalvault/adapters/outbound/analysis/statistical_comparator_module.py,sha256=dxGVa3zvuBRab6KhRIVfg2IDB0PEGljBmohlSYI-BtE,1843
 evalvault/adapters/outbound/analysis/summary_report_module.py,sha256=HCoM8DMEGwwFQUjJLDWXnC6vE9Xo0YvhLRh9v3GMHRg,4279
 evalvault/adapters/outbound/analysis/time_series_analyzer_module.py,sha256=6PhFH_aLDS85VePar3M9-ClaxonjcfmXCnCBP4vhvT8,1888
+evalvault/adapters/outbound/analysis/timeseries_advanced_module.py,sha256=V0t4rjLeb_EyfGUskXKbeKV5hd3tdK1OIbytELsSoR4,12650
 evalvault/adapters/outbound/analysis/trend_detector_module.py,sha256=b8rSKXxOH9NKaLbkG-APDeRpIxrYA-U5damse9R0smM,1977
 evalvault/adapters/outbound/analysis/verification_report_module.py,sha256=vFEPfsIKRGJmzZ2sRY9r-ELFZWY0UB0aLqhrQc0NRxk,1922
 evalvault/adapters/outbound/benchmark/__init__.py,sha256=fSL1fXtFaYmjwAHndThrwNA5bhvcKp4PaVltBI42WSg,171
-evalvault/adapters/outbound/benchmark/lm_eval_adapter.py,sha256=RAqVhPWCAhmWGPR7xNzYyx-hSeIquUqCesdhgaBy99M,12532
+evalvault/adapters/outbound/benchmark/lm_eval_adapter.py,sha256=xFj_Cgny3JN_COA1o4PjNH-hZ_rAgdLtovvmrqualqs,12531
 evalvault/adapters/outbound/cache/__init__.py,sha256=LcsKzxnx1AnAwS07iSCdws11CfEYuxkUjRkogN0SviI,317
 evalvault/adapters/outbound/cache/hybrid_cache.py,sha256=AVhctQVOIbQWwvn_K0kxSq3lkhucuM7tezmSkPDbCrA,12711
 evalvault/adapters/outbound/cache/memory_cache.py,sha256=jvjIgXp7YRj08_AzBFaJ58jjXNzUlYbG_zX6fQJP4C0,3533
@@ -110,28 +113,33 @@ evalvault/adapters/outbound/dataset/templates.py,sha256=5gfae7kqs66SRAP-OyWX6N2c
 evalvault/adapters/outbound/dataset/thresholds.py,sha256=5Vodqar6QrCL7R_Pq0gTxv1pJh_OiH_3pNimvJaUQA4,2199
 evalvault/adapters/outbound/debug/__init__.py,sha256=p_5zw3ys7E-ZjmY_74LYiz5f4Gd6tT-o6T2SNDxFuQg,168
 evalvault/adapters/outbound/debug/report_renderer.py,sha256=84lR7kA369JYregP4ARkfIWCcYpbluJ5mISeV0iIGnk,5427
+evalvault/adapters/outbound/documents/__init__.py,sha256=s_Fj5bi4NvZ5bPd5RoxFA4z-RnejHbP9_8Ceo4w3LK8,59
+evalvault/adapters/outbound/documents/pdf_extractor.py,sha256=ugDzoeZbTCqFPOlbl3a5nznHiBLaK6a23u20N3ZfFBc,1189
+evalvault/adapters/outbound/documents/versioned_loader.py,sha256=oNlwE40lfOFhX6uNCbxTLH_S1-zMy6kNq95SyRv2I1I,7786
+evalvault/adapters/outbound/documents/ocr/__init__.py,sha256=i6JIdO9UyHNd6wlb3KnBxLfI10WLjlFqssKBTbYUf6E,39
+evalvault/adapters/outbound/documents/ocr/paddleocr_backend.py,sha256=AORA9JUV5ux5QkrwXBg5xjzqJqgFUjTyyFrfqkUYdpw,3378
 evalvault/adapters/outbound/domain_memory/__init__.py,sha256=ksMX1IkNiDqQHLtJe9TOXiLC1iouGt6_QSdPLiALHHs,229
 evalvault/adapters/outbound/domain_memory/domain_memory_schema.sql,sha256=APlNhJNFZdcm7Sb2tvr7V8JMiLinmXkx1gd6pgTf9ZI,11268
 evalvault/adapters/outbound/domain_memory/sqlite_adapter.py,sha256=RWobnFgvxiItxFAr6niY89sT19O-cnExTbP0I7UAY78,85186
 evalvault/adapters/outbound/improvement/__init__.py,sha256=tXA6vaZOLvqwJpyjGMiC8WrvszMmvUPzJnHjvJhQxSI,1143
-evalvault/adapters/outbound/improvement/insight_generator.py,sha256=_rxVq7aOyhsMqKVljaSDNVcev4GZ8GWWS7JQ3u5l6K4,17144
-evalvault/adapters/outbound/improvement/pattern_detector.py,sha256=sEUelFjrAPdbTTPDqmlFLH2zSdTBwe0Fq-YyHv1eeI0,24215
-evalvault/adapters/outbound/improvement/playbook_loader.py,sha256=48jC7vn0c9rcypNV9i6wOyLRn3Xmi3WVY8xlTbEN1RI,7063
+evalvault/adapters/outbound/improvement/insight_generator.py,sha256=U16l0euCZy0_08Zb_i0eijXSjS5t-iq0iMUfttwPqgI,17636
+evalvault/adapters/outbound/improvement/pattern_detector.py,sha256=4Pc5yrsi2warhKdpWxL0Ba9Ms2sCvFeRVWU8jTeALZ8,24608
+evalvault/adapters/outbound/improvement/playbook_loader.py,sha256=zXDpiTpYWtQvVrDeo149YHKIyhF6nUP34j0FVnlBCJo,7471
 evalvault/adapters/outbound/improvement/stage_metric_playbook_loader.py,sha256=JdmXQsackWqeWTnULE4gfTK8vAikGR27h-TVc03CGXk,1706
 evalvault/adapters/outbound/kg/__init__.py,sha256=fUCKOV080ZjiEob9s4TmXWf-IDa6GbIFQMLfH6gFCKg,567
-evalvault/adapters/outbound/kg/graph_rag_retriever.py,sha256=d2JTQgcNHI7kvAL757_NysqcaSiuvXPHNuxdhHk1_Ug,18556
+evalvault/adapters/outbound/kg/graph_rag_retriever.py,sha256=_6qd8p_2TpHnppv8LUQQPxUdTPoE0QTQ-rCVnY1ap6c,18658
 evalvault/adapters/outbound/kg/networkx_adapter.py,sha256=wSZjMiMzpS9ZZLTRYjHm7X6TN9ITbuTWr10KyR6hFxg,21043
 evalvault/adapters/outbound/kg/parallel_kg_builder.py,sha256=sbR-bVpjTFhV47Ss8LYA3Ytk-THqo1HJz2YLfAelRyg,8886
 evalvault/adapters/outbound/kg/query_strategies.py,sha256=BDDft2Cc-xDvJWyIuyUTv0bPvaIiXJLd76YdjzMAZlk,19445
-evalvault/adapters/outbound/llm/__init__.py,sha256=iXYeEz6MbKL8celAW3PkgdynFC4kCvHEFdn0HSR32k0,4113
+evalvault/adapters/outbound/llm/__init__.py,sha256=GDllWZNBVqmQSFOXsXFlE82qxgaZWGL4TChu61bEG7U,4523
 evalvault/adapters/outbound/llm/anthropic_adapter.py,sha256=Qjpwqt6eDDvrSAGynvO0NZQIrhfEFJqLJfqfYPjcwaY,7491
 evalvault/adapters/outbound/llm/azure_adapter.py,sha256=FR9Gimy-jonzQjtILGHKXAY_ycbjGKbKLFiD-OZ8EVs,3033
 evalvault/adapters/outbound/llm/base.py,sha256=c4cJJTKwJiBlGNCV7qomq5mQCrbc48Yi7c3vjlat7Q0,7674
-evalvault/adapters/outbound/llm/instructor_factory.py,sha256=aXJyJCV8lns5A7sAyt6HZvbZedv2DcHTBXK4pr6TV-g,1364
+evalvault/adapters/outbound/llm/instructor_factory.py,sha256=6iJIjZbCJwDYEpV673R3lQOupzeWlvjCmhjYqthrueY,4497
 evalvault/adapters/outbound/llm/llm_relation_augmenter.py,sha256=jdeDumCi34KqAfRwLh9VTia9wiP5bvVwvHxJylLDOcg,3854
-evalvault/adapters/outbound/llm/ollama_adapter.py,sha256=vuGaDiY--sm5Zg_plf2kgvbjErs_S9jJLw74H23UgE0,10432
+evalvault/adapters/outbound/llm/ollama_adapter.py,sha256=L7MRlPUyYxTSVHhCz7LHducTqBifTzmovNBi26SWtr8,10615
 evalvault/adapters/outbound/llm/openai_adapter.py,sha256=Zv4gi0AxoQrXzf2hBrQjLaQVM4WttHuO2raTCekR_Kk,5163
-evalvault/adapters/outbound/llm/token_aware_chat.py,sha256=BMUvgC55cooUKew8afw7CNU7bXr6-ZdLc0_nT-eFQzY,11948
+evalvault/adapters/outbound/llm/token_aware_chat.py,sha256=HLmwTZkiwmUuopjFwDGpamIRC44PWnwkRA4O-pUBt_s,11937
 evalvault/adapters/outbound/llm/vllm_adapter.py,sha256=zwH_KKydABn0J-hCs6OB-3809X_qBx8FPQ2EhO1gkcY,3897
 evalvault/adapters/outbound/methods/__init__.py,sha256=3vyE9w3Ex2oMaO4ZE7Fy6xlHhJ6YQXHQNCvBiW9X2lM,345
 evalvault/adapters/outbound/methods/baseline_oracle.py,sha256=oUsF5sIiPY5vuDtrz0Ki05SnPlnVzn7APERP5v1KpPM,1308
@@ -148,21 +156,22 @@ evalvault/adapters/outbound/nlp/korean/korean_evaluation.py,sha256=Mxwu3zhtdm8Te
 evalvault/adapters/outbound/nlp/korean/korean_stopwords.py,sha256=UemEFCJudg2EpsHg8uU2eR-iCh34kw4ZSVCRvnEC6a4,4293
 evalvault/adapters/outbound/nlp/korean/toolkit.py,sha256=EYGpd89ilpn4Wg5t8pALYt4Qi0aDHYOfXGuYbQx7do0,4246
 evalvault/adapters/outbound/phoenix/sync_service.py,sha256=i6gHpNiZXKQ5yzV9B2TPb-P1N45k_Ck5ruzh3oqp4d8,9122
-evalvault/adapters/outbound/report/__init__.py,sha256=jY17ysqwkRbKCquNv94XUBI4QZQlrAzKyhb0xu87jdA,365
-evalvault/adapters/outbound/report/llm_report_generator.py,sha256=cjt-ydcufMLiAyYoNJ7NXuwqS9dQBQaA1Mlw-ki7hYY,24087
-evalvault/adapters/outbound/report/markdown_adapter.py,sha256=oRI4IJfVR9GrjcOq7IwtD_ngP2sy3kt2B8XO-wYT2jI,16610
+evalvault/adapters/outbound/report/__init__.py,sha256=8OUduTHnWkBLHYrc7mBg45DnAwz0RgvSJmz1HqxVjLY,477
+evalvault/adapters/outbound/report/dashboard_generator.py,sha256=Dcu18NTK4lS8XNKnnnquagpZkd-4TSf5Mb2isFNW5Pk,7800
+evalvault/adapters/outbound/report/llm_report_generator.py,sha256=sp2YRCmPOhn08vb8Bq_ayo-ZjgyBBxRhzRFvzlaDhsA,24063
+evalvault/adapters/outbound/report/markdown_adapter.py,sha256=5PS72h_qe4ZtYs-umhX5TqQL2k5SuDaCUc6rRw9AKRw,16761
 evalvault/adapters/outbound/storage/__init__.py,sha256=n5R6thAPTx1leSwv6od6nBWcLWFa-UYD6cOLzN89T8I,614
 evalvault/adapters/outbound/storage/base_sql.py,sha256=pPKlT2P7fCTMxCAIi0tzYr0d5rkroPTB4dHQNDDRxsI,18167
 evalvault/adapters/outbound/storage/benchmark_storage_adapter.py,sha256=Qgf9xSSIkYQRpG4uLzcUdoYO9LTQDQ4tFRkkMYer-WA,9803
-evalvault/adapters/outbound/storage/postgres_adapter.py,sha256=qRIb3h8FbrQVsSSkVaROQWcvdcS6YtH0bufL7jKdZwM,38134
+evalvault/adapters/outbound/storage/postgres_adapter.py,sha256=ro3DrE2e4l2jimoPidcmY0xBufhqi5M6_4VF-Ta0e-I,38133
 evalvault/adapters/outbound/storage/postgres_schema.sql,sha256=BLDQ7ynzS9Aw6NxN3efALpG3eN1ZfsmBcEeWugHwF98,7075
 evalvault/adapters/outbound/storage/schema.sql,sha256=R9Y3j76qR3_UbbeX1olhHs1hbsLjS3YfiSFyUgqTM28,10057
 evalvault/adapters/outbound/storage/sqlite_adapter.py,sha256=cldMzXW9_0jdAC0YkwhFznleKX6yF4RkFNpmYc8_lZQ,47446
 evalvault/adapters/outbound/tracer/__init__.py,sha256=xrvQQuAvF_UI02mKLMV7GTrG3zn836n5zwCRrrmhq_U,1054
-evalvault/adapters/outbound/tracer/open_rag_log_handler.py,sha256=8aND6mDNUq8aqsvS_g0zPiXVJrafXfJLV6HHWgxyNDY,2824
-evalvault/adapters/outbound/tracer/open_rag_trace_adapter.py,sha256=1YOwktXyrdHZmbDK6ESsvbfjdoyeueMpCnGX7U0L_NA,4781
+evalvault/adapters/outbound/tracer/open_rag_log_handler.py,sha256=aq96FIWD-bBaSkq-bygWhQArC9LWghSwi-S03Mga0mI,2827
+evalvault/adapters/outbound/tracer/open_rag_trace_adapter.py,sha256=P-4PN1UweITXu5uN3LJVCEL3wRwiExzhgs3y2GN78xM,4784
 evalvault/adapters/outbound/tracer/open_rag_trace_decorators.py,sha256=LFnk-3FSLwRz0pxp8gMZl3Kd1BIMv_4Gr21nbRQ53m4,2034
-evalvault/adapters/outbound/tracer/open_rag_trace_helpers.py,sha256=euHcXGdWEPKnyqmoCu2cwO3lMCLkHP5ApMxiIHXKwTo,3518
+evalvault/adapters/outbound/tracer/open_rag_trace_helpers.py,sha256=D48Mbj-ioDKztjhV9513Q5DiUNiVdO60B_2sWMFEmnI,3520
 evalvault/adapters/outbound/tracer/phoenix_tracer_adapter.py,sha256=inmTAolAVsm0IrszE9VTJoI7HSvGGAnGNZVu_vZRAGg,741
 evalvault/adapters/outbound/tracker/__init__.py,sha256=Suu5BznOK5uTuD5_jS8JMZd8RPfQNlddLxHCBvMTm_4,358
 evalvault/adapters/outbound/tracker/langfuse_adapter.py,sha256=Gejd3fOBwShfjbtjVcZK9sCJKRz6oB3OaN6KukOYN38,17782
@@ -175,12 +184,12 @@ evalvault/config/instrumentation.py,sha256=L8on9HjB6Ji8cSOJ6Pepsopfg9okDNMWF7LKZ
 evalvault/config/langfuse_support.py,sha256=DEzVMfMGGf1V45W_2oUG-NCDfsYI4UUdnYJIgBSrN2o,582
 evalvault/config/model_config.py,sha256=KlzDbGyDLeOGE7ElekFFk5YjjT5u8i6KO2B4EyZkLnI,3542
 evalvault/config/phoenix_support.py,sha256=e6RPWd6Qb7KU6Q8pLaYTpJGWULtvEEU6B0xHWyVyOH0,13604
-evalvault/config/settings.py,sha256=kY58QYFAFfAIx_MGlK8Rkktkpwe4sjhhHQHBOXIMDns,12594
+evalvault/config/settings.py,sha256=fh_Kl95LpAtLPgRrL-W-nBpp8HwWuGaoDb4NR54hcbc,12863
 evalvault/config/playbooks/improvement_playbook.yaml,sha256=9F9WVVCydFfz6zUuGYzZ4PKdW1LLtcBKVF36T7xT764,26965
 evalvault/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalvault/domain/entities/__init__.py,sha256=C63BX4ytkh0FCEfNFIy0MDY2tcYxp9G430IdyBxqqAk,2794
 evalvault/domain/entities/analysis.py,sha256=gcMtumC66g-AIqb2LgfMpm5BMzwJhJkjg-zuybNoJCM,15208
-evalvault/domain/entities/analysis_pipeline.py,sha256=YHe_lNfekDhIE5oOnNnjD52KVhxXXpEUuBmy1qqaKI8,16581
+evalvault/domain/entities/analysis_pipeline.py,sha256=hD9rFHMa4rUq0InRkSKhh6HQ9ZeNYAHKADzs-kWRP04,16845
 evalvault/domain/entities/benchmark.py,sha256=CVbz_eW7Y9eM7wG7xA_xmldTIs72csdoTmu3E0NKoMU,18475
 evalvault/domain/entities/benchmark_run.py,sha256=2ZJOq5Ny_pfvRKM7E4RuIKxfxvoYK-5PAtPDhOwra9k,5653
 evalvault/domain/entities/dataset.py,sha256=WsC_5ivGluy-o2nXxLGmoC8DYl5UafVSo2hSowb3rvs,1886
@@ -204,7 +213,7 @@ evalvault/domain/metrics/retrieval_rank.py,sha256=F55ByadJBowyKHKBmKAZ0T0qN_R1_7
 evalvault/domain/metrics/terms_dictionary.json,sha256=-ZQmpx6yMOYoAOpcLj-xK2LkAeCbAw0EUb6-syIOKS0,3801
 evalvault/domain/metrics/text_match.py,sha256=P-YTZs9ekDqEmxLNBP8eXnMRymPdC8V4dJPtwG2ajVM,10219
 evalvault/domain/services/__init__.py,sha256=a7YjsOuOzbY2yQvtDJg7W8dPJme31rI04Qc49w5iHKE,686
-evalvault/domain/services/analysis_service.py,sha256=_W8HqgJSb2Rlv-fEtLsI3JpfQ0DSAM-zo_z6jgoPyIg,10769
+evalvault/domain/services/analysis_service.py,sha256=oUEtfJHB3bNJ_Ksygx-pjnLm4CTk7_rDvDbqfkAfFD4,10838
 evalvault/domain/services/async_batch_executor.py,sha256=qYFRl7CGmv56XppeRhInde7Fw0GESCoZh8V-Iv_1hQQ,11140
 evalvault/domain/services/batch_executor.py,sha256=cYA_Q1es46n_PYeyyfm0iM2b7GGVtDoOGoMxexrf6tI,1243
 evalvault/domain/services/benchmark_report_service.py,sha256=IF-zqtvpsJ0ONJWUEw4ghKiC7ka_PWxUBO10lPaDRmI,15083
@@ -215,10 +224,11 @@ evalvault/domain/services/cluster_map_builder.py,sha256=qPKMPj-eSqECJSCOKvv3ZETg
 evalvault/domain/services/dataset_preprocessor.py,sha256=v-shY5ky1oW0LJwBfdfP4VFh7TXBabpLD5rMOmtS-dQ,14235
 evalvault/domain/services/debug_report_service.py,sha256=SGdFh8tctAIq7RotFbg47eetxdYSS4Yju7-LOzpCMCM,4386
 evalvault/domain/services/document_chunker.py,sha256=u05N1xSBcJuJPUfP7WmpY_EyHuUMuGMsPSM9qs-ID8c,2494
+evalvault/domain/services/document_versioning.py,sha256=M1qZaMpQ2exVT1wkVAmvEPPuoYibJDt0F7pYfTK7mvE,3323
 evalvault/domain/services/domain_learning_hook.py,sha256=rhKBmdnrJyfGzFNsNxzyv8jZO26-WOosHSmBV_9qdJg,7176
 evalvault/domain/services/embedding_overlay.py,sha256=ZTNxUPXpHGbQ3Uri5DD3feTUFn7qrhuNshhyCQEvRuM,3559
 evalvault/domain/services/entity_extractor.py,sha256=f3Rf5saK8QsgetLNK1Hbxzt8PtttJZCicSR63S8DJ5k,14141
-evalvault/domain/services/evaluator.py,sha256=9Yi2Cb-fRzV6CUdvBTziP9vJs7i6btCuFt77EQfjFzE,64476
+evalvault/domain/services/evaluator.py,sha256=rxj0tVMwtDrekNFstT6baQDfemsH-c6XtHxX-9BLKmo,64476
 evalvault/domain/services/experiment_comparator.py,sha256=IBrxIwux-8GucwlLx6e5lUqB9miSPvBLGJK9ctoW7Y0,3299
 evalvault/domain/services/experiment_manager.py,sha256=2k-qGiAUyZuqqmcp4P-M3Z9HTXwwcqW5HQYKNkcIHuI,4863
 evalvault/domain/services/experiment_reporter.py,sha256=QYlVmCFSx8hKTPMezc7QjJE07b3MSQ82Q4QVucSHLVY,1420
@@ -231,13 +241,13 @@ evalvault/domain/services/memory_aware_evaluator.py,sha256=vTiYoxiMfZ_CMjSBjqwkB
 evalvault/domain/services/memory_based_analysis.py,sha256=oh2irCy3le7fWiTtL31SMEhPyu7fyBVz-giO2hlNifE,4499
 evalvault/domain/services/method_runner.py,sha256=pABqKZeaALpWZYDfzAbd-VOZt2djQggRNIPuuPQeUSw,3571
 evalvault/domain/services/pipeline_orchestrator.py,sha256=yriVlEVZYDtt0Vwt4Ae6xyW1H6Dj4Hxdn8XQSvQNSoQ,19436
-evalvault/domain/services/pipeline_template_registry.py,sha256=XfMFx7cOVqBr_S0XzCeDcfeBytc2J4uXxJ7oy6wy4FU,21694
+evalvault/domain/services/pipeline_template_registry.py,sha256=c1rvYsTQU5MdAsmbZ7LlnuF6TD3p4IXlzgq_i18J3f8,24039
 evalvault/domain/services/prompt_manifest.py,sha256=5s5Kd6-_Dn-xrjjlU99CVo6njsPhvE50H5m_85U-H6U,5612
 evalvault/domain/services/prompt_registry.py,sha256=81tq__u2fFxTEG8bWnyJ2Qdb9N89jcqIdSfOAKEbEvg,3029
 evalvault/domain/services/prompt_status.py,sha256=r1dFLGz4SfRxXaxsULQsr0-HpJkG9YfZ_yLIxF1MMBo,6731
 evalvault/domain/services/ragas_prompt_overrides.py,sha256=4BecYE2KrreUBbIM3ssP9WzHcK_wRc8jW7CE_k58QOU,1412
 evalvault/domain/services/retrieval_metrics.py,sha256=dtrQPLMrXSyWLcgF8EGcLNFwzwA59WDzEh41JRToHAY,2980
-evalvault/domain/services/retriever_context.py,sha256=fdtB-_faOXQv5RJWUaCuUv_lF5XRAybvTfMgRVFpKnY,4684
+evalvault/domain/services/retriever_context.py,sha256=ySQ-GuadiggS0LVAib4AxA_0JpasYz4S9hbjau0eyIA,6482
 evalvault/domain/services/stage_event_builder.py,sha256=ScTgyeRiH7z_rnNI_2p-i9szVRIRwUxGSJvpEj3zto4,9645
 evalvault/domain/services/stage_metric_guide_service.py,sha256=_JdRsBRWirO24qYFlh6hG-dkoWlX6_XWEYKf_uUlKIQ,8807
 evalvault/domain/services/stage_metric_service.py,sha256=KukIWWhWVOtclrET6uyWJ17jG76LfkKiqrUrDIDJ3gw,15327
@@ -246,7 +256,7 @@ evalvault/domain/services/synthetic_qa_generator.py,sha256=v0-M9VXM5oZ12AkfDyhOJ
 evalvault/domain/services/testset_generator.py,sha256=6IpiZ0pqhKEymo-AlUdfJjDkF2P1n8Md_QKV4nOheyg,4470
 evalvault/domain/services/threshold_profiles.py,sha256=YuOrD5CkXugAdSQYbMsFzS5VS1R201JOJtpKTs4dpXU,1296
 evalvault/domain/services/unified_report_service.py,sha256=lG3VpMLC1MTYUlcGl-MUEE4PUopkyrhcgj4_ye9c_vM,11829
-evalvault/domain/services/visual_space_service.py,sha256=BBcPKT79WjpPb3odzHGsvIbWodMngqxlnvOc6cdm0pc,32570
+evalvault/domain/services/visual_space_service.py,sha256=xG2jxKuRuqmQgbWsXOqmytKr6pQ7igQujNgdpb5gyB0,32569
 evalvault/ports/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalvault/ports/inbound/__init__.py,sha256=2Wsc0vNzH8_ZaErk4OHxP93hRonLUkMbn3W28DtTDO0,562
 evalvault/ports/inbound/analysis_pipeline_port.py,sha256=RJfKtp22AYEqnmRk6RDawAK52rEmyAhuk0FUPJQUwQU,1758
@@ -256,13 +266,13 @@ evalvault/ports/inbound/web_port.py,sha256=kjDyNXkgRwbevmSnm25URk-qHjGN9K9ML83FA
 evalvault/ports/outbound/__init__.py,sha256=jEmLbY3lZ9osue6pG5dc345BdMikBEWq4cnX7ocEul0,3276
 evalvault/ports/outbound/analysis_cache_port.py,sha256=zPSdUVK_yw3PMWPII2YvS1WLmCGlg5bDScSuYINW9yc,1386
 evalvault/ports/outbound/analysis_module_port.py,sha256=QYzkvie9-BbONj8ZgiQUjm8I-bn8mgzlXTzIXMhehmQ,1881
-evalvault/ports/outbound/analysis_port.py,sha256=zAiYKotd93IVZnPc8odSHN_t5nHW5VhICbFKR7SKSyY,2088
+evalvault/ports/outbound/analysis_port.py,sha256=gE-iXToTgdQomj9JwNZJY4nwut8q0J6EurUmJNsnptQ,2127
 evalvault/ports/outbound/benchmark_port.py,sha256=pgo3rNbvvJS8x03UxBVQPBBgxc7X5kfG70ZlIf3sopE,7173
 evalvault/ports/outbound/causal_analysis_port.py,sha256=IsyVdFrs66mHcOc-_VbxrZQriwMrDxx-5a_4ElX5Bp0,941
 evalvault/ports/outbound/dataset_port.py,sha256=OpEBlkvFwpSRbmi-Lt3wK7n0wljmQ6m985mjyNn_qFk,990
 evalvault/ports/outbound/domain_memory_port.py,sha256=SZFurqsoBmTw1Kt_pej-YpMbooVeyV35jekhaDRojus,23320
 evalvault/ports/outbound/embedding_port.py,sha256=ZHeKRMRBNjpZKWxsLKrD8jJz0M66JTwNcrJbkRaklK4,2034
-evalvault/ports/outbound/improvement_port.py,sha256=ejulfyNLfFpiIoiS5QczxBh-XH4YDyW-dE8HK0Yzye4,2254
+evalvault/ports/outbound/improvement_port.py,sha256=fIXhcG4n6OJ1hdvWeqEoLBrVsCNdHZRgtEZjR8lf3qA,2325
 evalvault/ports/outbound/intent_classifier_port.py,sha256=gqMIk0rH6Z43ceuMMRX4vqXurgHZz-CJX2bR5PVAkjQ,2253
 evalvault/ports/outbound/korean_nlp_port.py,sha256=mJCnxBAkV8a5Nd_VX6QcjfDucY62er8GlaNO4HQA8q8,1572
 evalvault/ports/outbound/llm_port.py,sha256=qnVmQmkWgpeJ_eB_W1gLgXTWpowfDgYrXG5uKUhIsy8,3528
@@ -278,8 +288,8 @@ evalvault/reports/__init__.py,sha256=Bb1X4871msAN8I6PM6nKGED3psPwZt88hXZBAOdH06Y
 evalvault/reports/release_notes.py,sha256=pZj0PBFT-4F_Ty-Kv5P69BuoOnmTCn4kznDcORFJd0w,4011
 evalvault/scripts/__init__.py,sha256=NwEeIFQbkX4ml2R_PhtIoNtArDSX_suuoymgG_7Kwso,89
 evalvault/scripts/regression_runner.py,sha256=SxZori5BZ8jVQ057Mf5V5FPgIVDccrV5oRONmnhuk8w,8438
-evalvault-1.57.1.dist-info/METADATA,sha256=Jtdtv4zOIruMC5Wmo5kEGwqZZMlyhnQbZENl6U5uog8,32284
-evalvault-1.57.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-evalvault-1.57.1.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
-evalvault-1.57.1.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
-evalvault-1.57.1.dist-info/RECORD,,
+evalvault-1.59.0.dist-info/METADATA,sha256=unwBGPN_vReQ3ohlNQZjMhPy8GBTxDqy1eSPvprX7dk,14058
+evalvault-1.59.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+evalvault-1.59.0.dist-info/entry_points.txt,sha256=Oj9Xc5gYcyUYYNmQfWI8NYGw7nN-3M-h2ipHIMlVn6o,65
+evalvault-1.59.0.dist-info/licenses/LICENSE.md,sha256=3RNWY4jjtrQ_yYa-D-7I3XO12Ti7YzxsLV_dpykujvo,11358
+evalvault-1.59.0.dist-info/RECORD,,