Commit Graph

12 Commits

Author SHA1 Message Date
wangwei
791738bb07 feat: rename project to 'Siemens RAGAS 评估平台' in frontend
- index.html: page title, brand-mark, brand-sub
- server.py: FastAPI app title
- app.css: comment header

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-24 10:20:23 +08:00
wangwei
1dc7ab9727 fix: restore LLM profile test connectivity buttons (lost from git)
Frontend test functionality was implemented but never committed to git.
Re-adds:
- profiles.js: testCard(), testForm(), _showTestResult(), test btn in renderCard
- api.js: testProfile(id) and probeConnectivity(body) methods
- index.html: 测试连通性 button + result div in profile form
- app.css: .btn-test and .profile-test-result styles

Backend /probe and /{id}/test endpoints were already present in llm_profiles.py.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-23 13:58:43 +08:00
wangwei
f9e3ba0f64 feat: add weight config panel to 新建评估 and weighted_score card to report
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-18 17:28:15 +08:00
wangwei
9ad2daff73 feat: restore API文档 nav item (iframe /docs) without touching other 4 modules 2026-06-17 11:24:16 +08:00
wangwei
e8af5b906c chore: remove API docs iframe nav item, rename title to RAGAS 评估控制台 2026-06-17 11:18:01 +08:00
wangwei
8ea2b9c7d2 feat: add API文档 nav item with embedded Swagger UI iframe 2026-06-17 11:09:55 +08:00
wangwei
074800b741 feat: add history report switcher dropdown in report detail view 2026-06-17 10:35:56 +08:00
wangwei
3019390592 feat: add export-to-PDF via browser print with @media print CSS 2026-06-17 10:28:01 +08:00
wangwei
ca01e44ad2 feat(webapp): add session persistence via URL hash routing + sessionStorage
- app.js: hash-based router (#runs / #new / #profiles / #report/{runId})
  - navigate() pushes history entries for back/forward support
  - _restoreSession() reads hash on load and popstate
  - sessionStorage fallback for same-tab refreshes
  - run-card highlights selected run (.run-card.selected)
- runner.js: use App.navigate() for report redirect; persist lastRunId to sessionStorage
- index.html: report nav button starts disabled (enabled on run select/restore)
- app.css: .run-card.selected with petrol border + ring

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-16 17:55:07 +08:00
wangwei
1a2cc534b8 feat(webapp): add optimization advice section to report UI
- index.html: add section ⑤ advice block (hidden by default, shown when advice_markdown present)
- report.js: add renderAdvice() called in render(), simple Markdown→HTML converter
- app.js: add noise_sensitivity / factual_correctness / semantic_similarity to shortMetric map
- app.css: add .advice-panel, .advice-badge, .advice-md styles (purple left-border theme)

Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-16 17:26:37 +08:00
wangwei
dc8baf8662 feat: add LLM配置 management page (profiles view) 2026-06-16 16:25:20 +08:00
wangwei
e89695e490 Add RAGAS evaluation web console (FastAPI + vanilla JS)
- webapp/: FastAPI backend with runs/scenarios/evaluations API routers;
  services for run_reader, report_builder, scenario_scanner, task_manager
  (lazy ragas import — server boots even without ragas); Pydantic models
- webapp/static/: single-page console (layout A: left-nav + main area);
  report detail with metric cards, Chart.js distribution histogram,
  grouping table, lowest-score sample review; trigger evaluation + log polling
- webmain.py: uvicorn entry point (alongside existing main.py CLI)
- start.bat: Windows one-click launcher with env checks and auto-browser open
- rag_eval/datasets/: implement missing loader + normalizer modules
  (load_dataset_records, normalize_records) required by evaluator
- scripts/seed_sample_run.py: generate realistic demo run artifacts
- .gitignore: exclude datasets/ data files but keep rag_eval/datasets/ source

Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
2026-06-15 15:53:57 +08:00