{ "created_at_utc": "2026-10-02T14:03:39.595295+00:00", "base_url": "http://127.0.0.1:8000", "dataset": "evals\\knowledge_retrieval.jsonl", "metrics": { "cases": 11, "hit_at_1": 0.8181818181818182, "hit_at_3": 0.9090909090909091, "mean_reciprocal_rank": 0.8636363636363636, "evidence_rate": 0.9090909090909091 }, "results": [ { "id": "conversation-storage-ar", "query": "أين تحفظ المحادثات؟", "expected_document": "storage.md", "expected_evidence": "SQLite", "rank": 1, "top_paths": [ "storage.md" ], "evidence_found": true }, { "id": "image-model-ar", "query": "ما النموذج الذي يعالج الصور تلقائيًا؟", "expected_document": "images.md", "expected_evidence": "Ministral 3:3b", "rank": 1, "top_paths": [ "images.md", "timeout.md" ], "evidence_found": true }, { "id": "preview-safety-ar", "query": "كيف نحمي معاينة الملف قبل الموافقة؟", "expected_document": "preview.md", "expected_evidence": "SHA256", "rank": 1, "top_paths": [ "preview.md" ], "evidence_found": true }, { "id": "pdf-extraction-ar", "query": "كيف نستخرج النص من صفحات PDF؟", "expected_document": "pdf.md", "expected_evidence": "pypdf", "rank": 1, "top_paths": [ "pdf.md", "audio.md", "images.md" ], "evidence_found": true }, { "id": "voice-transcription-ar", "query": "أي خدمة تفرغ التسجيلات الصوتية؟", "expected_document": "audio.md", "expected_evidence": "Groq", "rank": null, "top_paths": [], "evidence_found": false }, { "id": "workspace-boundary-ar", "query": "كيف نحمي مساحة العمل من قراءة الملفات المخفية؟", "expected_document": "workspace.md", "expected_evidence": ".git", "rank": 1, "top_paths": [ "workspace.md", "preview.md", "pdf.md" ], "evidence_found": true }, { "id": "web-search-en", "query": "Which provider searches multiple web sources?", "expected_document": "search.md", "expected_evidence": "DuckDuckGo", "rank": 1, "top_paths": [ "search.md" ], "evidence_found": true }, { "id": "database-version-en", "query": "How are old conversation answers migrated?", "expected_document": "migration.md", "expected_evidence": "selected_version", "rank": 1, "top_paths": [ "migration.md" ], "evidence_found": true }, { "id": "model-routing-ar", "query": "متى يحول النظام الصور إلى نموذج الرؤية؟", "expected_document": "routing.md", "expected_evidence": "auto_routed", "rank": 2, "top_paths": [ "images.md", "routing.md", "audio.md" ], "evidence_found": true }, { "id": "api-timeout-ar", "query": "كيف يعرض API انتهاء مهلة النموذج؟", "expected_document": "timeout.md", "expected_evidence": "504", "rank": 1, "top_paths": [ "timeout.md", "routing.md" ], "evidence_found": true }, { "id": "skill-permissions-en", "query": "How does the server restrict tools for a selected skill?", "expected_document": "skills.md", "expected_evidence": "allowed_tools", "rank": 1, "top_paths": [ "skills.md", "migration.md" ], "evidence_found": true } ], "note": "Small deterministic fixture set; measures lexical retrieval only, not answer quality or general RAG quality." }