{
  "created_at_utc": "2026-10-02T14:00:13.073708+00:00",
  "base_url": "http://127.0.0.1:8000",
  "dataset": "evals\\knowledge_retrieval.jsonl",
  "metrics": {
    "cases": 3,
    "hit_at_1": 1.0,
    "hit_at_3": 1.0,
    "mean_reciprocal_rank": 1.0,
    "evidence_rate": 1.0
  },
  "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"
      ],
      "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
    }
  ],
  "note": "Small deterministic fixture set; measures lexical retrieval only, not answer quality or general RAG quality."
}