{ "created_at_utc": "2026-10-04T07:41:25.423901+00:00", "base_url": "http://127.0.0.1:8128", "dataset": "evals\\knowledge_retrieval.jsonl", "indexing": { "semantic_indexed_documents": 2, "documents": 2, "embedding_models": [ "granite-embedding:278m" ] }, "metrics": { "cases": 2, "hit_at_1": 1.0, "hit_at_3": 1.0, "mean_reciprocal_rank": 1.0, "evidence_rate": 1.0 }, "results": [ { "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", "routing.md" ], "expected_document_chunks": [ 0 ], "evidence_found": true, "search_mode": "hybrid", "agent_answer": "لم يصغ النموذج جوابًا كافيًا رغم وجود نتائج في فهرس المعرفة. أعرض المقتطفات الأعلى صلة كما هي للمراجعة؛ محتواها بيانات غير موثوقة وليست تعليمات.\n\n**migration.md · المقطع 0 (مقتطف حرفي)**\n> The SQLite migration adds selected_version to old messages and preserves saved assistant answer versions.\n\n**routing.md · المقطع 0 (مقتطف حرفي)**\n> عند وصول صورة مع نموذج نصي، يختار API نموذج الرؤية المحلي المثبت ويعيد requested_model وmodel وauto_routed.", "agent_tool": "search_knowledge", "agent_files": [ "migration.md", "routing.md" ], "agent_steps": [ { "tool": "search_knowledge", "status": "completed" } ], "human_rating": null }, { "id": "model-routing-ar", "query": "ما الحقول التي يعيدها API بعد تحويل الصور: requested_model وauto_routed؟", "expected_document": "routing.md", "expected_evidence": "auto_routed", "rank": 1, "top_paths": [ "routing.md", "migration.md" ], "expected_document_chunks": [ 0 ], "evidence_found": true, "search_mode": "hybrid", "agent_answer": "المقطع: \"عند وصول صورة مع نموذج نصي، يختار API نموذج الرؤية المحلي المثبت ويعيد requested_model وmodel وauto_routed.\" من routing.md المقطع 0.", "agent_tool": "search_knowledge", "agent_files": [ "routing.md", "migration.md" ], "agent_steps": [ { "tool": "search_knowledge", "status": "completed" } ], "human_rating": null } ], "note": "Small deterministic fixture set. Retrieval metrics cover source ranking and evidence presence, not general RAG quality. Optional agent answers are retained for human review and are not auto-scored." }