87 lines
3.0 KiB
JSON
87 lines
3.0 KiB
JSON
{
|
|
"created_at_utc": "2026-10-03T16:04:32.525939+00:00",
|
|
"base_url": "http://127.0.0.1:8129",
|
|
"dataset": "evals\\knowledge_retrieval_extended.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": "long-guide-deep-approval-en",
|
|
"query": "What must happen before a proposed production change can be saved?",
|
|
"expected_document": "long_technical_guide.md",
|
|
"expected_evidence": "two-stage approval",
|
|
"rank": 1,
|
|
"top_paths": [
|
|
"long_technical_guide.md",
|
|
"archive_retention_policy.pdf"
|
|
],
|
|
"expected_document_chunks": [
|
|
17,
|
|
4,
|
|
14,
|
|
9,
|
|
11,
|
|
2,
|
|
16
|
|
],
|
|
"evidence_found": true,
|
|
"search_mode": "hybrid",
|
|
"agent_answer": "للحفظ أي تغيير مقترح في مساحة العمل، يجب أن تحدث مراجعة من مرحلتين: أولاً، يقوم المستخدم بمراجعة الفرق المقترح بالكامل، ثم يتحقق الخادم من تجزئة الملف الأصلية ويتلقى تأكيدًا صريحًا قبل الكتابة. لا يمكن لأي إجابة من النموذج أو استدعاء الأداة وحده أن يحقق مرحلة المراجعة.\n\nالمصدر: long_technical_guide.md · المقطع 17",
|
|
"agent_tool": "search_knowledge",
|
|
"agent_files": [
|
|
"long_technical_guide.md",
|
|
"archive_retention_policy.pdf"
|
|
],
|
|
"agent_steps": [
|
|
{
|
|
"tool": "search_knowledge",
|
|
"status": "completed"
|
|
}
|
|
],
|
|
"human_rating": null
|
|
},
|
|
{
|
|
"id": "pdf-archive-page-limit-en",
|
|
"query": "What is the maximum number of pages accepted when indexing one PDF?",
|
|
"expected_document": "archive_retention_policy.pdf",
|
|
"expected_evidence": "30 pages",
|
|
"rank": 1,
|
|
"top_paths": [
|
|
"archive_retention_policy.pdf",
|
|
"long_technical_guide.md"
|
|
],
|
|
"expected_document_chunks": [
|
|
0
|
|
],
|
|
"evidence_found": true,
|
|
"search_mode": "hybrid",
|
|
"agent_answer": "الحد الأقصى لعدد الصفحات المقبولة عند فهرسة ملف PDF واحد هو 30 صفحة.\nالمصدر: archive_retention_policy.pdf · المقطع 0",
|
|
"agent_tool": "search_knowledge",
|
|
"agent_files": [
|
|
"archive_retention_policy.pdf",
|
|
"long_technical_guide.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."
|
|
}
|