feat(rag): close eval pipeline with live snapshots
This commit is contained in:
@@ -1,25 +1,81 @@
|
||||
{
|
||||
"caseId": "chat-l0-domain-hint",
|
||||
"query": "Should L0 keyword matching decide the final retrieval result?",
|
||||
"retrievedAt": "2026-07-05T00:00:00Z",
|
||||
"candidates": [
|
||||
{
|
||||
"rank": 1,
|
||||
"docId": "rag-l0-domain-entity-hint",
|
||||
"title": "RAG L0 Domain Entity Hint",
|
||||
"breadcrumb": "RAG > L0 > Domain Entity Hint",
|
||||
"content": "L0 should be retained as a domain detector, entity extractor, metadata filter generator, and explainability signal, not as the final retrieval decision.",
|
||||
"score": 0.88,
|
||||
"retrievalLayer": "L0"
|
||||
"retrievedAt": "2026-07-06T00:00:00Z",
|
||||
"lookupResult": {
|
||||
"found": true,
|
||||
"evidenceBlocks": [
|
||||
{
|
||||
"source": "rag-l0-domain-entity-hint",
|
||||
"title": "RAG L0 Domain Entity Hint",
|
||||
"breadcrumb": "RAG > L0 > Domain Entity Hint",
|
||||
"retrievalLayer": "L1",
|
||||
"content": "L0 should be retained as a domain detector, entity extractor, metadata filter generator, and explainability signal, not as the final retrieval decision.",
|
||||
"score": 0.88,
|
||||
"hitReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
|
||||
},
|
||||
{
|
||||
"source": "rag-l0-l1-fusion-ranking",
|
||||
"title": "RAG L0 L1 Fusion Ranking",
|
||||
"breadcrumb": "RAG > Ranking > Fusion",
|
||||
"retrievalLayer": "L1",
|
||||
"content": "L0 and L1 candidates should eventually be fused rather than handled as an early-return branch.",
|
||||
"score": 0.75,
|
||||
"hitReasons": ["domain_match:+0.15"]
|
||||
}
|
||||
],
|
||||
"contextPack": {
|
||||
"packedText": "[1] RAG L0 Domain Entity Hint\nRAG > L0 > Domain Entity Hint\nL0 should be retained as a domain detector, entity extractor, metadata filter generator, and explainability signal, not as the final retrieval decision.",
|
||||
"strategy": "top_evidence_blocks",
|
||||
"charBudget": 3500,
|
||||
"usedChars": 219,
|
||||
"includedSources": ["rag-l0-domain-entity-hint", "rag-l0-l1-fusion-ranking"],
|
||||
"omittedSources": []
|
||||
},
|
||||
{
|
||||
"rank": 2,
|
||||
"docId": "rag-l0-l1-fusion-ranking",
|
||||
"title": "RAG L0 L1 Fusion Ranking",
|
||||
"breadcrumb": "RAG > Ranking > Fusion",
|
||||
"content": "L0 and L1 candidates should eventually be fused rather than handled as an early-return branch.",
|
||||
"score": 0.75,
|
||||
"retrievalLayer": "L1"
|
||||
"retrievalTrace": {
|
||||
"originalQuery": "Should L0 keyword matching decide the final retrieval result?",
|
||||
"rewrittenQuery": "RAG L0 keyword matching domain entity hint final retrieval decision",
|
||||
"categoryFilter": "RAG",
|
||||
"selectedAttempt": "FILTERED_VECTOR",
|
||||
"fallbackReason": null,
|
||||
"evidenceStatus": "supported",
|
||||
"queryHints": {
|
||||
"domains": ["RAG"],
|
||||
"matched_keywords": ["domain detector", "entity extractor", "metadata filter"],
|
||||
"entities": ["L0"],
|
||||
"l0_titles": ["RAG L0 Domain Entity Hint"],
|
||||
"l0_match_count": 1
|
||||
},
|
||||
"attempts": [
|
||||
{
|
||||
"name": "FILTERED_VECTOR",
|
||||
"query": "RAG L0 keyword matching domain entity hint final retrieval decision",
|
||||
"categoryFilter": "RAG",
|
||||
"candidateCount": 2,
|
||||
"usable": true,
|
||||
"durationMs": 9,
|
||||
"topScore": 0.88,
|
||||
"topSimilarity": 0.88
|
||||
}
|
||||
]
|
||||
},
|
||||
"rerankTrace": {
|
||||
"items": [
|
||||
{
|
||||
"finalRank": 1,
|
||||
"source": "rag-l0-domain-entity-hint",
|
||||
"baseScore": 0.88,
|
||||
"finalScore": 1.13,
|
||||
"boostReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
|
||||
},
|
||||
{
|
||||
"finalRank": 2,
|
||||
"source": "rag-l0-l1-fusion-ranking",
|
||||
"baseScore": 0.75,
|
||||
"finalScore": 0.9,
|
||||
"boostReasons": ["domain_match:+0.15"]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user