osiman/SuperBizAgent-java
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(rag): close eval pipeline with live snapshots

Browse Source
This commit is contained in:
zhuyongxin
2026-07-06 21:39:27 +08:00
parent cf3333d607
commit ed7efc58b7
47 changed files with 2613 additions and 177 deletions
Download Patch File Download Diff File Expand all files Collapse all files
eval/rag-retrieval/fixtures/chat-diagnosis-flow.json
+75 -19
View File
@@ -1,25 +1,81 @@
{
"caseId": "chat-diagnosis-flow",
"query": "What is the standard troubleshooting flow for an application incident?",
"retrievedAt": "2026-07-05T00:00:00Z",
"candidates": [
{
"rank": 1,
"docId": "incident-diagnosis-flow",
"title": "Incident Diagnosis Flow",
"breadcrumb": "AIOps > Diagnosis Flow",
"content": "The standard flow is to collect evidence, identify the suspected fault domain, verify the hypothesis, apply remediation, and confirm recovery.",
"score": 0.82,
"retrievalLayer": "L1"
"retrievedAt": "2026-07-06T00:00:00Z",
"lookupResult": {
"found": true,
"evidenceBlocks": [
{
"source": "incident-diagnosis-flow",
"title": "Incident Diagnosis Flow",
"breadcrumb": "AIOps > Diagnosis Flow",
"retrievalLayer": "L1",
"content": "The standard flow is to collect evidence, identify the suspected fault domain, verify the hypothesis, apply remediation, and confirm recovery.",
"score": 0.82,
"hitReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
},
{
"source": "rag-chunk-context-reconstruction",
"title": "RAG Chunk Context Reconstruction",
"breadcrumb": "RAG > Chunking > Context Reconstruction",
"retrievalLayer": "L1",
"content": "Long sections may require neighbor chunk expansion and breadcrumb-aware packing.",
"score": 0.55,
"hitReasons": []
}
],
"contextPack": {
"packedText": "[1] Incident Diagnosis Flow\nAIOps > Diagnosis Flow\nThe standard flow is to collect evidence, identify the suspected fault domain, verify the hypothesis, apply remediation, and confirm recovery.",
"strategy": "top_evidence_blocks",
"charBudget": 3500,
"usedChars": 192,
"includedSources": ["incident-diagnosis-flow", "rag-chunk-context-reconstruction"],
"omittedSources": []
},
{
"rank": 2,
"docId": "rag-chunk-context-reconstruction",
"title": "RAG Chunk Context Reconstruction",
"breadcrumb": "RAG > Chunking > Context Reconstruction",
"content": "Long sections may require neighbor chunk expansion and breadcrumb-aware packing.",
"score": 0.55,
"retrievalLayer": "L1"
"retrievalTrace": {
"originalQuery": "What is the standard troubleshooting flow for an application incident?",
"rewrittenQuery": "standard application incident troubleshooting flow collect evidence verify remediation",
"categoryFilter": "AIOps",
"selectedAttempt": "FILTERED_VECTOR",
"fallbackReason": null,
"evidenceStatus": "supported",
"queryHints": {
"domains": ["AIOps"],
"matched_keywords": ["collect evidence", "verify", "remediation"],
"entities": ["application incident"],
"l0_titles": ["Incident Diagnosis Flow"],
"l0_match_count": 1
},
"attempts": [
{
"name": "FILTERED_VECTOR",
"query": "standard application incident troubleshooting flow collect evidence verify remediation",
"categoryFilter": "AIOps",
"candidateCount": 2,
"usable": true,
"durationMs": 10,
"topScore": 0.82,
"topSimilarity": 0.82
}
]
},
"rerankTrace": {
"items": [
{
"finalRank": 1,
"source": "incident-diagnosis-flow",
"baseScore": 0.82,
"finalScore": 1.07,
"boostReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
},
{
"finalRank": 2,
"source": "rag-chunk-context-reconstruction",
"baseScore": 0.55,
"finalScore": 0.55,
"boostReasons": []
}
]
}
]
}
}