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-rag-chunk-context.json
+75 -19
View File
@@ -1,25 +1,81 @@
{
"caseId": "chat-rag-chunk-context",
"query": "If a long section is split into multiple chunks, how do we keep retrieval context?",
"retrievedAt": "2026-07-05T00:00:00Z",
"candidates": [
{
"rank": 1,
"docId": "rag-chunk-context-reconstruction",
"title": "RAG Chunk Context Reconstruction",
"breadcrumb": "RAG > Chunking > Context Reconstruction",
"content": "After a chunk hit, expand to neighbor chunk candidates from the same section and preserve breadcrumb metadata in the evidence pack.",
"score": 0.79,
"retrievalLayer": "L1"
"retrievedAt": "2026-07-06T00:00:00Z",
"lookupResult": {
"found": true,
"evidenceBlocks": [
{
"source": "rag-chunk-context-reconstruction",
"title": "RAG Chunk Context Reconstruction",
"breadcrumb": "RAG > Chunking > Context Reconstruction",
"retrievalLayer": "L1",
"content": "After a chunk hit, expand to neighbor chunk candidates from the same section and preserve breadcrumb metadata in the evidence pack.",
"score": 0.79,
"hitReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
},
{
"source": "rag-breadcrumb-embedding-gap",
"title": "RAG Breadcrumb Embedding Gap",
"breadcrumb": "RAG > Embedding > Breadcrumb",
"retrievalLayer": "L1",
"content": "Embedding title and breadcrumb with content helps recover section semantics.",
"score": 0.72,
"hitReasons": ["domain_match:+0.15"]
}
],
"contextPack": {
"packedText": "[1] RAG Chunk Context Reconstruction\nRAG > Chunking > Context Reconstruction\nAfter a chunk hit, expand to neighbor chunk candidates from the same section and preserve breadcrumb metadata in the evidence pack.",
"strategy": "top_evidence_blocks",
"charBudget": 3500,
"usedChars": 203,
"includedSources": ["rag-chunk-context-reconstruction", "rag-breadcrumb-embedding-gap"],
"omittedSources": []
},
{
"rank": 2,
"docId": "rag-breadcrumb-embedding-gap",
"title": "RAG Breadcrumb Embedding Gap",
"breadcrumb": "RAG > Embedding > Breadcrumb",
"content": "Embedding title and breadcrumb with content helps recover section semantics.",
"score": 0.72,
"retrievalLayer": "L1"
"retrievalTrace": {
"originalQuery": "If a long section is split into multiple chunks, how do we keep retrieval context?",
"rewrittenQuery": "RAG chunk context reconstruction neighbor chunk same section breadcrumb",
"categoryFilter": "RAG",
"selectedAttempt": "FILTERED_VECTOR",
"fallbackReason": null,
"evidenceStatus": "supported",
"queryHints": {
"domains": ["RAG"],
"matched_keywords": ["neighbor chunk", "same section", "breadcrumb"],
"entities": ["chunk", "breadcrumb"],
"l0_titles": ["RAG Chunk Context Reconstruction"],
"l0_match_count": 1
},
"attempts": [
{
"name": "FILTERED_VECTOR",
"query": "RAG chunk context reconstruction neighbor chunk same section breadcrumb",
"categoryFilter": "RAG",
"candidateCount": 2,
"usable": true,
"durationMs": 9,
"topScore": 0.79,
"topSimilarity": 0.79
}
]
},
"rerankTrace": {
"items": [
{
"finalRank": 1,
"source": "rag-chunk-context-reconstruction",
"baseScore": 0.79,
"finalScore": 1.04,
"boostReasons": ["domain_match:+0.15", "keyword_match:+0.10"]
},
{
"finalRank": 2,
"source": "rag-breadcrumb-embedding-gap",
"baseScore": 0.72,
"finalScore": 0.87,
"boostReasons": ["domain_match:+0.15"]
}
]
}
]
}
}