mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-11 02:33:51 +08:00
feat: Add method to retrieve all semantic chunks from the vector store
- Implemented `get_all_chunks` method in `VectorStore` class to fetch all semantic chunks from the database. - Added a new benchmark script `analyze_methods.py` for analyzing hybrid search methods and storage architecture. - Included detailed analysis of method contributions, storage conflicts, and FTS + Rerank fusion experiments. - Updated results JSON structure to reflect new analysis outputs and method performance metrics.
This commit is contained in:
catlog22
406
codex-lens/benchmarks/results/method_contribution_analysis.json
Normal file
406
codex-lens/benchmarks/results/method_contribution_analysis.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"storage_analysis": {
|
||||
"tables": {
|
||||
"code_relationships": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"source_symbol_id",
|
||||
"target_qualified_name",
|
||||
"relationship_type",
|
||||
"source_line",
|
||||
"target_file"
|
||||
]
|
||||
},
|
||||
"embeddings_config": {
|
||||
"row_count": 1,
|
||||
"columns": [
|
||||
"id",
|
||||
"model_profile",
|
||||
"model_name",
|
||||
"embedding_dim",
|
||||
"backend",
|
||||
"created_at",
|
||||
"updated_at"
|
||||
]
|
||||
},
|
||||
"file_keywords": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"file_id",
|
||||
"keyword_id"
|
||||
]
|
||||
},
|
||||
"files": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"name",
|
||||
"full_path",
|
||||
"language",
|
||||
"content",
|
||||
"mtime",
|
||||
"line_count"
|
||||
]
|
||||
},
|
||||
"files_fts_exact": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"name",
|
||||
"full_path",
|
||||
"content"
|
||||
]
|
||||
},
|
||||
"files_fts_exact_config": {
|
||||
"row_count": 1,
|
||||
"columns": [
|
||||
"k",
|
||||
"v"
|
||||
]
|
||||
},
|
||||
"files_fts_exact_data": {
|
||||
"row_count": 2,
|
||||
"columns": [
|
||||
"id",
|
||||
"block"
|
||||
]
|
||||
},
|
||||
"files_fts_exact_docsize": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"sz"
|
||||
]
|
||||
},
|
||||
"files_fts_exact_idx": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"segid",
|
||||
"term",
|
||||
"pgno"
|
||||
]
|
||||
},
|
||||
"files_fts_fuzzy": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"name",
|
||||
"full_path",
|
||||
"content"
|
||||
]
|
||||
},
|
||||
"files_fts_fuzzy_config": {
|
||||
"row_count": 1,
|
||||
"columns": [
|
||||
"k",
|
||||
"v"
|
||||
]
|
||||
},
|
||||
"files_fts_fuzzy_data": {
|
||||
"row_count": 2,
|
||||
"columns": [
|
||||
"id",
|
||||
"block"
|
||||
]
|
||||
},
|
||||
"files_fts_fuzzy_docsize": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"sz"
|
||||
]
|
||||
},
|
||||
"files_fts_fuzzy_idx": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"segid",
|
||||
"term",
|
||||
"pgno"
|
||||
]
|
||||
},
|
||||
"graph_neighbors": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"source_symbol_id",
|
||||
"neighbor_symbol_id",
|
||||
"relationship_depth"
|
||||
]
|
||||
},
|
||||
"keywords": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"keyword"
|
||||
]
|
||||
},
|
||||
"merkle_hashes": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"file_id",
|
||||
"sha256",
|
||||
"updated_at"
|
||||
]
|
||||
},
|
||||
"merkle_state": {
|
||||
"row_count": 1,
|
||||
"columns": [
|
||||
"id",
|
||||
"root_hash",
|
||||
"updated_at"
|
||||
]
|
||||
},
|
||||
"semantic_chunks": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"file_path",
|
||||
"content",
|
||||
"embedding",
|
||||
"metadata",
|
||||
"created_at",
|
||||
"embedding_binary",
|
||||
"embedding_dense"
|
||||
]
|
||||
},
|
||||
"semantic_metadata": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"file_id",
|
||||
"summary",
|
||||
"purpose",
|
||||
"llm_tool",
|
||||
"generated_at"
|
||||
]
|
||||
},
|
||||
"sqlite_sequence": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"name",
|
||||
"seq"
|
||||
]
|
||||
},
|
||||
"subdirs": {
|
||||
"row_count": 2,
|
||||
"columns": [
|
||||
"id",
|
||||
"name",
|
||||
"index_path",
|
||||
"files_count",
|
||||
"last_updated"
|
||||
]
|
||||
},
|
||||
"symbols": {
|
||||
"row_count": 0,
|
||||
"columns": [
|
||||
"id",
|
||||
"file_id",
|
||||
"name",
|
||||
"kind",
|
||||
"start_line",
|
||||
"end_line"
|
||||
]
|
||||
}
|
||||
},
|
||||
"conflicts": [],
|
||||
"recommendations": [
|
||||
"Found 10 FTS tables: ['files_fts_exact', 'files_fts_exact_config', 'files_fts_exact_data', 'files_fts_exact_docsize', 'files_fts_exact_idx', 'files_fts_fuzzy', 'files_fts_fuzzy_config', 'files_fts_fuzzy_data', 'files_fts_fuzzy_docsize', 'files_fts_fuzzy_idx']. Dual FTS (exact + fuzzy) is properly configured."
|
||||
]
|
||||
},
|
||||
"contribution_analysis": {
|
||||
"per_query": [
|
||||
{
|
||||
"query": "binary quantization",
|
||||
"methods": {
|
||||
"fts_exact": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"vector": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"splade": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
}
|
||||
},
|
||||
"fusion_analysis": {},
|
||||
"overlaps": {}
|
||||
},
|
||||
{
|
||||
"query": "hamming distance search",
|
||||
"methods": {
|
||||
"fts_exact": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"vector": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"splade": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
}
|
||||
},
|
||||
"fusion_analysis": {},
|
||||
"overlaps": {}
|
||||
},
|
||||
{
|
||||
"query": "embeddings generation",
|
||||
"methods": {
|
||||
"fts_exact": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"vector": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"splade": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
}
|
||||
},
|
||||
"fusion_analysis": {},
|
||||
"overlaps": {}
|
||||
},
|
||||
{
|
||||
"query": "reranking algorithm",
|
||||
"methods": {
|
||||
"fts_exact": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"vector": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"splade": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
}
|
||||
},
|
||||
"fusion_analysis": {},
|
||||
"overlaps": {}
|
||||
},
|
||||
{
|
||||
"query": "database connection handling",
|
||||
"methods": {
|
||||
"fts_exact": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"vector": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
},
|
||||
"splade": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'",
|
||||
"count": 0
|
||||
}
|
||||
},
|
||||
"fusion_analysis": {},
|
||||
"overlaps": {}
|
||||
}
|
||||
],
|
||||
"summary": {
|
||||
"fts_exact": {
|
||||
"avg_count": 0.0,
|
||||
"avg_latency_ms": 0
|
||||
},
|
||||
"fts_fuzzy": {
|
||||
"avg_count": 0.0,
|
||||
"avg_latency_ms": 0
|
||||
},
|
||||
"vector": {
|
||||
"avg_count": 0.0,
|
||||
"avg_latency_ms": 0
|
||||
},
|
||||
"splade": {
|
||||
"avg_count": 0.0,
|
||||
"avg_latency_ms": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
"fusion_experiment": {
|
||||
"per_query": [
|
||||
{
|
||||
"query": "binary quantization",
|
||||
"strategies": {
|
||||
"standard_hybrid": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
},
|
||||
"fts_rerank_fusion": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"query": "hamming distance search",
|
||||
"strategies": {
|
||||
"standard_hybrid": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
},
|
||||
"fts_rerank_fusion": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"query": "embeddings generation",
|
||||
"strategies": {
|
||||
"standard_hybrid": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
},
|
||||
"fts_rerank_fusion": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"query": "reranking algorithm",
|
||||
"strategies": {
|
||||
"standard_hybrid": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
},
|
||||
"fts_rerank_fusion": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"query": "database connection handling",
|
||||
"strategies": {
|
||||
"standard_hybrid": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
},
|
||||
"fts_rerank_fusion": {
|
||||
"error": "'obj' object has no attribute 'symbol_boost_factor'"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"summary": {}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user