rust-kgdb 0.6.46 → 0.6.47
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +25 -0
- package/README.md +25 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,31 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to the rust-kgdb TypeScript SDK will be documented in this file.
|
|
4
4
|
|
|
5
|
+
## [0.6.47] - 2025-12-17
|
|
6
|
+
|
|
7
|
+
### Memory Retrieval Depth Benchmark Added
|
|
8
|
+
|
|
9
|
+
#### New Benchmark Documentation
|
|
10
|
+
Added Memory Retrieval Depth Benchmark to README, based on academic benchmarks:
|
|
11
|
+
- MemQ (arXiv 2503.05193)
|
|
12
|
+
- mKGQAgent (Text2SPARQL 2025)
|
|
13
|
+
- MTEB (Massive Text Embedding Benchmark)
|
|
14
|
+
|
|
15
|
+
**Results** (50 queries per depth, HNSW index):
|
|
16
|
+
|
|
17
|
+
| Depth | P50 Latency | Recall@5 | Recall@10 | MRR |
|
|
18
|
+
|-------|-------------|----------|-----------|-----|
|
|
19
|
+
| 10 | 0.06 ms | 78% | 100% | 0.68 |
|
|
20
|
+
| 100 | 0.50 ms | 88% | 98% | 0.42 |
|
|
21
|
+
| 1,000 | 1.59 ms | 80% | 94% | 0.50 |
|
|
22
|
+
| 10,000 | 16.71 ms | 76% | 94% | 0.54 |
|
|
23
|
+
|
|
24
|
+
**Key insight**: Even at 10K stored queries, Recall@10 stays at 94% with sub-17ms latency.
|
|
25
|
+
|
|
26
|
+
Reproduce: `node memory-retrieval-benchmark.js`
|
|
27
|
+
|
|
28
|
+
---
|
|
29
|
+
|
|
5
30
|
## [0.6.46] - 2025-12-17
|
|
6
31
|
|
|
7
32
|
### Honest Comparison Fix
|
package/README.md
CHANGED
|
@@ -135,6 +135,31 @@ db.loadTtl(':Provider123 :hasRiskScore "0.87" .', null)
|
|
|
135
135
|
└─────────────────────────────────────────────────────────────────────────────┘
|
|
136
136
|
```
|
|
137
137
|
|
|
138
|
+
### Memory Retrieval Depth Benchmark
|
|
139
|
+
|
|
140
|
+
Based on academic benchmarks: MemQ (arXiv 2503.05193), mKGQAgent (Text2SPARQL 2025), MTEB.
|
|
141
|
+
|
|
142
|
+
```
|
|
143
|
+
┌─────────────────────────────────────────────────────────────────────────────┐
|
|
144
|
+
│ BENCHMARK: Memory Retrieval at Depth (50 queries per depth) │
|
|
145
|
+
│ METHODOLOGY: LUBM schema-driven queries, HNSW index, random seed 42 │
|
|
146
|
+
├─────────────────────────────────────────────────────────────────────────────┤
|
|
147
|
+
│ │
|
|
148
|
+
│ DEPTH │ P50 LATENCY │ P95 LATENCY │ Recall@5 │ Recall@10 │ MRR │
|
|
149
|
+
│ ──────────────────────────────────────────────────────────────────────────│
|
|
150
|
+
│ 10 │ 0.06 ms │ 0.26 ms │ 78% │ 100% │ 0.68 │
|
|
151
|
+
│ 100 │ 0.50 ms │ 0.75 ms │ 88% │ 98% │ 0.42 │
|
|
152
|
+
│ 1,000 │ 1.59 ms │ 5.03 ms │ 80% │ 94% │ 0.50 │
|
|
153
|
+
│ 10,000 │ 16.71 ms │ 17.37 ms │ 76% │ 94% │ 0.54 │
|
|
154
|
+
│ ──────────────────────────────────────────────────────────────────────────│
|
|
155
|
+
│ │
|
|
156
|
+
│ KEY INSIGHT: Even at 10,000 stored queries, Recall@10 stays at 94% │
|
|
157
|
+
│ Sub-17ms retrieval from 10K query pool = practical for production use │
|
|
158
|
+
│ │
|
|
159
|
+
│ Reproduce: node memory-retrieval-benchmark.js │
|
|
160
|
+
└─────────────────────────────────────────────────────────────────────────────┘
|
|
161
|
+
```
|
|
162
|
+
|
|
138
163
|
### Where We Actually Outperform (Database Performance)
|
|
139
164
|
|
|
140
165
|
```
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "rust-kgdb",
|
|
3
|
-
"version": "0.6.
|
|
3
|
+
"version": "0.6.47",
|
|
4
4
|
"description": "High-performance RDF/SPARQL database with AI agent framework. GraphDB (449ns lookups, 35x faster than RDFox), GraphFrames analytics (PageRank, motifs), Datalog reasoning, HNSW vector embeddings. HyperMindAgent for schema-aware query generation with audit trails. W3C SPARQL 1.1 compliant. Native performance via Rust + NAPI-RS.",
|
|
5
5
|
"main": "index.js",
|
|
6
6
|
"types": "index.d.ts",
|