Total vectors
51,238
Embedding model
text-embedding-3-small
Dimensions
1,536
Avg query latency
12ms
Vectors by namespace
| Namespace | Vectors | Last upserted | Query latency p50 |
|---|---|---|---|
| fleet-wide (universal sailing) | 18,432 | 13:12 | 11ms |
| SLG-0427 Caribbean | 7,128 | 14:35 | 12ms |
| SLG-0428 Mediterranean | 6,891 | 14:18 | 13ms |
| SLG-0429 Alaska | 5,742 | 14:06 | 12ms |
| SLG-0430 Transatlantic | 6,412 | 13:48 | 11ms |
| SLG-0431 Bahamas | 6,633 | 14:22 | 13ms |
Embedding pipeline
Documents are chunked at sentence-aware boundaries (±500 tokens), embedded via OpenAI text-embedding-3-small (1,536 dimensions), and upserted to Pinecone with rich metadata: source, date, content_type, and sailing_id. Queries run with top_k=8 and a 0.75 score threshold. Per-tenant namespace isolation — no cross-sailing inference.