Navigation
There isn't a limit or performance metric we can't improve by an order of magnitude when prioritized! If you expect to brush up against a limit or you are limited by present performance, contact us. Often can be fixed in days.
| turbopuffer excels at | turbopuffer may not currently be the best fit for |
|---|---|
| Large scale (1B+ documents/vectors) with lots of namespaces (tens of millions) | Large namespaces (250M+) with lots of queries |
| Naturally sharded data (e.g. B2B where each tenant's data is isolated in its own namespace) | Low scale, free tier |
| Cost-effectiveness | 🔜 Aggregation (e.g. group by, sums, explore clusters, ...) |
| Fast cold starts | Single-digit millisecond latency (tpuf is currently low double digits) |
| Reliability | Extensive 1st-stage ranking (we encourage generating a candidate set with hybrid search and refining/re-ranking further in your own 2nd stage) |
| Hybrid search (BM25 + vector search) | Built-in re-ranking (we encourage you to do it in your own application) |
| Support from DB Engineers | Built-in embedding (ditto) |
| Deploy into your VPC (BYOC) | Open Source |
| Heavy writes (Appends, Updates and Deletes) |
| Metric | Max seen in production | Production limits (current) | Production limits (soon) |
|---|---|---|---|
| Max documents (global) | 125B+ | Unlimited | |
| Max documents (per namespace) | 200M | 100M | 1B+ |
| Number of namespaces | 35M+ | Unlimited | |
| Max dimensions | 10,752 | ||
| Max inactive time in cache | ~3 days | Contact us for custom | |
| Write rate (global) | 1,000,000 doc/s | Unlimited | |
| Write rate (per namespace) | 10,000 doc/s | 10,000 doc/s | |
| Max upsert batch request size | 256 MB | 256 MB | |
| Max write batch rate (per namespace) | 1 batch/s | 1 batch/s | 4 batches/s |
| Max rows affected by delete by filter | 25M | ~10M | |
| Max ingested, unindexed data | 2 GB | 2 GB | |
| Queries (global) | 6K+ queries/s | Unlimited | |
| Max queries/second (per namespace) | 100+ queries/s | 100+ queries/s | 10,000 QPS |
| Max concurrent queries per namespace | 16 | 16 | |
| Vector search recall@10 | 90-100% | 90-100% | Configurable |
| Max attribute value | 8 MiB | 8 MiB | |
| Max id size | 64 bytes | ||
| Max attribute name length | 128 | 128 | |
| Max attribute names per namespace | 256 | 256 | |
| Max namespace name length | 128 | 128 | |
| Max full-text query length | 1024 | 1024 | |
| Max topk | 10,000 | 1200 |
