命名空间分支功能：即时克隆与独立读写
turbopuffer 推出 Namespace Branching 功能，通过 branch_from 实现命名空间的即时克隆，基于 copy-on-write 机制，克隆时间与命名空间大小无关。分支完全独立，支持多级分支链，无子分支数量限制。每次分支费用固定 0.032 美元，存储按逻辑字节计费。适用场景包括代码库索引、测试流水线、开发环境隔离和快照查询。 
RSS: https://turbopuffer.com/blog/rss.xml
vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable
提交点赞
评论
点赞
收藏Training SID-1 to beat GPT-5 at search with 1k+ QPS RL
SID-1 is an agentic search model that is 24x faster than GPT-5.1-high, 374x cheaper than Sonnet 4.5, and achieves 1.9x higher recall than traditional RAG pipelines. Here's how we trained it using larg...
Mixing numeric attributes into text search for better first-stage relevance
turbopuffer now allows you to combine attribute values into the scoring function of text queries. Ranking by attribute helps achieve better relevance in the first stage with the same scalability chara...
Rust zero-cost abstractions vs. SIMD
A customer query was taking over 4× longer than it should have. The profiler pointed at Rust code we'd assumed was free. We followed the trail all the way down to assembly to find the true cost.
ANN v3: 200ms p99 query latency over 100B vectors
Our latest ANN release supports scales of 100+ billion vectors in a single search index, with 200ms p99 query latency at 1k QPS and 92% recall.
Designing inverted indexes in a KV-store on object storage
How we redesigned our inverted index structure using fixed-sized posting blocks to achieve 10x smaller indexes and dramatically better throughput.
Why BM25 queries with more terms can be faster (and other scaling surprises)
I analyzed how BM25 query latencies scale with document count and top_k. Longer queries scale less efficiently, and essential terms impact performance in some surprising ways.
Vectorized MAXSCORE over WAND, especially for long LLM-generated queries
turbopuffer has improved text search performance up to 20x by adopting the same text search algorithm as Apache Lucene, a vectorized variant of block-max MAXSCORE
FTS v2: up to 20x faster full-text search
turbopuffer's full-text search engine is getting a major upgrade for 20x better full-text search performance
Native filtering for high-recall vector search
Describing how turbopuffer ensures high recall (accuracy) on queries that use attribute filters.
Turbopuffer: Continuous Recall Measurement
Describing how turbopuffer measures the recall (accuracy) of its vector indexes in production continuously. This ensures that turbopuffer's search results are accurate and reliable, despite using appr...
Turbopuffer: Fast search on object storage
Inaugural blog post about the development of turbopuffer, a search engine that uses object storage and SSD caching for cost-effective, low latency search. This post describes into the motivation behin...