- 🌿 Namespace branching: instant copy-on-write namespace cloning
- ✏️ Typo-tolerant string matching with the Fuzzy filter
- 🗺️ View namespace metadata in the dashboard
- #️⃣ C# API client
- 🔤 word_v4 tokenizer, ~3x faster than
word_v3 - ⏱️ Make asynchronous requests to
copy_from_namespaceandrecallendpoints - 📋 New API key permission to list namespaces
turbopuffer
- 📌 Pin a namespace to cache for lower cost at high QPS
- 🕸️ Support for sparse vector search
- ↔️ GCP <-> AWS namespace copies with copy_from_namespace
- 🔎 Search the turbopuffer docs (type cmd+K!)
- 🏃♂️ Faster commit cadence on AWS for 2.5x lower write latency
- 💗 Increased full-text query length limit to 8,192 chars
- 🦣 Increased attributes per namespace limit to 1,024
- 🌎 3 new regions (São Paulo, South Carolina, Belgium)
- 🧱 Drop #002 (lil block puff) now live on turbopuffer.supply
- 🗂️ Multiple vectors per document now available for everyone
- 🔐 Audit logs with SIEM integration [opt-in, beta]
- ⚡️ Up to 30% faster AND queries
- 📄 Copy docs as markdown with token counts
- 3️⃣ Control term frequency's influence on BM25 scores with k3
- 💵 Query pricing reduced by up to 94%
- 🔤 Regex index for much faster
Regex,Glob, andIGlobfilters - 🍵 Up to 20% faster filtered FTS queries
- 💎 Use attribute values to influence full-text search ranking
- 📐 Boost result recency with distance ranking in full-text search
- 🗂️ Store and query multiple vectors per document [opt-in, beta]
- 🇬🇧 AWS eu-west-2 (London) region
- 🐡 turbopuffer.supply - the official tpuf store
- 🔡 FTS v2: up to 20x faster full-text search, now live for everyone
- ☯️ Up to 26% faster FTS queries on high-frequency terms with dynamic bit set encoding
- 🔌 turbopuffer MCP Server [beta]
- 🏷️ Match documents on any token with ContainsAnyToken
- 🔐 Permissions guide for document-level access control using filters
- 📝 remove_stopwords now defaults to
falsefor more predictable FTS behavior - 📊 Increase aggregate group_by limit to 10k
- 🧱 Redesigned inverted index structure for faster full-text search queries
- 📤 New object storage-native indexing queue for up to 10x faster queue time
- 🔦 kNN exact search for 100% recall on filtered vector search queries
- 🪣 Return a max number of search results per attribute value using limit.per
- 🇨🇦 AWS ca-central-1 (Montreal) region
- 🌏 Cross-region backups guide
- 🤝 Link multiple orgs to a single account for unified billing, SSO, and roles [opt-in, beta]
- 🏎️ FTS v2: up to 20x faster full-text search [opt-in, beta]
- 🔑
copy_from_namespacecan now encrypt with a different key into the destination - ✈️ Cross-region, cross-org copy_from_namespace for testing, backups, branching
- ⬆️ Max limit.total raised from 1,200 to 10,000
- ➕ Sum aggregate function
- 🔗 ContainsTokenSequence filter for full-text phrase matching
- 🔡 word_v3 tokenizer with Unicode-aware segmentation
- 🪭 ascii_folding option for full-text search
- ⏫ Rank by filter for full-text search
- 🧩 patch_by_filter
- 🔘 []bool support
- 🏎️ Improved performance for order-by queries
- 👁️ View indexing state in metadata API
- 📚 Read replicas for scalable read throughput (opt-in)
- 🔐 Cross-region PrivateLink connectivity
- 🏛️ FIPS-compliant AWS endpoints available for BYOC deployments
- 🧮 ANN v3: query 100B+ vectors with p99 of 200ms [opt-in, beta]
- 🚀 5x object storage throughput for faster cold queries and indexing
- 🔍 Prefix queries for full-text search
- 💧 Disable backpressure for large scale ingestions
- 🔐 Org-level option to enforce private networking
- 💎 Ruby client gem renamed from
turbopuffer-rubyto turbopuffer - 📝 2025 SOC 2 Type 2 audit report
- 🇮🇪 Ireland region
- 🟰 Eq operator for array attributes
- 🗂️ Grouped aggregates (facets)
- 🇰🇷 South Korea region
- 🇮🇳 India region
- 🔀 Any* filter operators for array attributes (e.g.
AnyLt,AnyLte,AnyGt,AnyGte)
- 🇸🇬 Singapore region
- 🇨🇦 Canada region
- 🕵️♀️ Private Service Connect + PrivateLink support
- 🎈 float type
- 🕳️ exclude_attributes query parameter
- 🪢 Regex filter operator
- 📋 Listing namespaces is now consistent
- 💎 Ruby API client GA release
- 👩🏽⚖️ Conditional writes
- 🔣 Multi-query API
- 📝 Contains and ContainsAny filter operators
- 🐍 Python async API client
- ☕ Java API client GA release (with improved ergonomics)
- 🦫 Go API client GA release
- 💸 Discount queries on large namespaces (80% discount after 32GB)
- 🐡 turbopuffer is generally available
- 🎊 v2 query API (unifies vector and full-text ranking)
- ✌️
Countaggregate function - 🦫 Go API client beta release
- ⏩ Up to 4x faster filtering and full-text search ranking
- 🥳 v2 write API (includes patch support)
- 💾 Up to 33% reduction in p90 query latency by using Direct I/O for local SSD cache
- 🔼
Maxoperator for full-text search - 🙅
Notfiltering parameter - ☀️ Warm cache endpoint
- ☁️ AWS us-east-2 region
- ☁️ Public AWS regions
- 🐜 f16 vector type (50% reduced storage and
query cost compared to
f32) - 🔢 i64 type (alongside existing
u64) - ⏰ datetime type
- 🔤 Custom tokenizers for full-text search
- 📝 ContainsAllTokens filter operator for full-text indexed attributes
- 📉 Up to 50% faster vector bulk upserts with client-side base64-encoding (default in new API clients)
- ❌ delete_by_filter
- ⚖️
Productoperator for weighted/boosted full-text search queries - 🌊 Add or update full-text indexes on existing attributes
- 🦾 ARM support on GCP (increases end-to-end indexing throughput by 70%)
- 🤖 Java API client beta release
- 🧮 Type checking for query filters against the namespace schema
- 📝 Blog post on Native filtering
- ⏰ Configurable consistency (strong or eventual) on queries (21ms -> 11ms p90 for 1M vectors)
- 🔒 Per-namespace Customer-Managed Encryption Key (CMEK) support
- 🔢 Order by attributes
- 🔄
/v1/vectorsdeprecated in favor of/v1/namespaces
- ✨ Support for Eq null and NotEq null filters
- 📑 All filter operators now supported in Filter-Only Search
- 📉 Faster queries during high write throughput (<100ms p90 consistent reads during 200+ WPS)
- 📉 Faster large namespaces (<100ms p50 on namespaces with 10M+ documents)
- 📉 Faster filters with 10-100k ids (50ms for 100k ids)
- 📕 Rewritten API docs, and new performance guide!
- 📈 Improved write throughput, up to 10x faster in some cases
- 📊 Time-series data in dashboard (and faster!)
- 📜 Allow schema changes in upsert