Qdrant

Databases & DataApache-2.0

A vector database and similarity search engine.

Latest v1.19.1 · by QdrantWritten in RustWebsiteqdrant/qdrantRSS

Release activity

Release activity — 11 releases across 11 days since Nov 25, 2025. Each cell is one day; darker means more releases that day. Nothing is recorded before Nov 25, 2025. Older weeks are hidden at this screen width.
JunJulAugSep
SundayNo releases on May 24, 2026No releases on May 31, 2026No releases on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 2026No releases on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 2026No releases on Aug 2, 2026No releases on Aug 9, 2026No releases on Aug 16, 2026No releases on Aug 23, 2026No releases on Aug 30, 2026No releases on Sep 6, 2026
MondayNo releases on May 25, 2026No releases on Jun 1, 2026No releases on Jun 8, 2026No releases on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 2026No releases on Jul 27, 2026No releases on Aug 3, 2026No releases on Aug 10, 2026No releases on Aug 17, 2026No releases on Aug 24, 2026No releases on Aug 31, 2026No releases on Sep 7, 2026
TuesdayNo releases on May 26, 2026No releases on Jun 2, 2026No releases on Jun 9, 2026No releases on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 2026No releases on Jul 14, 2026No releases on Jul 21, 2026No releases on Jul 28, 2026No releases on Aug 4, 2026No releases on Aug 11, 2026No releases on Aug 18, 2026No releases on Aug 25, 2026No releases on Sep 1, 2026No releases on Sep 8, 2026
WednesdayNo releases on May 27, 2026No releases on Jun 3, 2026No releases on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 2026No releases on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 2026No releases on Jul 22, 2026No releases on Jul 29, 20261 release on Aug 5, 2026No releases on Aug 12, 2026No releases on Aug 19, 2026No releases on Aug 26, 2026No releases on Sep 2, 2026
ThursdayNo releases on May 28, 20261 release on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 2026No releases on Jun 25, 2026No releases on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026No releases on Aug 6, 2026No releases on Aug 13, 2026No releases on Aug 20, 2026No releases on Aug 27, 2026No releases on Sep 3, 2026
FridayNo releases on May 29, 2026No releases on Jun 5, 2026No releases on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 20261 release on Jul 17, 2026No releases on Jul 24, 2026No releases on Jul 31, 2026No releases on Aug 7, 2026No releases on Aug 14, 2026No releases on Aug 21, 2026No releases on Aug 28, 20261 release on Sep 4, 2026
SaturdayNo releases on May 30, 2026No releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 2026No releases on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026No releases on Aug 8, 2026No releases on Aug 15, 2026No releases on Aug 22, 2026No releases on Aug 29, 2026No releases on Sep 5, 2026

11 releases since Nov 25, 2025

Changelog

v1.19.1

Latest
Added 1
  • Expose used CPU cores in /metrics (cpu_cores_used)
Changed 16
  • Speed up and saturate memory bandwidth in quantized scoring with prefetching
  • Rework and batch 4-bit TurboQuant SIMD implementation for better performance
  • Limit query plane allocations for better search performance
  • Improve L2 cosine preprocessing performance on AVX
  • Batch deletion checks for faster full scans
  • Batch searches in HNSW for faster search
Fixed 16
  • Make set replica state and abort transfer/resharding crash safe to prevent consensus desync
  • Make restart transfer operation crash safe to prevent consensus desync
  • Fix data consistency, flush CoW segments before building payload index
  • Fix Gridstore panic on new page after unsafe shutdown, repairs preexisting failures
  • On aborting resharding down, don't block consensus with deferred points for along time
  • Reject vector size larger than 65536
Security 1
  • Reject . and .. in collection names

From Qdrant

Change log

Improvements
Bug Fixes
Security
View originalPermalink
How v1.19.1 went

v1.19.0

Added 7
  • TurboQuant 4-bit as a datatype of primary vector storage to store only 4-bit quantized vectors and spare disk space on original vectors
  • Unify definition of memory usage strategy for collection components using "memory": "cold" / "cached" / "pinned" to define memory behavior for each individual collection component
  • Allow "match": {"prefix": "..."} in filter to match keywords by prefix when enabled in keyword index
  • Per-query IDF corpus for sparse vector search
  • Slice filtering condition for sliced scroll and deterministic sampling
  • Global quota API
  • Add routing token for deterministic read routes
Changed 10
  • Use batched reads in vector and payload storage
  • Utilize io_uring for payload storage
  • Lower default update queue length from 1M to 200
  • Enable single file mmap vector storage by default for immutable segments
  • Add option to explicitly disable BM25 stemmer and deprecate "none" hack
  • Respond HTTP 405 on cluster endpoints when in standalone mode
Fixed 4
  • Fixes for resharding abort logic consistency
  • Fix data loss when a payload index drop races the background segment flush
  • Fix abort resharding live-lock
  • Fix empty min_should with non-zero min_count matching everything

From Qdrant

Change log

Features :point_up:
Improvements :point_left:
Bug Fixes :facepunch:
Deprecations :point_down:
Web UI :open_hands:
View originalPermalink
How v1.19.0 went

v1.18.2

Changed 3
  • Log slow operations during shard WAL recovery
  • Clear cache of ID tracker after building a segment
  • Don't rebuild payload index if changing on_disk flag
Fixed 7
  • Fix potential infinite loop in optimizer when using multi vectors with prevent_unoptimized
  • Clean up unfinished segment optimizations on cancellation, don't load them on restart
  • Fix MatchAny with an empty list being rejected on integer index
  • Add timeout to shard snapshot streaming endpoint, drop connections not actively read from
  • Fix abort transfer with resharding not being idempotent
  • Fix reporting old progress in new snapshot transfers
  • Fix WAL lock error on Android platforms
Security 2
  • Fix REST auth whitelist bypass on specially crafted paths, resolve route before authorizing
  • Fix out of bound heap read with malicious snapshot by rejecting incorrect length

From Qdrant

Change log

Improvements
Bug Fixes
Security
View originalPermalink
How v1.18.2 went

v1.18.1

Changed 2
  • Refactor quantized multi-vector scorers for io_uring support
  • Validate vector dimensions before WAL write for async upserts
Fixed 13
  • Notify pending consensus ops on snapshot apply
  • Fix indexed integer range filter with float values
  • Fix {match: {except: []}} returning zero results with payload index
  • Fix empty vector panic
  • Fix TurboQuant heap memory under-reporting
  • Do not use unnecessary sequential mmaps
Security 1
  • Authorize request before accepting snapshot file upload

From Qdrant

Change log

Improvements
Bug Fixes
Security
View originalPermalink
How v1.18.1 went

v1.18.0

Added 5
  • Add TurboQuant quantization variant for 8x vector compression without recall penalty
  • Add API to create and delete named vectors in existing collections
  • Add deep memory reporting showing memory usage breakdown for storage components
  • Add low memory mode to force open everything on disk and minimize out of memory crashes on startup
  • Add strict mode parameter to reject updates when memory usage is high via max_resident_memory_percent
Changed 14
  • Use dynamic CPU pool for search workers to improve search performance with high IO wait
  • Use operation size based batching in shard transfers to achieve higher throughput
  • Reduce memory usage of immutable geo index by 7x
  • Don't stall update queue when waiting for deferred points
  • Use default timeout of 60 seconds for update requests and clean up long running update requests
  • Clear optimizer errors when collection update triggers optimizer recreation to allow recovery without restart
Fixed 25
  • Fix stop words always being lowercased over gRPC even if disabled
  • Fix datetime parsing for YYYY-MM-DDTHH:MM format
  • Fix IsEmpty condition on freshly rebuilt null index
  • Fix nested MatchTextAny not using full-text index
  • Fix geo circle hash bound checks
  • Fix phrase matching crossing string-array element boundaries
Removed 1
  • Fully remove RocksDB support

From Qdrant

Change log

Features 🏎️
Improvements 📏
Bug Fixes 🪺
Security 🕵️
Web UI 🍱
View originalPermalink
How v1.18.0 went

v1.17.1

Added 2
  • Defer point updates and efficiently apply and optimize points with prevent_unoptimized=true
  • Add request tracing ID into audit log
Changed 4
  • Make Gridstore flushes non-blocking to reduce search tail latencies
  • Improve performance of filtered search in case of singular payload value
  • Propagate WAL errors instead of panicking during loading of shards
  • Allow peer to bootstrap with used URI if empty
Fixed 13
  • Fix raw Vulkan name pointer type in GPU
  • Fix creation of uninitialized shard key with replication factor > 1 in tiered multi-tenancy workflow
  • Prevent min_should panic on large amount of conditions
  • Fix restore of cluster snapshots which creates unnecessary replicas in Partial state
  • Fix Server disconnected without sending a response error while performing concurrent ingestion
  • Fix lock for collection-level operations during shard transfer
Security 1
  • Force snapshot recovery from snapshot directory only

From Qdrant

Change log

Improvements
Bug fixes
Preview

This features are not officially released yet, but available in the build:

Edge
View originalPermalink
How v1.17.1 went

v1.17.0

Added 13
  • Relevance Feedback feature for search results
  • API for detailed report on optimization progress and stages
  • API for aggregated telemetry of the whole cluster
  • Unlimited update queue to gracefully smooth update spikes
  • Audit Access Logging
  • Weighted RRF for hybrid queries
Changed 5
  • Improve timeout handling on read operations
  • Improve timeout handling in update operations, prevent shard failures in case of timed out updates after WAL
  • Recover snapshot without creating intermediate files, greatly improves recovery time and disk usage
  • Recover snapshots directly into target file system to avoid expensive file movements
  • Disable old shard key format deprecated in 1.15.0
Fixed 2
  • Fix flush ordering to follow segment dependencies, prevents dataloss by CoW on flush interruption
  • Fix data race in stream records transfer potentially missing ongoing updates

From Qdrant

Change log

Features 🏋️
Improvements 🤸
Bug Fixes 🤹
Web UI :bento:
Qdrant Edge :hocho:

Qdrant Edge is an in-process version of Qdrant, which shares the same internals, storage format, and points API as the server version, but designed to work locally. Qdrant Edge is compatible with server version and it can read shard snapshots created by server version of Qdrant. More documentation available here.

Deprecations :warning:

  • Starting from v1.17.0 Qdrant changes response format for vector fields in gRPC interface. All official Qdrant clients should be already adopted to this change, so please make sure you upgrade your client libraries and check that you are not using deprecated fields. More info: https://github.com/qdrant/qdrant/pull/7183

  • Upcoming deprecations:

    • In Qdrant v1.18.x all deprecated search methods will be completely removed and won't be available even from old client libraries.
    • In Qdrant v1.17.x we will completely remove RocksDB support in favor of gridstore, that means that direct upgrade from v1.15.x into v1.17.x won't be possible. Please follow upgrade instructions and upgrade one minor version at a time to avoid unsupported storage errors. Note that Qdrant Cloud infrastructure automatically generates a proper upgrade steps, so you don't have to worry about that.
View originalPermalink
How v1.17.0 went

v1.16.3

Changed 4
  • Respect search and point retrieve timeout when trying to access segments
  • Respect telemetry timeout when fetching shard statistics
  • Log snapshot download duration and speed
  • Keep RocksDB support until 1.18.0 in development builds
Fixed 10
  • Fix WAL delta transfer corrupting replica after a previous full transfer was aborted
  • Fix flush losing changes on transient disk IO errors, potentially corrupting data
  • Fix incorrectly aborting shard transfers when dropping unrelated shard
  • Fix flush error in Gridstore, potentially corrupting data when quickly alternating inserts/deletes
  • Fix flush data race in Gridstore, potentially corrupting data when storage is cleared in parallel
  • Fix handling of collection names with weird characters, breaking snapshot transfers for example

From Qdrant

Change log

Improvements
Bug fixes
View originalPermalink
How v1.16.3 went

v1.16.2

Added 1
  • Add user agent to HTTP requests sent by Qdrant server
Changed 2
  • Improve request timeout handling for telemetry and metrics
  • Report `collection_indexed_only_excluded_points` metric if zero
Fixed 8
  • Fix critical WAL bug that could break consensus or cause data corruption on restart
  • Fix consensus crash when applying consensus snapshot with non-replicated collection
  • Fix panic during search on segments with empty HNSW graph
  • Fix shard resource cleanup when shard is replaced and prevent deadlock on small CPUs
  • Fix payload index storage still flushing after removal, preventing data corruption and IO errors on Windows
  • Fix Gridstore storage still flushing after wipe, preventing data corruption and IO errors
  • Fix Docker/WSL on Windows with bind mount corrupting storage
  • Fix `collections_vector_total` metric reporting -0.0 if there are no vectors

From Qdrant

Change log

Improvements
Bug fixes
View originalPermalink
How v1.16.2 went

v1.16.1

Added 3
  • Add 60s internal timeout for telemetry/metrics endpoints to prevent long hanging tasks
  • Add validation to restart shard transfer operation
  • Make timeout for inference requests user configurable
Changed 4
  • Make batch queries up to 3 times faster on full scans by reading each point only once
  • Actively migrate vector, payload and payload index storage from RocksDB into Gridstore on startup for better and more predictable performance
  • Defer Gridstore flushing to make flushing behavior consistent with all other storage components
  • Improve consensus WAL compaction logging to aid debugging
Fixed 7
  • Fix panic at startup on old clusters with user defined sharding, if not updated to Qdrant 1.15.5 first
  • Fix breaking Raft by killing node at specific time during consensus snapshot, preventing potential crash loop
  • Fix corrupting WAL with broken flush edge case after WAL is cleared or truncated
  • Fix incorrect rescoring default on mutable segments when using binary quantization
  • Spawn search/update tasks on the correct runtime, significantly reduce number of general/actix threads
  • Fix data race in shard transfers, wait on transfer to start before initializing shards
  • Fix incorrect log message when failing to read lock segment for some time

From Qdrant

Change log

Improvements
Bug fixes
View originalPermalink
How v1.16.1 went

More in Databases & Data

View all
Elasticsearch

The distributed search and analytics engine.

Elastic
Redis

In-memory data store used as a database, cache, and message broker.

Redis
Supabase

The open-source Firebase alternative.

Supabase
NocoDB

An open-source Airtable alternative that turns any database into a smart spreadsheet.

NocoDB
DBeaver

DBeaver release notes.

DBeaver Corp
PocketBase

A single-file backend with an embedded database, auth and file storage.

PocketBase

Discussion

If you publish Qdrant, you can claim this product by proving you administer its repository.