Releases: qdrant/qdrant
Releases · qdrant/qdrant
v1.9.4
v1.9.3
Change log
Improvements
- #4165 - Handle Out-Of-Disk on insertions gracefully
- #3964 - Faster consensus convergence with batched updates
- #4301 - Deduplicate points by ID for custom sharding
Bug fixes
- #4307 - Fix overflow panic if scroll limit is usize::MAX
- #4322 - Fix panic with missing sparse vectors after recovery of corrupted storage
Web UI
- qdrant/qdrant-web-ui#183 - Notification for miss-configured collections
Full change log: https://github.com/qdrant/qdrant-web-ui/releases/tag/v0.1.26
v1.9.2
Change log
Improvements
- #4148 - Greatly improve proxy segment performance when a lot of changes are tracked
- #4176 - Speed up loading of large memory mapped segments
- #4205 - Use distinct gRPC types for shard replication and overwriting payload requests, existing clients remain compatible
- #4163 - Extend sparse vector benchmarks
Bug fixes
- #4206 - Fix potential deadlock with concurrent searches and snapshot creation
v1.9.1
v1.9.0
Change log
Features 🏎️
- #3477 - Implement and enable shard diff transfer, greatly improve shard transfer speed on node recovery
- #3777 - Role-based access control with JWT
- #3976, #4049, #4065 - Add support for byte vectors, represent your vectors as float32 or uint8
Improvements 🕵️
- #3420, #3938 - Greatly improve write performance while creating a snapshot of a large collection
- #3962, #3971 - Report pending optimizations awaiting an update operation in collection info
- #3998 - Improve
indexed_only
reliability on proxy shards - #3798 - Make shard diff transfer fall back to streaming records
- #3784 - Cancel shard transfers when the shard is deleted
- #4037 - Improve sparse vectors search performance by another 7%
- #3982 - Build Qdrant with a single codegen unit to allow better compile-time optimizations
- #4052 - Remove
vectors_count
from collection info because it is unreliable. Check usage of this field before upgrading - #3803 - Remove shard transfer method field from abort shard transfer operation
Bug fixes 💔
- #3990 - Fix potentially losing points on crash
- #4034 - Fix potentially losing points on segment flushing
- #4057 - Fix potentially losing points by improper moves between segments when recovering WAL
- #4058 - Fix segments not being flushed properly with rapid sequential optimizations
- #3995, #3996 - Fix read ordering of segments to prevent missing points just being moved
- #3975 - Fix consensus operations getting stuck if they timed out
- #3905 - Fix collection creation if files were left behind on disk
- #4029 - Fix collection deletions conflicting with concurrent collection creation
- #3991 - Fix arbitrary path traversal when uploading snapshots with created collection names
- #4033 - Do not allow symlinks in snapshot archives
- #4047 - Fix recommendation API for sparse vectors
- #3965 - Fix discovery search with sparse vectors over gRPC
- #3928 - Stabilize vector normalization, prevent renormalizing multiple times breaking data consistency
- #4054 - Fix incorrect ordering when using order_by across multiple nodes
- #4067 - Fix timeout being ignored when dropping segment data, potentially leaving them behind forever
- #3980 - Internally forward operations with
wait=true
during shard transfers - #3945 - Keep jemalloc only for amd64 and aarch64 to fix build failures
Dashboard 🍱
- qdrant/qdrant-web-ui#175 - Add page to generate RBAC JWT tokens
- qdrant/qdrant-web-ui#169 - Before saving payload changes, ask for confirmation with dialog showing diff
- qdrant/qdrant-web-ui#173 - Validate collection names
- Other changes
Thanks to @abhishek818 @RPallas92 @tellet-q @xzfc @ffuugoo @IvanPleshkov @agourlay @coszio @generall @timvisee for their contributions!
v1.8.4
v1.8.3
Bug fixes
Improvements
- #3837 - Improve error message when doing upsertion with malformed data
Dashboard
- qdrant/qdrant-web-ui#167 - Find similar points by payload key:value pair
- qdrant/qdrant-web-ui#166 - Fix find similar point ID not working in some cases
- qdrant/qdrant-web-ui#165 - Support 64-bit numbers
- Other changes
v1.8.2
v1.8.1
v1.8.0
Change log
Features 📅
- Add ability to order Scroll API results by payload value - #3493, #3533, #3562, #3540, #3589, #3726
- Add date time payload index to efficiently filter by date time ranges - #3395, #3516, #3549, #3578, #3622, #3729, #3730
- #3472 - Add API to check if a collection exists
- #3466 - Allow specifying a minimum number of conditions to match in payload filters
- #3548 - Improve
set_payload
API, adds ability to modify nested fields
Improvements 🏎️
- Sparse vector search performance improvements, making it 16x faster - #3464, #3275, #3327, #3348, #3347, #3368, #3393, #3413, #3424, #3527, #3560, #3609, #3619, #3605
- Improve CPU saturation, greatly speeding up indexing on high CPU systems - #3364, #3115
- Improve various payload indices
- Add new release artifacts to support more platforms
- Avoid re-indexing point if fields without an index are updated - #3611
- Refactor payload key parsing - #3674, #3697, #3709
- #3367 - Ensure consistency when an update request is dropped in the middle
- #3525 - Optimize MatchAny performance with a large number of values
- #3629, #3633, #3641 - Performance optimizations for empty payloads
- #2840, #3381 - Add a checksum for snapshot files
- #3374 - Improve "loss" function for discovery search
- #3255 - Add config property to set default shard transfer method
- #3380 - Add ability to selectively disable the range or lookup index for integer payloads to save memory
- #3555 - Report progress of ongoing shard transfers
- #3311 - Also report collection recovery progress in non-interactive terminals
- #3235 - Set custom thread priorities on Linux for better scheduling
- #3257, #3313 - Avoid logging of health and metrics APIs in access log
- #3418 - Report the timestamp of last seen error in cluster, helpful for debugging
- #3419 - Expose the git commit hash of the build at the root endpoint
- #3498 - Allow loading of segments to be stopped in the middle if cancelled
- #3552 - Expose request timing histogram for Prometheus in metrics endpoint
- #3581 - Report version in logs on startup
Bug fixes 🔂
- #3386 - Fix multiple vector updates on same point in batch not working
- #3512 - Expose
discover
endpoint statistics in the metrics - #3544 - Fix some REST endpoints not being usable with read-only API key
- #3592 - Fix internal proxy always forwarding successful requests three times
- #3423 - Return better suited status codes in the gRPC API
- #3387 - Disable large limit optimization for plain indices
- #3557, #3565 - Properly configure RocksDB options on all column families, reducing memory usage
- #3580 - Fix reading vector data out of bounds
- #3608 - Fix a potential zero division error in geo filter queries
- #3623 - Security patch for snapshot upload file name
Dashboard 🍱
- qdrant/qdrant-web-ui#153 - Add snapshots for demo collections
- qdrant/qdrant-web-ui#156 - Auto-complete required fields when inserting commands
- qdrant/qdrant-web-ui#155 - Add button to delete points
- qdrant/qdrant-web-ui#134 - Visualize discovery scores
- qdrant/qdrant-web-ui#160 - Fix vector visualisation with optional named vectors
- Other changes
Thanks to @AlexandruCihodaru @Florents-Tselai @Shylock-Hg @amietn @ding-young @Okabe-Rintarou-0 @JojiiOfficial @mrbusche @gabrieldemian @2k4sm @Anush008 @TuanaCelik @kwkr @neo773 @Dhanus3133 @KShivendu @joein @xzfc @ffuugoo @IvanPleshkov @agourlay @coszio @generall @timvisee for their contributions!