Change log

Features

• Multi-threaded optimizer - https://github.com/qdrant/qdrant/issues/30
• Allow to use UUID as point ID - https://github.com/qdrant/qdrant/pull/265
• Include payload and vector into search result https://github.com/qdrant/qdrant/issues/50
• Delete points by filter - https://github.com/qdrant/qdrant/issues/39
• Remove payload using filters - https://github.com/qdrant/qdrant/issues/269
• Individual endpoints for collection & point operations https://github.com/qdrant/qdrant/issues/32
• Limit segment size for better indexing performance - https://github.com/qdrant/qdrant/issues/135

Bug fixes

• Collection remove times-out while optimization is in process - https://github.com/qdrant/qdrant/issues/31

Deprecation

• Update Collection and Update Points APIs are deprecated. Please use individual endpoints for each type of update operations instead. E.g. use https://qdrant.github.io/qdrant/redoc/index.html?v=master#operation/set_payload to set payload

Breaking changes

• Due to changes related to UUID and configuration format, indexes created with the previous version of the engine are not compatible with the new version. The most straightforward migration approach would be to re-create collections with the latest version from scratch. Breaking changes are required to make our v1.0 release as legacy-free as possible. Hope for your understanding.

Bugfix for multiple architectures support

Change log

Bug Fixes

• Alias creation issue fixed https://github.com/qdrant/qdrant/issues/103
• Proper return code for operations with non-exiting collections https://github.com/qdrant/qdrant/issues/99
• Proper (this time) use of DYNAMIC_ARCH for support older CPU architecture as well as modern SIMD instructions in BLAS https://github.com/qdrant/qdrant/issues/78
• Fixed https://github.com/qdrant/qdrant/issues/77 - issue related to possible corruption of storage. Related changes:
  • Now all updates go through a dedicated thread to ensure proper update sequence
  • Each record now have it's individual version - to ensure nothing is mixed during a segment swap
  • Segments now have a failure lock - in case of failed update operation (e.g. not enough disk space) the failed segment will be locked for write until failed operation is (automatically) re-applied

Features

• It is now possible to retrieve payload along with search query in a single request - https://github.com/qdrant/qdrant/issues/50 Also field selection/exclusion works

Change log

Bug Fixes

• Fix point retrieve from copy-on-write proxy segment - https://github.com/qdrant/qdrant/pull/94 Related issue - https://github.com/qdrant/qdrant/issues/80
• Deadlock on parallel segment holder access - https://github.com/qdrant/qdrant/pull/91 Related issue - https://github.com/qdrant/qdrant/issues/75
• Handle corner case of limit = 0 in scroll API - https://github.com/qdrant/qdrant/issues/90
• Use DYNAMIC_ARCH=1 for OpenBLAS build. Related issue - https://github.com/qdrant/qdrant/issues/78

Change log

Improvements

• Actix upgraded to version 4.0beta, which allows to completely upgrade Tokio to 1.0+

Bug fix

• WAL now uses CBOR format, which properly handles some corner cases of payload interface format. The implementation is backward compatible

Change log

Improvements

• API endpoint for scrolling over points with filters https://qdrant.github.io/qdrant/redoc/index.html#operation/scroll_points

Bug fix

• Tokio updated to version ~1.7. It allows to separate blocking and worker threads. Fixes issue https://github.com/qdrant/qdrant/issues/34

Change log

• Payload schema included into collection info API
• Fixed redundant links building for range payload index in HNSW graph

Bugfix

• HNSW index and search is much faster
• Segment removal is now atomic
• Optimizer no longer loops on optimizing mmap segments

Change log

• Filtrable HNSW Index - optimizer will automatically build HNSW index for vectors after specified threshold. HNSW index takes into account indexed payload
• Dynamic collection configuration - each collection now has individual configuration settings. Configuration could be updated with an API request at any moment https://github.com/qdrant/qdrant/issues/16
• Query planner decides whether to use HNSW index or not based on estimated filtering cardinality
• Collection status indicator https://github.com/qdrant/qdrant/issues/17

Fix filtering issue with indexed fields

Change log

• Added Functionality to mark a payload field as "indexed".
• Payload indexation for number and keyword fields. Geo fields index is WIP.
• Segments are now automatically rebuilt into MMap and indexed segments if there are enough vectors stored.
• Search API filtering schema changed
  Old version

"filter": {
  "should": [
    {
      "match": {
        "key": "city",
        "keyword": "London"
      }
    }
  ]
}

New version

"filter": {
  "should": [
    {
      "key": "city",
      "match": {
        "keyword": "London"
      }
    }
  ]
}