milvus-0.10.2

Release date：2020-8-15

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.10.2	0.2.14	0.8.4	0.4.4

Improvements

• Improved IVF search performance when both nq and nprobe are large. #2653

Fixed issues

• Inaccurate calculation of the memory allocated for index files. #2890
• Search result sets based on IVF_PQ index with IP metric are incorrectly merged in situations where multiple segments are produced for the inserted data. #2952
• The server crashes if you set cache.cache_size smaller than the size of an index file in a multi-GPU scenario. #3012
• Search result sets based on IP metric are incorrectly merged, if you insert vectors to multiple partitions in Mishards. #3133

See CHANGELOG for more information.

milvus-0.10.1

Release date：2020-7-20

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.10.1	0.2.14	0.8.3	0.4.3

Fixed issues

• Occasionally, the result count does not match the query count. #2578
• IVF_PQ does not support IP on GPU-enabled Milvus. #2585
• Milvus reports "illegal instruction" when running on some legacy CPUs. #2598
• Updated the range of HNSW settings. #2637
• Milvus processes crash when building an index. #2642
• The default ANNOY settings do not match the settings specified in the document. #2649
• Milvus does not respond under a stress test. #2692
• The precision of the returned vectors is incorrect in an HTTP interface. #2752
• The upper limit of nprobe is incorrect on the GPU-enabled Milvus. #2767
• The number of the vectors changes occasionally after building an index. #2768

See CHANGELOG for more information.

milvus-0.8.1

Release date：2020-6-22

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.8.1	0.2.10	0.7.0	0.3.0

Fixed issues

• Index files are missing after a compact operation. #1997
• Too many files are opened when metric_config.enable_monitor is set to true. #2264
• The server hangs when multiple clients query different collections at the same time. #2266
• nlist set by the user may not take effect. #2399
• Deleted vectors are still found in GPU-enabled Milvus. #2450

See CHANGELOG for more information.

milvus-0.10.0

Release date：2020-6-15

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.10.0	0.2.13	0.8.2	0.4.2

Compatibility changes

• Updates the Milvus configuration file. #2510

Improvements

• Optimizes the index building performance when many small segments exist. #2373
• FAISS is upgraded to 1.6.3. #2381
• Optimizes dropping collection performance when too many partitions exist. #2394
• Optimizes the implementation of k-selection algorithm for GPU-enabled Milvus. #2466

Fixed issues

• The search performance degrades on Milvus 0.9.1. #2429

See CHANGELOG for more information.

milvus-0.9.1

Release date：2020-5-29

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.9.1	0.2.12	0.8.1	0.4.1

Fixed issues

• In a multi-partition situation, data is inserted twice after the server reboots. #2378
• A cudaMalloc failure occurs with GPU IVF index when nq (number of queries) is high. #2395.
• Deleted vectors are still found in GPU-enabled Milvus. #2450

See CHANGELOG for more information.

milvus-0.9.0

Release date：2020-5-15

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.9.0	0.2.11	0.8.0	0.4.0

New features

• Checks the CPU instruction set, GPU driver version, and CUDA version, when Milvus starts up. #2054 #2111
• Prevents multiple Milvus instances from accessing the same Milvus database at the same time. #2059
• Supports log file rotating. #2206
• Suspends index building when a search request comes in. #2283

Improvements

• Refactors log output. #221
• Upgrades OpenBLAS to improve Milvus' performance. #1796
• Unifies the vector distance calculation algorithms among FAISS, NSG, HNSW, and ANNOY. #1965
• Supports SSE4.2 instruction set. #2039
• Refactors the configuration files. #2149 #2167
• Uses Elkan K-means algorithm to improve the IVF index performance. #2178

Fixed issues

See CHANGELOG for more information.

API changes

Added methods

C++	Python	Java	Go
HasPartition	has_partition	hasPartition	HasPartition

Changed methods

	C++	Python	Java	Go
Earlier than v0.9.0	DescribeCollection	describe_collection	describeCollection	DescribeCollection
v0.9.0	GetCollectionInfo	get_collection_info	getCollectionInfo	GetCollectionInfo

	C++	Python	Java	Go
Earlier than v0.9.0	CountCollection	count_collection	getCollectionRowCount	CountCollection
v0.9.0	CountEntities	count_entities	countEntities	CountEntities

	C++	Python	Java	Go
Earlier than v0.9.0	ShowCollections	show_collections	showCollections	ShowCollections
v0.9.0	ListCollections	list_collections	listCollections	ListCollections

	C++	Python	Java	Go
Earlier than v0.9.0	ShowCollectionInfo	collection_info	showCollectionInfo	ShowCollectionInfo
v0.9.0	GetCollectionStats	get_collection_stats	getCollectionStats	GetCollectionStats

	C++	Python	Java	Go
Earlier than v0.9.0	DescribeIndex	describe_index	describeIndex	DescribeIndex
v0.9.0	GetIndexInfo	get_index_info	getIndexInfo	GetIndexInfo

	C++	Python	Java	Go
Earlier than v0.9.0	ShowPartitions	show_partitions	showPartitions	ShowPartitions
v0.9.0	ListPartitions	list_partitions	listPartitions	ListPartitions

	C++	Python	Java	Go
Earlier than v0.9.0	GetEntitiesByID	get_vectors_by_ids	getVectorsByIds	GetVectorsByID
v0.9.0	GetEntityByID	get_entity_by_id	getEntityByID	GetEntityByID

	C++	Python	Java	Go
Earlier than v0.9.0	GetIDsInSegment	get_vector_ids	getVectorIds	GetEntityIDs
v0.9.0	ListIDInSegment	list_id_in_segment	listIDInSegment	ListIDInSegment

	C++	Python	Java	Go
Earlier than v0.9.0	N/A	search_in_files	searchInFiles	N/A
v0.9.0	N/A	search_in_segment	DELETED	N/A

	C++	Python	Java	Go
Earlier than v0.9.0	DeleteByID	delete_by_id	deleteByIds	DeleteByID
v0.9.0	DeleteEntityByID	delete_entity_by_id	deleteEntityByID	DeleteEntityByID

	C++	Python	Java	Go
Earlier than v0.9.0	PreloadCollection	preload_collection	preloadCollection	PreloadCollection
v0.9.0	LoadCollection	load_collection	loadCollection	LoadCollection

	C++	Python	Java	Go
Earlier than v0.9.0	FlushCollection and Flush	flush	flush and flushAsync	Flush
v0.9.0	Flush	UNCHANGED	UNCHANGED	UNCHANGED

	C++	Python	Java	Go
Earlier than v0.9.0	CompactCollection and Compact	compact	compact and compactAsync	Compact
v0.9.0	Compact	UNCHANGED	UNCHANGED	UNCHANGED

	C++	Python	Java	Go
Earlier than v0.9.0	Connect	connect	connect	Connect
v0.9.0	UNCHANGED	DELETED	UNCHANGED	UNCHANGED

	C++	Python	Java	Go
Earlier than v0.9.0	Connected	connected	isConnected	IsConnected
v0.9.0	UNCHANGED	DELETED	UNCHANGED	UNCHANGED

	C++	Python	Java	Go
Earlier than v0.9.0	Disconnect	disconnect	disconnect	Disconnect
v0.9.0	UNCHANGED	DELETED	UNCHANGED	UNCHANGED

milvus-0.8.0

Compatibility

Milvus version	Python SDK version	Java SDK version	Go SDK version
0.8.0	0.2.10	0.7.0	0.3.0

New features

• ANNOY index support

  Added support for ANNOY index type. Refer to our documentation for more information. #261

• Vector deletion

  Added support to delete one or multiple vectors for more index types. #1655 #1660 #1661 #1849

  Including: Flat/IVFlat/IVFPQ/IVFSQ8/IVFSQ8H/NSG/HNSW/ANNOY

Enhancements

• Added new metric SuperStructure and SubStructure in HTTP module. #1784

Bug fixes

• Limited the maximum number of partitions to 4096. #1276
• Forbidden to create partition with name _default. #1762
• Resolved the issue that concurrent operations from multiple clients cause system crash. #1789
• Resolved the issue that some raw vectors are missed when the raw data file size is larger than 2GB. #1883

milvus-0.7.1

New features

• Added new distance metrics, including substructure and superstructure, for the FLAT index type. These metrics are used for substructure and superstructure search of chemical structures.#1603.

Enhancements

• Improved the performance of the compact operation. #1619
• Improved search performance using CPU, especially for scenarios with multiple, concurrent connections. #267
• Improved the search performance when nq is less than the number of threads in the CPU. #1690
• Milvus performs a combined search for same search requests from multiple clients, thus significantly improving search speed. #1728
• Upgraded Mishards to 0.7.1. #1698

Bug fixes

Refer to CHANGELOG for details.

milvus-0.7.0

New features

• Vector deletion
  Added support to delete one or multiple vectors. If you performed vector deletion on a collection, later search operations for this collection are limited to part of the index types, including FLAT, IVFLAT, IVFSQ8, etc. Milvus is planned to support other index types in the upcoming versions.#861

• Get vector by ID
  Added support to get vector data by ID. #861

• Flush and compact
  Added support to flushing and compaction. You can configure flushing at an interval or manual flushing to avoid data loss. If some vectors are deleted from a segment, the space taken by the deleted vectors cannot be released automatically. You can compact segments in a collection to release space. #861 #1426

• Change Milvus server configurations during runtime
  Added support to update Milvus server configurations during runtime. You can use Milvus clients to update the parameters. Changes to some parameters take effect immediately without restarting Milvus. #665

• Write-Ahead logging (WAL)
  Added support for WAL, which significantly improves the reliability of data operations. You can configure WAL settings in the Milvus server configuration file (server_config.yaml). #830

• RESTful API
  Added RESTful API. Refer to RESTful API Readme for more information.

• Go SDK
  Added Go SDK. Refer to https://github.com/milvus-io/milvus-sdk-go for more information.

• HNSW index support
  Added support for HNSW index type. Refer to Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs for more information about HNSW. #853

• Jaccard/Hamming/Tanimoto distance support
  Added support for Jaccard distance, Hamming distance, and Tanimoto distance. #823

• Pushgateway support in Prometheus
  Added support for Pushgateway in Prometheus. Pushgateway makes it possible for short-lived, batch metrics to be acquired by Prometheus. #813

• AVX 512
  Added support for AVX 512 instruction set. Milvus theoretically supports all CPUs with AVX 512. #1122

Changes

• Interface updates for index creation and vector search
  Starting from Milvus 0.7.0, part of the Milvus client parameters for index creation and vector search use JSON strings as values.

• Milvus server configuration file updates
  Starting from Milvus 0.7.0, the Milvus server configuration file (server_config.yaml) is updated to 0.2 with parameter changes.

• Term updates
  Starting from Milvus 0.7.0, Table is named as Collection in Milvus.

Bug fixes

• Resolved the issue that duplicate IDs may be generated when inserting vector data using auto-generated IDs. #1508

milvus-0.6.0

New features

• CPU-only Milvus

  Milvus v0.6.0 provides Docker images for both CPU-only and GPU support Milvus. Milvus compilation on Docker is also supported on machines with or without GPU. #192

• Table partitioning

  Add table partitioning funtion to secure fast query performance for incremental data. Partitioning APIs are added to Python, Java and C++ SDK to support partition creation, vector insertion into a specified partition and query against a specified partition, etc. #245

• Experimental features

  The experimental features in Milvus are still under development and subject to change. They may contain unknown errors, and are intended for testing and user feedback gathering.

  • Mishards

    Propose Mishards, a Milvus sharding middleware, as the distributed deployment solution. Mishards provides unlimited extension of memory and computation capacity through request forwarding, read/write splitting, horizontal scalability and dynamic extension. #232

  • New index types

    Start supporting new experimental index types such as SPTAG-KDT, SPTAG-BKT, RNSG and IVFPQ. SPTAG#438 RNSG#554 IVFPQ#324

• Index test reports

  Provide performance test reports for IVFFLAT, IVFSQ8 and IVFSQ8H indexes.

Improvements

• Milvus internal FAISS

  In addition to original FAISS, Milvus has made deep optimizations to increase query performance and support more index types such as IVFSQ8H. Now this part of internal FAISS is open sourced. #585

• Multiple GPUs for index building

  Support index building by multiple GPUs to reduce index building and overall query time. You can specify multiple GPUs for index building process through Milvus configuration parameter build_index_resources. #414

Bug fixes

• Solved the issue of increased memory usage during vector queries. #335