Milvus

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](https://github.com/milvus-io/milvus/pull/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](https://github.com/milvus-io/milvus/pull/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](https://github.com/milvus-io/milvus/pull/232)

- **New index types**

Start supporting new experimental index types such as `SPTAG-KDT`, `SPTAG-BKT`, `RNSG` and `IVFPQ`. [SPTAG438](https://github.com/milvus-io/milvus/pull/438) [RNSG#554](https://github.com/milvus-io/milvus/pull/554) [IVFPQ#324](https://github.com/milvus-io/milvus/pull/324)

- **Index test reports**

Provide performance [test reports](https://github.com/milvus-io/milvus/tree/master/docs) 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](https://github.com/milvus-io/milvus/pull/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](https://github.com/milvus-io/milvus/pull/414)

Bug fixes

- Solved the issue of increased memory usage during vector queries. [335](https://github.com/milvus-io/milvus/pull/335)

- Double the transmission speed of search results to the client application through the following updates to gRPC:

- Optimize messages.
- Change the API of generated code.
- Remove compression.

- Python SDK

- Divide the storage of search result ids and distances into separate arrays, which reduces the API response time.
- Add a new option to retrieve a specific target vector in search results: `id = results.id_array[i][j], distance = results.distance_array[i][j]`.
- Add a new option for looping over arrays, which takes much less time if `nq` and `topk` is large.

>> for id_list, dis_list in zip(results.id_array, results.distance_array):
>> for id, dis in zip(id_list, dis_list):
>> print("id={}, distance={}".format(id, dis))


- Java SDK

- Add keepalive and idleTimeout settings when connecting to Milvus server.
- Now users can retrieve search result ids and distances separately through `getResultIdsList` and `getResultDistancesList` with better performance, or they can retrieve them together as a list of `QueryResult` objects through `getQueryResultsList`.

- C++ SDK

- Now C++ SDK uses shared library.
- Add README file.

- Enhance the search performance of `IVF_SQ8H`.

- Hotfix: Search failed: Table file doesn't exist.
- Add Japanese README.
- Change config parameter default value.

In this release, following functions are added or improved.

- Solve more queries more memory usage issue.
- Solve searching vectors slower and slower.
- Add GPU searching threshold to control GPU execution trigger point.
- Support Pure GPU mode for IVFSQ8 and IVFFlat.
- Allow CPU to build the index.
- Speed up project compilation.

In this release, following functions are added or improved.

New Feature:

Add new index IVFSQ8 Hybrid.
Add preload data on system startup phase.
Add new Java SDK
Remove API: DeleteByDate
Improvement:

Improve result merge performance
Detailed release information, please check CHANGELOG.md