freshcrate
Skin:/
Home > Databases > pymilvus

pymilvus

Python SDK for Milvus Vector Database

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

Python SDK for Milvus Vector Database

README

Milvus Python SDK

version Supported Python Versions Downloads Downloads Downloads

license Static BadgePython SDK for Milvus. To contribute code to this project, please read our contribution guidelines first. If you have some ideas or encounter a problem, you can find us in the Slack channel #py-milvus.

Compatibility

The following collection shows Milvus versions and recommended PyMilvus versions:

Milvus version Recommended PyMilvus version
1.0.* 1.0.1
1.1.* 1.1.2
2.0.* 2.0.2
2.1.* 2.1.3
2.2.* 2.2.15
2.3.* 2.3.7
2.4.* 2.4.X
2.5.* 2.5.X
2.6.* 2.6.X

Installation

You can install PyMilvus via pip or pip3 for Python 3.8+:

$ pip3 install pymilvus
$ pip3 install pymilvus[model] # for milvus-model
$ pip3 install pymilvus[bulk_writer] # for bulk_writer

You can install a specific version of PyMilvus by:

$ pip3 install pymilvus==2.4.10

You can upgrade PyMilvus to the latest version by:

$ pip3 install --upgrade pymilvus

FAQ

Q1. How to get submodules?

A1. The following command will get the protos matching to the generated files, for protos of certain version, see milvus-proto for details.

$ git submodule update --init

Q2. How to generate python files from milvus-proto?

A2.

$ make gen_proto

Q3. How to use the local PyMilvus repository for Milvus server?

A3.

$ make install

Q4. How to check and auto-fix the coding styles?

A4.

make lint
make format

Q5. How to set up pre-commit hooks to automatically check and fix the coding styles?

Once installed, the hooks will automatically run make format and make lint before each commit. If the checks fail, the commit will be aborted, and you'll need to fix the issues before committing again.

A5. Pre-commit hooks help ensure code quality by automatically running linting and formatting checks before each commit.

# Install pre-commit (if not already installed)
$ pip install pre-commit

# Install the git hook scripts
$ pre-commit install

Q7. How to run unittests?

A7

$ pip install ".[dev]"
$ make unittest

Q8. zsh: no matches found: pymilvus[model], how do I solve this?

A8

$ pip install "pymilvus[model]"

Documentation

Documentation is available online: https://milvus.io/api-reference/pymilvus/v2.4.x/About.md

Developing package releases

The commits on the development branch of each version will be packaged and uploaded to Test PyPI.

The package name generated by the development branch is x.y.z.rc, where is the number of commits that differ from the most recent release.

  • For example, after the release of 2.3.4, two commits were submitted on the 2.3 branch. The version number of the latest commit of 2.3 branch is 2.3.5.rc2.

  • For example, after the release of 2.3.4, 10 commits were submitted on the master branch. The version number of the latest commit of master branch is 2.4.0.rc10.

To install the package on Test PyPi, you need to append --extra-index-url after pip, for example:

$ python3 -m pip install --extra-index-url https://test.pypi.org/simple/ pymilvus==2.1.0.dev66

License

Apache License 2.0

Release History

VersionChangesUrgencyDate
v2.6.15## What's Changed * Add `get_replicate_info()` to `MilvusClient` and `AsyncMilvusClient` for reading replication checkpoint state. #3509 by @bigsheeper, backported in #3515. * Move Search logical-type handling to the shared type registry. #3482, backported in #3498. * Add the internal `TypeCapability` contract for shared type-specific operation bindings. #3531, backported in #3532. * Use the logical type registry in batch insert and upsert paths. #3517, backported in #3540. * Migrate deveHigh6/1/2026
v2.6.14## What's Changed * refactor: consolidate duplicated array element type mapping (#3401) by @pymilvus-bot in https://github.com/milvus-io/pymilvus/pull/3478 * feat(client): add internal data type metadata registry (#3475) by @pymilvus-bot in https://github.com/milvus-io/pymilvus/pull/3480 * feat: [2.6] add FieldOp helpers for array partial update operators by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/3492 * fix(client): reject oversized compaction target sizes (#3494) by @pymiHigh5/15/2026
v3.0.0## PyMilvus 3.0.0 for Milvus 3.0.0betaHigh5/7/2026
v2.6.12## What's Changed ### Bug Fixes * **fix: default to port 443 for https:// URIs in MilvusClient** ([#3372](https://github.com/milvus-io/pymilvus/pull/3372), [#3374](https://github.com/milvus-io/pymilvus/pull/3374)) by @pymilvus-bot — reported by @XuanYang-cn in [#3369](https://github.com/milvus-io/pymilvus/issues/3369) * **fix: remove duplicate timeout kwarg in Collection.\_\_init\_\_** ([#3371](https://github.com/milvus-io/pymilvus/pull/3371), [#3378](https://github.com/milvus-io/pymilvus/pHigh4/9/2026
v2.6.11## What's Changed ### Bug Fixes * **fix: pass address to GrpcHandler in ConnectionManager strategies** — fixed Milvus Lite local path broken since 2.6.10 ([#3321](https://github.com/milvus-io/pymilvus/pull/3321), [#3323](https://github.com/milvus-io/pymilvus/pull/3323)) by @XuanYang-cn * **fix: prevent "Cannot invoke RPC on closed channel" after connection recovery** ([#3326](https://github.com/milvus-io/pymilvus/pull/3326), [#3345](https://github.com/milvus-io/pymilvus/pull/3345)) bMedium3/27/2026
v2.6.10 ## What's Changed ### New Features - feat: add global cluster client support (#3264) - feat: add ConnectionManager to replace connections singleton for MilvusClient (#3307) ### Bug Fixes - fix: is_legal_ids() to accept negative int64 primary keys (#3281) - fix: avoid callLow3/13/2026
v2.6.9### Bug Fixes - **fix: pass context to `describe_collection` in `SearchIteratorV2`** ([#3271](https://github.com/milvus-io/pymilvus/pull/3271)) — Forward `kwargs` (including `context` carrying `db_name`) from `SearchIteratorV2.__init__` to `describe_collection`, matching the existing `QueryIterator` pattern. Without this fix, `SearchIteratorV2` always queries the `default` database, causing "can't find collection" errors for non-default databases. - **fix: unpack `_get_schema` tuple returnLow2/10/2026
v2.6.8 ## 🐛 Bug Fixes - **Parse dbname from uri** ([#3247](https://github.com/milvus-io/pymilvus/pull/3247)) ## 🔧 Enhancements - **Remove the usage of grpcio-testing** ([#3225](https://github.com/milvus-io/pymilvus/pull/3225)) - **Exclude data generation time from benchmark** ([#3246](https://github.com/milvus-io/pymilvus/pull/3246)) - **Optimize search result performance (Hit class, HybridHits init)** ([#3248](https://github.com/milvus-io/pymilvus/pull/3248)) - **Add channel_state and Low1/29/2026
v2.6.7## 🎉 New Features - **Support semantic-highlighter** ([#3180](https://github.com/milvus-io/pymilvus/pull/3180)) - **Support async client list_persistent_segments** ([#3207](https://github.com/milvus-io/pymilvus/pull/3207)) ## 🐛 Bug Fixes - **Pass parameters as keyword arguments to avoid incompatible issue of minio-py 7.2.19** ([#3171](https://github.com/milvus-io/pymilvus/pull/3171)) - **Float scalar datatype supports floating-point numbers** ([#3173](https://github.com/milvus-io/pyLow1/26/2026
v2.6.6 ## Features **1. Add comprehensive benchmarking framework (#3151)** **2. Add Function SDK support (#3080)** ## Enhancements **1. Change highlight query keyword (#3143)** ## Bug Fixes 1. **fix: Keep boolean serialization as uppercase for e2e compatibility** (#3168) 2. **fix: Preserve False boolean values in SCANN index parameters** (#3165) 3. **fix: Use json to parse deep recursive json when orjson failed** (#3156) 4. **fix: Fix search params in orm search iterator** (#3162Low12/30/2025
v2.6.5# PyMilvus 2.6.5 Release Notes ## Enhancements **1. Added comprehensive features to `AsyncMilvusClient` including: (#3108)** **2. Enhanced error messages when AsyncMilvusClient fails to connect. (#3102)** ## Bug Fixes 1. **fix: AsyncMilvusClient.search supports EmbeddingList** (#3101) 2. **fix: AsyncMilvusClient.create_index supports nested fields** (#3100) 3. **fix: Use deepcopy for struct_schema in add_field** (#3105) 4. **fix: Error when function or function_score fetch emLow12/5/2025
v2.5.18## What's Changed * [cherry-pick] Breaking change: Rename Stage to Volume by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/3111 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.5.17...v2.5.18Low12/2/2025
v2.6.4## Highlights ### 1. Support for TimestampTZ Data Type (Introduced in Milvus v2.6.6) PyMilvus now supports the TIMESTAMPTZ data type, allowing you to store and query timestamps with time zone information. ```python from pymilvus import MilvusClient, DataType client = MilvusClient(uri="http://localhost:19530") # 1. Define Schema with TimestampTZ schema = MilvusClient.create_schema() schema.add_field("id", DataType.INT64, is_primary=True) schema.add_field("timestamp", DataType.TIMESTALow11/26/2025
v2.5.17## What's Changed * enhance: allow user insert pk when autoid is enabled by @sunby in https://github.com/milvus-io/pymilvus/pull/3006 * Support insert serialized json (#3024) by @sunby in https://github.com/milvus-io/pymilvus/pull/3032 * fix: Bulk writer support geometry by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/3053 * GCP supports using stage by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/3063 **Full Changelog**: https://github.com/milvus-io/pymilvusLow11/10/2025
v2.6.3## Highlights ### 1. Support for Array of Structs PyMilvus now supports array of structs data types, allowing you to store and query complex nested data structures. ```python from pymilvus import MilvusClient, DataType client = MilvusClient(uri="http://localhost:19530") schema = client.create_schema(auto_id=False) schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True) schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=128) struct_sLow10/31/2025
v2.5.16## What's Changed * support geo data type for insert,query and search for pymilvus 2.5 by @Yinwei-Yu in https://github.com/milvus-io/pymilvus/pull/2943 * fix: [25]Fix the existing version fmt by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2959 * fix: [2.5]Passing unknown req.is_refresh to wait by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2965 * [cherry-pick] support connectType if use oss-bucket by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/2Low9/19/2025
v2.6.2## What's Changed * fix: Refine partial upsert to preserve unspecified fields (#2955) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2970 * fix: Correct validation logic for partial upsert requests (#2974) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2977 * feat: support group by json field(#2884) by @MrPresent-Han in https://github.com/milvus-io/pymilvus/pull/2980 * enhance: [2.6]Run actions when push to repo to enable cov compare by @XuanYang-cn in https://gitLow9/18/2025
v2.6.1## What's Changed * Avoid describe_collection when query by ids by @yhmo in https://github.com/milvus-io/pymilvus/pull/2930 * bulkImport add objectUrls/token paramster & add example use by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/2934 * support stageManager & stageFileManager by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/2935 * fix: Fix the existing version fmt by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2960 * enhance: Add unixmsec in eLow8/29/2025
v2.5.15## What's Changed * Compatible with the default behavior of free on the cloud by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/2912 * fix: Return new pk value for upsert when autoid=true by @yhmo in https://github.com/milvus-io/pymilvus/pull/2915 * fix: Multiple cherry-picks from master by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2906 * bulkImport add objectUrls/token paramster & add example use by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/29Low8/21/2025
v2.6.0## New Features 1. Add APIs in MilvusClient * enhance: add describe and alter database in MilvusClient by @smellthemoon in https://github.com/milvus-io/pymilvus/pull/2433 * enhance: support milvus-client iterator by @MrPresent-Han in https://github.com/milvus-io/pymilvus/pull/2461 * enhance: Enable resource group api in milvus client by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2513 * enhance: add release_collection, drop_index, create_partition, drop_partition, load_partiLow8/6/2025
v2.5.14## What's Changed * fix: Aviod coping functions when init CollectionSchema by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2903 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.5.13...v2.5.14Low7/21/2025
v2.5.13## What's Changed * fix: Fix hybrid search params check by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2890 * fix: [25]Concurrent init MilvusClient don't reuse connections by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2897 * fix: [25]Tidy alias configs when connect fails by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2899 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.5.12...v2.5.13Low7/18/2025
v2.5.12## What's Changed * fix: [2.5]add retry in compact for compatibility with old Milvus server in order to reduce describecollection by @JsDove in https://github.com/milvus-io/pymilvus/pull/2842 * enhance: optimize perf for search&&query under large topk(#2848) by @MrPresent-Han in https://github.com/milvus-io/pymilvus/pull/2855 * fix: remove validation for collection_id in manual_compaction method by @JsDove in https://github.com/milvus-io/pymilvus/pull/2857 * fix: update manual_compaction metLow7/2/2025
v2.5.11## What's Changed * fix:[2.5] wrong marshal field schema prarams case alter collection failed by @aoiasd in https://github.com/milvus-io/pymilvus/pull/2811 * Add bulkinsert example for parquet file by @yhmo in https://github.com/milvus-io/pymilvus/pull/2813 * fix: [2.5] Pass correct number of params of _prepare_row_upsert_request by @congqixia in https://github.com/milvus-io/pymilvus/pull/2819 * enhance: Multiple Cherry picks from master by @XuanYang-cn in https://github.com/milvus-io/pymilvLow6/10/2025
v2.5.10## What's Changed * fix: load collection with resource group by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2801 * fix: avoid collision on aliases in MilvusClient (#2716) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2799 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.5.9...v2.5.10Low5/23/2025
v2.5.9## What's Changed * fix: Pass request-id in metadata per API (#2766) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2779 * fix: Handle collection schema update timestamp (#2777) by @congqixia in https://github.com/milvus-io/pymilvus/pull/2778 * fix: remove default replica_number in load_collection (#2782) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2786 * fix: Extend iterable instead of assign load_fields by @XuanYang-cn in https://github.com/milvus-io/pymilvLow5/19/2025
v2.5.8## What's Changed * feat: [2.5] support run analyzer by @aoiasd in https://github.com/milvus-io/pymilvus/pull/2748 * feat:[2.5] suppoprt multi analyzer params (#2747) by @aoiasd in https://github.com/milvus-io/pymilvus/pull/2751 * fix: Correct module misspell and patch for submodule by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2753 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.5.7...v2.5.8Low4/28/2025
v2.5.7## What's Changed * enhance: Add force_drop parameter to drop_role method for role deletion by @SimFG in https://github.com/milvus-io/pymilvus/pull/2706 * weighted reranker to allow skip score normalization by @zhengbuqian in https://github.com/milvus-io/pymilvus/pull/2709 * fix: Retry batch insert will use changed entites if enabled Nul… by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2714 * enhance: change flush default backoff (#2707) by @XuanYang-cn in https://github.com/mLow4/23/2025
v2.5.6## What's Changed * fix: Remove field check in create_index (#2677) by @sunby in https://github.com/milvus-io/pymilvus/pull/2685 * fix: Fix failure of create multiple indices for a field by @sunby in https://github.com/milvus-io/pymilvus/pull/2687 * fix: Remove not useful SequenceIterator by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2700 * fix: db_name overwritten by empty string (#2678) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2702 **Full ChangelogLow3/21/2025
v2.5.5## What's Changed * enhance: Add schema update time verification to insert and upsert to use cache by @JsDove in https://github.com/milvus-io/pymilvus/pull/2596 * enhance: enable describe_replica api in milvus client (#2541) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2599 * enhance: get and delete to use schema cache by @JsDove in https://github.com/milvus-io/pymilvus/pull/2607 * feat: add external filter func for search iterator v2 by @PwzXxm in https://github.com/milvus-Low3/6/2025
v2.4.15## What's Changed * enhance: Add schema update time verification to insert and upsert to use cache by @JsDove in https://github.com/milvus-io/pymilvus/pull/2597 * enhance: enable describe_replica api in milvus client (#2541) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2600 * enhance: get and delete to use schema cache by @JsDove in https://github.com/milvus-io/pymilvus/pull/2608 * Fix BulkWriter bug for Array type field by @yhmo in https://github.com/milvus-io/pymilvus/pullLow2/24/2025
v2.5.4## What's Changed * enhance: simplify the structure of search_params(#2507)(#2537)(#2540) by @smellthemoon in https://github.com/milvus-io/pymilvus/pull/2550 * enhance: use trusted publisher and remove deprecated by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2548 * enhance: support recalls for milvus_client by @chasingegg in https://github.com/milvus-io/pymilvus/pull/2553 * fix: use correct primary field name in Hits by @czs007 in https://github.com/milvus-io/pymilvus/pull/25Low1/22/2025
v2.4.14## What's Changed * enhance: [2.4]add database operation example by @JsDove in https://github.com/milvus-io/pymilvus/pull/2518 * enhance: [2.4] add release_collection, drop_index, create_partition, drop_partition, load_partition and release_partition by @brcarry in https://github.com/milvus-io/pymilvus/pull/2528 * enhance: [2.4] add example code for create_collection, drop_collection, load_collection, release_collection, create_index, drop_index, create_partition, drop_partition, load_partitiLow1/22/2025
v2.5.3## What's Changed * enhance: add search iterator v2 by @PwzXxm in https://github.com/milvus-io/pymilvus/pull/2524 * enhance:refine search iter v2 warning by @PwzXxm in https://github.com/milvus-io/pymilvus/pull/2527 * enhance: add release_collection, drop_index, create_partition, drop_partition, load_partition and release_partition by @brcarry in https://github.com/milvus-io/pymilvus/pull/2529 * fix: fix search iter v2 limit compatibility by @PwzXxm in https://github.com/milvus-io/pymilvus/pLow1/2/2025
v2.5.2## What's Changed * fix: [2.5] await conn.describe_collection in async client's query by @brcarry in https://github.com/milvus-io/pymilvus/pull/2502 * enhance: [2.5]add alter properties example by @JsDove in https://github.com/milvus-io/pymilvus/pull/2505 * fix: grant ManualCompact api doesn't work (#2396) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2509 * fix: [2.5] fix privilege typo by @shaoting-huang in https://github.com/milvus-io/pymilvus/pull/2512 * enhance: Enable rLow12/26/2024
v2.4.13## What's Changed * fix: [2.4] await conn.describe_collection in async client's query by @brcarry in https://github.com/milvus-io/pymilvus/pull/2501 * enhance: [2.4]add alter properties example by @JsDove in https://github.com/milvus-io/pymilvus/pull/2506 * fix: grant ManualCompact api doesn't work (#2396) by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2508 * fix: [2.4] fix privilege typo by @shaoting-huang in https://github.com/milvus-io/pymilvus/pull/2511 * enhance: Enable rLow12/26/2024
v2.5.1## New Features ### Support AsyncIO (EXPERIMENTAL) * feat: asyncio support by @brcarry in https://github.com/milvus-io/pymilvus/pull/2459 Introducing the native asyncio client in PyMilvus: `AsyncMilvusClient`. While only a subset of APIs is currently supported, this marks a significant step forward for PyMilvus. Enjoy exploring it! ```python import asyncio from pymilvus import MilvusClient, AsyncMilvusClient, DataType async def main(): URI = "./milvus.db" async_clienLow12/23/2024
v2.4.12## What's Changed * fix: [2.4] RuntimeWarning: coroutine 'Channel.close' was never awaited when closing async client by @brcarry in https://github.com/milvus-io/pymilvus/pull/2498 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.4.11...v2.4.12Low12/23/2024
v2.4.11## New Features ### Support AsyncIO (EXPERIMENTAL) * feat: asyncio support by @brcarry in https://github.com/milvus-io/pymilvus/pull/2459 Introducing the native asyncio client in PyMilvus: `AsyncMilvusClient`. While only a subset of APIs is currently supported, this marks a significant step forward for PyMilvus. Enjoy exploring it! ```python import asyncio from pymilvus import MilvusClient, AsyncMilvusClient, DataType async def main(): URI = "./milvus.db" async_clienLow12/20/2024
v2.4.10## What's Changed * Corrected grammar and consistency in error messages (#2289) by @czs007 in https://github.com/milvus-io/pymilvus/pull/2330 * enhance: Update the template expression proto to improve transmission efficiency by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2336 * Use filter_params for milvus client by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2321 * fix insertto avoid describe collection on every insert call by @zhengbuqian in https://github.comLow11/26/2024
v2.5.0New features: - Report cost in the dml and dql request by @SimFG in https://github.com/milvus-io/pymilvus/pull/2055 - feat: Support major compaction in ManualCompaction by @wayblink in https://github.com/milvus-io/pymilvus/pull/2015 - Support Milvus Lite by @junjiejiangjjj in https://github.com/milvus-io/pymilvus/pull/2073 - Enable set_properties and describe_database api by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2082 - Allowing search iterator on sparse float vector fielLow11/26/2024
v2.4.9## What's Changed * Improve embedding retrieval performance by @yhmo in https://github.com/milvus-io/pymilvus/pull/2290 * fix: Passing messages to code in ParamError (#2304) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2305 * Supports filling elements through templates for expression by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2308 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.4.8...v2.4.9Low10/29/2024
v2.4.8## What's Changed * fix: upsert rows when set autoid==true fail(#2286) by @smellthemoon in https://github.com/milvus-io/pymilvus/pull/2287 * Upgrade the bulkWriter cloud API call from v1 to v2 by @lentitude2tk in https://github.com/milvus-io/pymilvus/pull/2246 * enhance: Enable bulkwriter to support import v2 (#2295) by @bigsheeper in https://github.com/milvus-io/pymilvus/pull/2296 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.4.7...v2.4.8Low10/12/2024
v2.4.7## What's Changed * enhance: Make load parameter naming normal (#2243) by @congqixia in https://github.com/milvus-io/pymilvus/pull/2244 * Add hybrid_search for MilvusClient by @czs007 in https://github.com/milvus-io/pymilvus/pull/2259 ## Bug fixes: * fix: move page_retain_order to the same level as radius by @PwzXxm in https://github.com/milvus-io/pymilvus/pull/2250 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.4.6...v2.4.7Low9/25/2024
v2.4.6## New Features * Bulkinsert supports importing binlog by @yhmo in https://github.com/milvus-io/pymilvus/pull/2223 * enhance: upsert support autoid (#2173) by @smellthemoon in https://github.com/milvus-io/pymilvus/pull/2224 * enhance: Support load with Field Partial load by @congqixia in https://github.com/milvus-io/pymilvus/pull/2227 * feat: add page_retain_order param during search with offset by @PwzXxm in https://github.com/milvus-io/pymilvus/pull/2230 * feat: support the mmap_enable paLow8/30/2024
v2.4.5## New features * feat: Support clustering compaction by @wayblink in https://github.com/milvus-io/pymilvus/pull/2220 ## Enhancements * Export indexed rows for describe_index (#2148) by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2149 * Refine the error message for type mismatches during data insertion (#2156) by @xiaocai2333 in https://github.com/milvus-io/pymilvus/pull/2157 * Add database operations to MilvusClient (#2152) by @ashkrisk in https://github.com/milvus-io/pyLow8/9/2024
v2.3.8## Bug fixes * fix: rename_collection not apply in current db(#1959) by @smellthemoon in https://github.com/milvus-io/pymilvus/pull/1961 * fix: Update versions in readme to latest by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/1978 * fix: Remove the dependency of server_name to others by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/1981 **Full Changelog**: https://github.com/milvus-io/pymilvus/compare/v2.3.7...v2.3.8Low8/2/2024
v2.4.4## New Features * Allowing search iterator on sparse float vector field by @zhengbuqian in https://github.com/milvus-io/pymilvus/pull/2105 * Accept list of single row scipy.sparse object as input for insert/search by @zhengbuqian in https://github.com/milvus-io/pymilvus/pull/2112 * Support float16/bfloat16/sparse vector for bulkwriter by @yhmo in https://github.com/milvus-io/pymilvus/pull/2128 ## Enhancements * enhance: print search result more elegantly (#2123) by @longjiquan in https://Low6/20/2024
v2.4.3## What's Changed * support the report value in the dml and dql request by @SimFG in https://github.com/milvus-io/pymilvus/pull/2092 * enhance: Expand grpcio version to latest by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2096 ## Bug fixes: * fix sparse: accpet int/float wrapped in string by @zhengbuqian in https://github.com/milvus-io/pymilvus/pull/2095 * fix the str function of the extra list by @SimFG in https://github.com/milvus-io/pymilvus/pull/2098 **Full ChangeLow5/17/2024
v2.4.2## What's Changed * Support milvuslite by @junjiejiangjjj in https://github.com/milvus-io/pymilvus/pull/2075 * Make bulk_writer's requirments optional (#2086) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2087 * enhance: Enable set_properties and describe_database api by @weiliu1031 in https://github.com/milvus-io/pymilvus/pull/2084 ## Bug fixes * fix: Remove params for property vars by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2069 * change sparse relateLow5/14/2024
v2.4.1## What's Changed ### Bug fixes * Fix float16_example and bfloat16_example by @czs007 in https://github.com/milvus-io/pymilvus/pull/1993 * Use wrong placeholder type for bf16 and float16 by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2012 * Restrict input/search type for vector fields (#2025) by @XuanYang-cn in https://github.com/milvus-io/pymilvus/pull/2029 * Fix import array via bulkwriter (#2035) by @bigsheeper in https://github.com/milvus-io/pymilvus/pull/2036 * Pass offLow4/29/2024
v2.4.0### Milvus 2.4.0-rc.1 related scenario-based features: Milvus has released version 2.4.0-rc.1. This version of pymilvus incorporates the new features introduced in Milvus 2.4.0-rc.1 - **New GPU Index named [CAGRA](https://docs.rapids.ai/api/raft/nightly/cpp_api/neighbors_cagra/)** Thanks to NVIDIA's contribution, this new GPU index provides a 10x performance boost, especially for batch searches. Please refer to the sample code in `examples/example_gpu_cagra.py` - **Multi-vector and hLow3/20/2024
v2.3.7MilvusClient provides a simple and easy-to-use alternative to the legacy ORM approach. It adopts a purely functional approach to simplify interactions with the server. Each MilvusClient establishes a gRPC connection to the server you specified. To set up multiple connections, you can create multiple MilvusClient instances. # Install & Update You can run the following command to install the latest PyMilvus or update your PyMilvus to this version. ``` pip install --upgrade pymilvus==v2.3.7 Low3/13/2024

Dependencies & License Audit

Loading dependencies...

Similar Packages

milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN searchv2.6.18
LMForge-End-to-End-LLMOps-Platform-for-Multi-Model-AgentsAI Agent Development Platform - Supports multiple models (OpenAI/DeepSeek/Wenxin/Tongyi), knowledge base management, workflow automation, and enterprise-grade security. Built with Flask + Vue3 + LangCv1.1.2
vector-graph-ragGraph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.v0.1.3
ai-news-scraperAI News Scraper & Semantic Search: A Python application that scrapes news articles, uses GenAI to generate summaries and identify topics, and provides semantic search capabilities through vector embed2.9.7
OllamaRAG🤖 Build a smart AI assistant that learns from any website using a Retrieval-Augmented Generation framework with local models powered by Ollama.main@2026-06-06

More from milvus-io

milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search

More in Databases

milvusMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search
WeKnoraLLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
ai-real-estate-assistantAdvanced AI Real Estate Assistant using RAG, LLMs, and Python. Features market analysis, property valuation, and intelligent search.
alibabacloud-adb20211201Alibaba Cloud adb (20211201) SDK Library for Python