Change8

Milvus

AI & LLMs

Python SDK for Milvus Vector Database

Latest: v2.6.927 releases4 breaking changes6 common errorsView on GitHub

Release History

v2.6.92 fixes2 features
Feb 10, 2026

This release enhances gRPC configuration and adds support for warmup parameters in FieldSchema. It also fixes critical bugs related to database context handling in SearchIteratorV2.

v2.6.81 fix1 feature
Jan 29, 2026

This release focuses on bug fixes, performance optimizations for search results, and improved gRPC error diagnostics. It also removes the dependency on grpcio-testing.

v2.6.711 fixes2 features
Jan 26, 2026

This release introduces support for semantic-highlighter and async list_persistent_segments, alongside numerous bug fixes addressing data type handling, memory usage, and database context management.

v2.6.67 fixes2 features
Dec 30, 2025

This release introduces a new benchmarking framework and Function SDK support, alongside numerous bug fixes related to boolean serialization, JSON parsing, and iterator handling.

v2.6.5Breaking4 fixes3 features
Dec 5, 2025

PyMilvus 2.6.5 introduces significant enhancements to AsyncMilvusClient, adds highlighter support for search, and fixes several bugs related to index creation and data handling. This release also includes a breaking change renaming 'Stage' to 'Volume'.

v2.5.18Breaking
Dec 2, 2025

This release introduces a breaking change by renaming 'Stage' to 'Volume' to improve clarity and consistency within the library.

v2.6.49 fixes7 features
Nov 26, 2025

This release introduces support for the TIMESTAMPTZ data type and significantly enhances BulkWriter capabilities for STRUCT and Geometry types. Numerous bug fixes address issues in connection handling, MilvusClient argument passing, and async operations.

v2.5.171 fix3 features
Nov 10, 2025

This release introduces enhancements for primary key insertion with autoID, support for serialized JSON inserts, and geometry support in the bulk writer. It also includes a fix for GCP stage configuration.

v2.6.3Breaking1 fix6 features
Oct 31, 2025

This release introduces major features including support for Array of Structs and Geometry data types, alongside manual L0 compaction control. A critical breaking change mandates JSON serialization for string data during insertion.

v2.5.163 fixes2 features
Sep 19, 2025

This release introduces support for the geo data type in core operations and includes several minor bug fixes and documentation improvements related to connection types and bulk import.

v2.6.22 fixes2 features
Sep 18, 2025

PyMilvus v2.6.2 introduces support for grouping by JSON fields and fixes several issues related to partial upsert operations. It also includes enhancements for OSS bucket connections.

v2.6.13 fixes2 features
Aug 29, 2025

This patch release (v2.6.1) introduces new features like enhanced bulk import capabilities and stage management support, alongside several bug fixes and performance enhancements like adding unixmsec to RPC calls.

v2.5.152 fixes2 features
Aug 21, 2025

This release introduces support for stageManager/stageFileManager and enhances bulkImport functionality. It also resolves a bug related to returning primary keys during upsert operations.

v2.6.0Breaking39 features
Aug 6, 2025

This release introduces comprehensive asynchronous client support via `AsyncMilvusClient` and significantly expands the API surface of `MilvusClient` with numerous database, partition, index, and search management features. The long-deprecated `Milvus` class has been removed.

v2.5.141 fix
Jul 21, 2025

This minor release primarily addresses a bug where functions were unnecessarily copied during CollectionSchema initialization.

v2.5.133 fixes
Jul 18, 2025

This patch release focuses on stability, fixing issues related to hybrid search parameters, connection reuse during concurrent MilvusClient initialization, and alias configuration cleanup upon connection failure.

v2.5.124 fixes
Jul 2, 2025

This release focuses on performance optimizations, bug fixes related to compaction and data handling, and general code quality improvements based on linting updates.

v2.5.115 fixes2 features
Jun 10, 2025

This release focuses on bug fixes related to schema alteration, upsert requests, and connection handling, alongside enhancements for analyzer configuration.

v2.5.102 fixes
May 23, 2025

This patch release (v2.5.10) addresses two specific bugs related to collection loading with resource groups and alias collision handling in MilvusClient.

v2.5.95 fixes
May 19, 2025

This patch release focuses on several bug fixes, including ensuring request-id propagation, correcting schema timestamp handling, and fixing parameter passing issues in collection loading methods.

v2.5.81 fix2 features
Apr 28, 2025

This release introduces support for running analyzers and configuring multi-analyzer parameters, alongside a minor fix for module spelling.

v2.5.75 fixes4 features
Apr 23, 2025

This release introduces new features like weighted reranker support and enhanced bulk import capabilities, alongside several bug fixes related to batch insertion, parameter validation, and deprecated type removal.

v2.5.64 fixes
Mar 21, 2025

This release focuses on stability, addressing several bugs related to index creation and database name handling. It also removes an unnecessary internal utility.

v2.5.58 fixes2 features
Mar 6, 2025

This release introduces schema update time verification for cache usage in insert/upsert operations and enhances the search iterator v2 with external filter support. Numerous bug fixes address issues in BulkWriter, connection handling, and API parameter types.

v2.4.153 fixes4 features
Feb 24, 2025

This release introduces several enhancements focused on schema caching for improved performance in insert, upsert, get, and delete operations, alongside various bug fixes including one for BulkWriter and gRPC thread management.

v2.5.46 fixes1 feature
Jan 22, 2025

This release simplifies search parameter structures, adds recall support to milvus_client, and fixes several bugs related to iterators and search parameter handling.

v2.4.143 fixes4 features
Jan 22, 2025

This release introduces several new management operations like partition and index management, adds database operation examples, and fixes bugs related to Hits field names and iterator mismatches during alias alteration. The release also enhances publishing security via trusted publisher adoption.

Common Errors

DataNotMatchException3 reports

DataNotMatchException in Milvus usually arises from a discrepancy between the data provided during insertion/upsertion and the schema defined for the collection (e.g., incorrect data type, missing required fields, or extra unexpected fields). To resolve this, carefully review your data against the collection schema – ensure data types align, all non-nullable fields have values (or default values are set), and no unexpected fields are being inserted.

ConnectionConfigException3 reports

The "ConnectionConfigException" in Milvus usually arises from incorrect or missing connection parameters such as host, port, secure, or URI when initializing the Milvus client; or shared library loading errors, like missing `libknowhere.so`. Double-check your connection parameters in your MilvusClient instantiation and ensure that the necessary shared libraries like `libknowhere.so` are installed and accessible in your environment or that Milvus dependencies are correctly set up using `pip install pymilvus[default]`. If using Milvus Lite, verify you're using compatible pymilvus version per the docs.

AioRpcError2 reports

AioRpcError in Milvus often indicates issues with network connectivity, server unavailability, or authorization problems when making gRPC calls. Ensure the Milvus server is running and reachable, and verify that your client has correct authorization credentials (e.g., valid username/password) when authentication is enabled. If the issue persists, examine server logs for detailed error messages to diagnose underlying problems.

MilvusException2 reports

"MilvusException" usually arises from invalid input parameters or schema definitions during operations like index creation, data insertion, or query execution. To fix it, carefully validate all input data types and values against the Milvus schema, and thoroughly inspect the error message for specific constraints violated, adjusting the code accordingly before retrying the operation. Consult Milvus documentation for appropriate data type and range specifications.

SchemaNotReadyException2 reports

The SchemaNotReadyException often arises when Milvus attempts to access collection metadata before it's fully initialized, especially after collection creation or server restarts. To fix this, ensure that the collection creation process is complete before performing further operations and introduce a retry mechanism with a short delay to allow the schema to become available. You can also explicitly call `collection.load()` before other operations.

ConnectionNotExistException1 report

The "ConnectionNotExistException" often arises from attempting to use a Milvus connection after it has been explicitly closed or garbage collected while other clients are still relying on it. Ensure each MilvusClient uses its own dedicated connection or manages a connection pool properly. Avoid prematurely closing the underlying connection object if other MilvusClient instances might still need it.

Related AI & LLMs Packages

Subscribe to Updates

Get notified when new versions are released

RSS Feed