Releases: microsoft/semantic-kernel
dotnet-1.42.0
Changes:
- 842fa49 .Net: Version 1.42.0 (#11050)
- fb61cbc .Net: Processes UTs causing Build pipeline errors (#11008) [ #11019 ]
- d2f8ff6 .Net: Switch postgres and sqlserver to preview, and move experimental to only memory store artifacts. (#10974)
- f34bcf5 .Net MEVD: SqlServerVectorStore should accept a connection string to be thread safe (#11042)
- ea00f4f .Net: Sync to MEAI 9.3.0-preview.1.25114.11 (#10989)
- a01a31b .Net MEVD: Unify collection deletion and creation (#10958) [ #10882 ]
- 66f4cce .Net: Add functionality to create and import plugins with YAML functions (#10840)
- a0dce99 Added Feature to pass document to Mistral AI's CHAT Models (#10921)
- bf8a773 .Net: HuggingFace Connector Enhancement for Batch Embedding Generation (#10862) [ #10861 ]
- 4a15231 .Net: Allow HttpClient to be passed in for AzureOpenAI when building from s… (#10703)
See More
- c4de1ab .Net: Revert KernelAIFunction name separator using dash (#10827)
- 106c92c .Net: Fix Bedrock agent function calling complex type (#10985) [ #10982, #10925 ]
- 15b515e .Net: Make a few OpenAPI APIs non-experimental (#10978)
- 550648b .Net MEVD: Fix String mapping for SQL Server connector (#11005) [ #10975 ]
- 886e822 .Net: don't use a mutable static counter for tests that can run in parallel (#11004) [ #11001 ]
- 8c6250f .Net: Processes: Hook up uninitialization for Steps in Local Runtime (#10825) [ #10282 ]
- 1823554 .Net MEVD: More Conformance tests (#10944) [ #10194, #10882, #10883 ]
- 044cb33 .Net: Fix CodeQL errors (#10937)
- 6d377e1 .Net: scrub preceding cross region identifier in Amazon Bedrock model IDs (#10859) [ #10738, #10047 ]
- eb3de69 .Net: Bump DocumentFormat.OpenXml and System.IO.Packaging in /dotnet (#10906) [ #1863, #1884, #1862 ]
This list of changes was auto generated.
python-1.24.1
Release Notes
New Features
- Python: Introducing the Pinecone Connector by @eavanvalkenburg in #10886
Enhancements and Improvements
- Python: Improve test coverage by @rracanicci in #10681
- Python: Model dump json step info for Dapr step actor by @moonbox3 in #10946
Bug Fixes
Python Package Updates
- Python: Bump google-cloud-aiplatform from 1.82.0 to 1.83.0 in /python by @dependabot in #10901
- Python: Update websockets requirement from <15,>=13 to >=13,<16 in /python by @dependabot in #10902
- Python: Bump Python version to 1.24.1 and rc3 for a release by @moonbox3 in #10949
Full Changelog: python-1.24.0...python-1.24.1
python-1.24.0
Release Notes
New Features
- Add Bedrock agent retrieval samples in Python and .Net by @TaoChenOSU in #10857
- Python: Introducing the Faiss Connector by @eavanvalkenburg in #10810
Enhancements and Improvements
Python Package Updates
Full Changelog: python-1.23.1...python-1.24.0
dotnet-1.41.0
Changes:
- 43326a2 .Net: Updated package version for SK and MEVD (#10922)
- 056470c .Net Add mechanism to access http request options (#10888)
- 2ef5233 .Net: March 2025 VectorData updates (#10804)
- c00060f .Net: Make Bedrock agent clients required and public (#10899)
- ba9c17c .Net: Bump PdfPig from 0.1.9 to 0.1.10 in /dotnet (#10905)
- 6778ad3 .Net: Implement support for text embedding generation in AWS Bedrock (#10863) [ #10644 ]
- a36fa18 .Net: Bump Microsoft.Azure.Functions.Worker.Extensions.Http from 3.2.0 to 3.3.0 in /dotnet (#10903) [ #2901, #2894, #2940, #2936, #2930, #2907, #2906, #2898 ]
- 3162bc3 .Net: Bump Microsoft.AspNetCore.Mvc.Testing, Microsoft.Extensions.Configuration, Microsoft.Extensions.Configuration.Binder, Microsoft.Extensions.Configuration.EnvironmentVariables, Microsoft.Extensions.Configuration.Json and Microsoft.Extensions.Configuration.UserSecrets in /dotnet (#10904)
See More
- 3072da1 .Net: Apply a JSON converter for exceptions when serializing chat history (#10869)
- 774510c Fix Typos in ADR Documentation (#10768)
- 32f311e Add Bedrock agent retrieval samples in Python and .Net (#10857)
- b08f22c .Net: Bump DuckDB.NET.Data.Full from 1.1.3 to 1.2.0 in /dotnet (#10776)
- 85020e9 .Net: Bump Microsoft.OpenApi and Microsoft.OpenApi.Readers in /dotnet (#10663) [ #2020, #2018, #2013, #2012, #2011, #2010, #2007 ]
- 9c71640 .Net: Changes to support .NET9 formatting (#10838) [ #10716, #10741 ]
- 40a85d1 .Net: Remove EditorBrowsable(EditorBrowsableState.Never) from ChatMessageContent.Content property (#10847)
- d4363af .Net: Bump Markdig from 0.37.0 to 0.40.0 in /dotnet (#10774) [ #837, #842, #843, #844, #834, #835, #836, #826, #829, #831, #832, #828 ]
- 9347423 .Net: Updated User-Agent header for agent types (#10822)
- 7502712 .Net: Process Cloud Events - Publish Events Abstractions (#10477) [ #10328 ]
- 77e8a89 .Net: Fix some documentation issues (#10807)
- f8ee3ac .Net: Demo showing how to integrate MCP tools with Semantic Kernel (#10779)
- 7c8dccc .Net: Add missing Ollama Connector Aspire Friendly Extensions (#10775) [ #10532 ]
- 022f05e .Net: dotnet format issues with SDK 9.0 (#10741) [ #10715 ]
- b07ce3d .Net: Concept Samples Updates and Fixes (#10746)
- 04f5fbb .Net: Add Calendar write for Copilot Agent Plugin Calendar (#10622)
- bee063c .Net: Upgrade to latest ONNX Runtime GenAI (#10743)
This list of changes was auto generated.
vectordata-dotnet-9.0.0-preview.1.25161.1
python-1.23.1
Enhancements and Improvements
- Python: New samples added to use the auto_reduce flag in the ChatHistorySummarizationReducer and the ChatHistoryTruncationReducer classes by @saurabhvartak1982 in #10830
- Python: During Dapr step activation, perform model validate internally by @moonbox3 in #10841
Bug Fixes
- Python: fix for import without realtime extra by @eavanvalkenburg in #10851
Python Package Updates
- Python: Bump 1.23.1 by @eavanvalkenburg in #10856
New Contributors
- @saurabhvartak1982 made their first contribution in #10830
Full Changelog: python-1.23.0...python-1.23.1
Python 1.23.0
Release Notes
Realtime Clients!
We are super excited to release the experimental version of the RealtimeClients, now for OpenAI websockets and WebRTC and for Azure OpenAI over Websockets, see our blog and documentation for more info.
- Introducing Realtime Clients for OpenAI and Azure OpenAI by @eavanvalkenburg in #10127 and #10834
New Features
Enhancements and Fixes
- Move to a thinner wrap for Bedrock Agent in Python by @TaoChenOSU in #10740
- Improve Bedrock service setup docs by @TaoChenOSU in #10772
- Remove custom separator in Bedrock tool call fully qualified name by @TaoChenOSU in #10826
- Improve handling the Dapr process context by @moonbox3 in #10725
- Update Cross Language Test to get raw request and now raw response by @moonbox3 in #10799
- Improved chat history samples by @eavanvalkenburg in #10737
- Add embedding and text completion samples by @TaoChenOSU in #10797
Bug Fixes and Improvements
- Fix issues of Gemini parallel function call by @TaoChenOSU in #10813
Python Package Updates
- Bump google-cloud-aiplatform from 1.80.0 to 1.82.0 in /python by @dependabot in #10773
- Bump version by @eavanvalkenburg in #10835
Full Changelog: python-1.22.1...python-1.23.0
python-1.22.1
Release Notes
Python Package Updates
Enhancements and Fixes
- Cleanup ChatCompletionAgent concept samples by @moonbox3 #10726
- Allow OpenAIAssistant model id to pass into setup resources by @moonbox3 #10748
Bug Fixes and Improvements
- fixed vector dimension to 1536 by @cplemm #10749
- Don't store AzureAIInferenceChatCompletion response inner_content inside of item's text content by @moonbox3 #10747
New Contributors
Full Changelog: python-1.22.0...python-1.22.1
dotnet-1.40.1
python-1.22.0
Release Notes
New Features
-
Python: Agent
get_response
API by @TaoChenOSU in #10701We've simplified our APIs to make it easier to quickly get started with agents. You can now directly retrieve an agent response using:
response = await agent.get_response(chat_history)
This new API complements the existing invoke and invoke_stream methods you may already be using.
-
Python: Allow plugins via agent constructors. Update samples. by @moonbox3 in #10707
We've streamlined the way plugins and services can be added to agents. You no longer need to separately define a kernel and manually add plugins before constructing an agent. The simplified constructor looks like this:
agent = ChatCompletionAgent( service=AzureChatCompletion(), instructions="Answer questions about the world.", plugins=[SamplePlugin()], )
This update enhances usability as we approach our release candidate. The previous approach remains valid, but this new method offers improved simplicity. Please refer to the migration guide for details on updating to SK 1.22.0+.
The old way is still valid, but this is a much more streamlined approach.
-
Python: Add support for AutoGen's 0.2 ConversableAgent by @moonbox3 in #10607
Semantic Kernel Python now supports integration with AutoGen 0.2's
ConversableAgent
, enabling seamless use within the SK ecosystem:from autogen import ConversableAgent from semantic_kernel.agents.autogen.autogen_conversable_agent import AutoGenConversableAgent async def main(): cathy = ConversableAgent( "cathy", system_message="Your name is Cathy and you are a part of a duo of comedians.", llm_config={ "config_list": [ { "model": os.environ["OPENAI_CHAT_MODEL_ID"], "temperature": 0.9, "api_key": os.environ.get("OPENAI_API_KEY"), } ] }, human_input_mode="NEVER", # Never ask for human input. ) cathy_autogen_agent = AutoGenConversableAgent(conversable_agent=cathy) joe = ConversableAgent( "Joe", system_message="Your name is Joe and you are a part of a duo of comedians.", llm_config={ "config_list": [ { "model": os.environ["OPENAI_CHAT_MODEL_ID"], "temperature": 0.7, "api_key": os.environ.get("OPENAI_API_KEY"), } ] }, human_input_mode="NEVER", # Never ask for human input. ) joe_autogen_agent = AutoGenConversableAgent(conversable_agent=joe) async for content in cathy_autogen_agent.invoke( recipient=joe_autogen_agent, message="Tell me a joke about the stock market.", max_turns=3 ): print(f"# {content.role} - {content.name or '*'}: '{content.content}'") if __name__ == "__main__": asyncio.run(main())
-
Python: Introducing AzureCosmosDBforMongoDB store and collection by @eavanvalkenburg in #10609
-
Python: Introducing the Chroma Connector with the new vector store design by @eavanvalkenburg in #10678
-
Python: Introduce feature decorator to allow for experimental and release candidate decorator usage by @moonbox3 in #10691
Python Package Updates
- Python: Update boto3 requirement from ~=1.36.4 to >=1.36.4,<1.38.0 in /python by @dependabot in #10660
- Python: Bump Python version to 1.22.0 for a release. by @moonbox3 in #10718
Enhancements and Fixes
-
Python: Improve/Simplify the Assistant Agents by @moonbox3 in #10666
We’ve significantly enhanced our
AzureAssistantAgent
andOpenAIAssistantAgent
classes to improve scalability and flexibility. Developers now have direct access to the underlying client and assistant model configurations. Note: this update introduces breaking changes for those upgrading from versions prior to 1.22.0. Please consult our migration guide to assist with the transition. -
Python: Improve agent getting started samples by @TaoChenOSU in #10667
-
Python: improve feature decorator return type so it doesn't affect Pylance by @moonbox3 in #10704
-
Python: lazy create stores in integration tests by @eavanvalkenburg in #10705
Bug Fixes and Improvements
- Python: removed pyright until we have time to reevaluate typing setup by @eavanvalkenburg in #10670
- Python: resolving #10642 - public events fail to propagate by @drdrew42 in #10643
Full Changelog: python-1.21.3...python-1.22.0