Skip to content

Releases: microsoft/semantic-kernel

python-1.24.0

11 Mar 22:54
285dc9e
Compare
Choose a tag to compare

Release Notes

New Features

Enhancements and Improvements

  • Python: Support AzureAIAgent agent_id instead of assistant_id by @moonbox3 in #10908

Python Package Updates

  • Python: Bump Python version to 1.24.0 for a release. by @moonbox3 in #10929

Full Changelog: python-1.23.1...python-1.24.0

dotnet-1.41.0

11 Mar 19:58
43326a2
Compare
Choose a tag to compare

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

This list of changes was auto generated.

vectordata-dotnet-9.0.0-preview.1.25161.1

11 Mar 19:14
43326a2
Compare
Choose a tag to compare

Changes:

python-1.23.1

07 Mar 19:27
3fc9864
Compare
Choose a tag to compare

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 Package Updates

New Contributors

Full Changelog: python-1.23.0...python-1.23.1

Python 1.23.0

06 Mar 21:07
b1a81e7
Compare
Choose a tag to compare

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.

New Features

  • Add sample to show how to retrieve existing azure ai agent definition by @moonbox3 in #10801

Enhancements and Fixes

Bug Fixes and Improvements

Python Package Updates

Full Changelog: python-1.22.1...python-1.23.0

python-1.22.1

03 Mar 12:38
0153073
Compare
Choose a tag to compare

Release Notes

Python Package Updates

Enhancements and Fixes

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

03 Mar 10:17
5d55c05
Compare
Choose a tag to compare

Changes:

  • 5d55c05 .Net: Use preview suffix for Agents abstractions (#10745)
  • 9ad9f2c .Net: ADR Samples Contribution Guidelines (#10526) [ #10168 ]
  • 4fdaf67 .Net: Sample Code Showcasing Usage of Reasoning Models in OpenAI and AzureOpenAI (#10558)

python-1.22.0

28 Feb 02:28
fd27470
Compare
Choose a tag to compare

Release Notes

New Features

  • Python: Agent get_response API by @TaoChenOSU in #10701

    We'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 and OpenAIAssistantAgent 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

Full Changelog: python-1.21.3...python-1.22.0

dotnet-1.40.0

28 Feb 01:30
5e8fc1e
Compare
Choose a tag to compare

Changes:

  • 0235f2b .Net: Adding preview package suffix to Agents.OpenAI. (#10719)
  • 9d746f6 .Net: Updated package version (#10717)
  • 9401760 .Net Agents: Update experimental meta-data for graduation (#10600)
  • de22689 .Net: Use Contoso endpoints (#10711)
  • 9048d15 .Net: Concept sample showing how to switch deployments based on functions being called (#10480) [ #10466 ]
  • 583db49 .Net: Update sample to demonstrate how hybrid AI orchestration can be used with Kernel (#10684)
  • bd22ea3 .Net: Add support for OpenAPI parameters defined with schema but without a type (#10682)

This list of changes was auto generated.

dotnet-1.39.0

25 Feb 17:39
2c73059
Compare
Choose a tag to compare

Changes:

  • 2c73059 .Net: Updated package version (#10677)
  • a24de53 .Net: Bump Microsoft.ML.Tokenizers and Microsoft.ML.Tokenizers.Data.Cl100kBase in /dotnet (#10665)
  • f5480e9 .Net: Fix Usage Tokens in AzureOpenAI Connector - Added UT + IT's (#10657) [ #10636 ]
  • 7b83ffd .Net: Add prompt execution settings to AutoFunctionInvocationContext (#10551)
  • 4c91cfd .Net: Adds Process Framework with Aspire demo (#10614)
  • f431685 .Net Agents - Update Templating Pattern (#10633)
  • ef56875 .Net: Added traces for OpenAI Assistant and Azure AI channels (#10630)
  • 5c7e759 .Net: Change Agents.Abstractions to depend on SemanticKernel.Abstractions instead of SemanticKernel.Core (#10574) [ #10571 ]
See More

This list of changes was auto generated.