semantic-kernel
semantic-kernel copied to clipboard
microsoft
Integrate cutting-edge LLM technology quickly and easily into your apps
**Describe the bug** When attempting to use any of the new GA models in Azure OpenAI for Semantic Kernel Realtime, you're faced with an error **To Reproduce** Steps to reproduce...
### Motivation and Context SK has support for realtime-preview models; however, since they've gone to GA we have not added support for the latest library abstractions. This PR brings in...
Hi, I am developing an enterprise application where I need the AI agents (AzureAIAgent) to be deterministic (produce exactly same response to the same prompt and instruction) over multiple runs....
[SK version - 1.32.0] Unlike general metadata field with LLM prompts usage info which is available in `ChatMessageContent` objects, same is not available in the final response from the new...
**Describe the bug** When streaming agent responses via `Agent.InvokeStreamingAsync` that include function tool calls, the assistant entry Semantic Kernel adds to chat history concatenates the pre-tool-call text with the post-tool-call...
--- Feature request to support direct MCP integration in the .NET SDK --- **Current Integration Methods:** In .NET, MCP tools are converted into AI functions for use with semantic kernel...
When using `GetStreamingChatMessageContentsAsync` with function calls, the results are added to `ChatHistory` in order of completion rather than order of execution causing error when submitting history in subsequence "chats" to...
**Describe the bug** When calling SequentialOrchestration with invalid parameters, GetResultAsync() hangs indefinetly. **To Reproduce** ```c# using Microsoft.SemanticKernel; using Microsoft.SemanticKernel.Agents.Orchestration.Sequential; using Microsoft.SemanticKernel.Agents; using Microsoft.SemanticKernel.Agents.Runtime.InProcess; var builder = Kernel.CreateBuilder(); // intentionally bad...
**Describe the bug** When used in an Orchestration (tested with Parallel and Sequential), a ChatCompletionAgent without a description will hang indefinitely or time out (if timeout specified) without a response....
Llamasharp model inference, the GetStreamingChatMessageContentsAsync method does not pass the PromptExecutionSettings parameter, and will automatically terminate halfway through the reply. ``` using LLama; using LLama.Common; using LLamaSharp.SemanticKernel; using LLamaSharp.SemanticKernel.ChatCompletion; using...
