mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
3c322c91e7
* Update to latest Azure.AI.*, OpenAI, and M.E.AI* Absorb breaking changes in Responses surface area * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/AgentWebChat/AgentWebChat.AgentHost/Utilities/ChatClientExtensions.cs * Update dotnet/samples/GettingStarted/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Program.cs Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Using patch to remove the model is necessary, updated the response client to actually use the the ForAgent --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
3c322c91e7
ยท
2025-12-16 12:41:20 +00:00
History
Agent Framework with OpenAI
These samples show how to use the Agent Framework with the OpenAI exchange types.
By default, the .Net version of Agent Framework uses the Microsoft.Extensions.AI.Abstractions exchange types.
For developers who are using the OpenAI SDK this can be problematic because there are conflicting exchange types which can cause confusion.
Agent Framework provides additional support to allow OpenAI developers to use the OpenAI exchange types.
| Sample | Description |
|---|---|
| Creating an AIAgent | This sample demonstrates how to create and run a basic agent with native OpenAI SDK types. Shows both regular and streaming invocation of the agent. |
| Using Reasoning Capabilities | This sample demonstrates how to create an AI agent with reasoning capabilities using OpenAI's reasoning models and response types. |
| Creating an Agent from a ChatClient | This sample demonstrates how to create an AI agent directly from an OpenAI.Chat.ChatClient instance using OpenAIChatClientAgent. |
| Creating an Agent from an OpenAIResponseClient | This sample demonstrates how to create an AI agent directly from an OpenAI.Responses.OpenAIResponseClient instance using OpenAIResponseClientAgent. |
| Managing Conversation State | This sample demonstrates how to maintain conversation state across multiple turns using the AgentThread for context continuity. |