agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into copilot/move-workflow-and-agent-samples

Browse Source
This commit is contained in:
Shawn Henry
2026-04-02 04:21:26 +00:00
Unverified
parent 12f6f82c18 628bb1af48
commit 733748c925
467 changed files with 12233 additions and 7020 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/02-agents/declarative/README.md
+3 -3
View File
@@ -68,7 +68,7 @@ Illustrates a basic agent using Azure OpenAI with structured responses.
**Key concepts**: Azure OpenAI integration, credential management, structured outputs
### 5. **OpenAI Responses Agent** ([`openai_responses_agent.py`](./openai_responses_agent.py))
### 5. **OpenAI Responses Agent** ([`openai_agent.py`](./openai_agent.py))
Demonstrates the simplest possible agent using OpenAI directly.
@@ -159,7 +159,7 @@ agent_factory = AgentFactory(
"MyProvider": {
"package": "my_custom_module",
"name": "MyCustomChatClient",
"model_id_field": "model_id",
"model_field": "model",
}
}
)
@@ -176,7 +176,7 @@ agent = agent_factory.create_agent_from_yaml_path(Path("custom_provider.yaml"))
This allows you to extend the declarative framework with custom chat client implementations. The mapping requires:
- **package**: The Python package/module to import from
- **name**: The class name of your SupportsChatGetResponse implementation
- **model_id_field**: The constructor parameter name that accepts the value of the `model.id` field from the YAML
- **model_field**: The constructor parameter name that accepts the value of the `model.id` field from the YAML
You can reference your custom provider using either `Provider.ApiType` format or just `Provider` in your YAML configuration, as long as it matches the registered mapping.