agent/agent-framework
1
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

Python: [BREAKING] Remove deprecated Python OpenAI/Azure AI surfaces (#4990)

Browse Source 
* [BREAKING] Remove deprecated Python OpenAI/Azure AI surfaces

Also clean up follow-on docs, environment guidance, package metadata, and lab test stability.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix deleted semantic-kernel sample links

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address PR review feedback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* improve foundry language

* Fix A2A Foundry sample regression

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Eduard van Valkenburg
2026-03-31 22:36:21 +02:00
committed by GitHub
Unverified
parent a5eacbbe65
commit 3a49b1d6dd
144 changed files with 669 additions and 18739 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/01-get-started/README.md
+7
View File
@@ -9,6 +9,13 @@ concepts of **Agent Framework** one step at a time.
pip install agent-framework --pre
```
Set the required environment variables:
```bash
export FOUNDRY_PROJECT_ENDPOINT="https://your-project-endpoint"
export FOUNDRY_MODEL="gpt-4o" # optional, defaults to gpt-4o
```
## Samples
| # | File | What you'll learn |
python/samples/02-agents/chat_client/README.md
+12 -18
View File
@@ -15,22 +15,19 @@ This folder contains examples for direct chat client usage patterns.
`built_in_chat_clients.py` starts with:
```python
asyncio.run(main("openai_chat"))
asyncio.run(main("openai_responses"))
```
Change the argument to pick a client:
- `openai_chat`
- `openai_responses`
- `openai_assistants`
- `openai_chat_completion`
- `anthropic`
- `ollama`
- `bedrock`
- `azure_openai_chat`
- `azure_openai_responses`
- `azure_openai_responses_foundry`
- `azure_openai_assistants`
- `azure_ai_agent`
- `azure_openai_chat_completion`
- `foundry_chat`
Example:
@@ -42,22 +39,19 @@ uv run samples/02-agents/chat_client/built_in_chat_clients.py
Depending on the selected client, set the appropriate environment variables:
**For Azure clients:**
**For Azure OpenAI clients (`azure_openai_responses` and `azure_openai_chat_completion`):**
- `AZURE_OPENAI_ENDPOINT`: Your Azure OpenAI endpoint
- `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`: The name of your Azure OpenAI chat deployment
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your Azure OpenAI responses deployment
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The Azure OpenAI deployment used by the sample
- `AZURE_OPENAI_API_VERSION` (optional): Azure OpenAI API version override
- `AZURE_OPENAI_API_KEY` (optional): Azure OpenAI API key if you are not using `AzureCliCredential`
**For Azure OpenAI Foundry responses client (`azure_openai_responses_foundry`):**
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your Azure OpenAI responses deployment
**For Azure AI agent client (`azure_ai_agent`):**
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI project endpoint
- `AZURE_AI_MODEL_DEPLOYMENT_NAME`: The name of your model deployment (used by `azure_ai_agent`)
**For Foundry client (`foundry_chat`):**
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: The Foundry deployment used by the sample
**For OpenAI clients:**
- `OPENAI_API_KEY`: Your OpenAI API key
- `OPENAI_CHAT_MODEL`: The OpenAI model for `openai_chat` and `openai_assistants`
- `OPENAI_CHAT_MODEL`: The OpenAI model for `openai_chat_completion`
- `OPENAI_RESPONSES_MODEL`: The OpenAI model for `openai_responses`
**For Anthropic client (`anthropic`):**
python/samples/02-agents/chat_client/built_in_chat_clients.py
+17 -42
View File
@@ -6,13 +6,9 @@ from random import randint
from typing import Annotated, Any, Literal
from agent_framework import Message, SupportsChatGetResponse, tool
from agent_framework.azure import (
AzureOpenAIAssistantsClient,
)
from agent_framework.foundry import FoundryChatClient
from agent_framework.openai import OpenAIAssistantsClient
from agent_framework.openai import OpenAIChatClient, OpenAIChatCompletionClient
from azure.identity import AzureCliCredential
from azure.identity.aio import AzureCliCredential as AsyncAzureCliCredential
from dotenv import load_dotenv
from pydantic import Field
@@ -26,31 +22,25 @@ This sample demonstrates how to run the same prompt flow against different built
chat clients using a single `get_client` factory.
Select one of these client names:
- openai_chat
- openai_responses
- openai_assistants
- openai_chat_completion
- anthropic
- ollama
- bedrock
- azure_openai_chat
- azure_openai_responses
- azure_openai_responses_foundry
- azure_openai_assistants
- azure_ai_agent
- azure_openai_chat_completion
- foundry_chat
"""
ClientName = Literal[
"openai_chat",
"openai_responses",
"openai_assistants",
"openai_chat_completion",
"anthropic",
"ollama",
"bedrock",
"azure_openai_chat",
"azure_openai_responses",
"azure_openai_responses_foundry",
"azure_openai_assistants",
"azure_ai_agent",
"azure_openai_chat_completion",
"foundry_chat",
]
@@ -71,55 +61,41 @@ def get_client(client_name: ClientName) -> SupportsChatGetResponse[Any]:
from agent_framework.amazon import BedrockChatClient
from agent_framework.anthropic import AnthropicClient
from agent_framework.ollama import OllamaChatClient
from agent_framework.openai import OpenAIResponsesClient
# 1. Create OpenAI clients.
if client_name == "openai_chat":
return FoundryChatClient()
if client_name == "openai_responses":
return OpenAIResponsesClient()
if client_name == "openai_assistants":
return OpenAIAssistantsClient()
return OpenAIChatClient()
if client_name == "openai_chat_completion":
return OpenAIChatCompletionClient()
if client_name == "anthropic":
return AnthropicClient()
if client_name == "ollama":
return OllamaChatClient()
if client_name == "bedrock":
return BedrockChatClient()
# 2. Create Azure OpenAI clients.
if client_name == "azure_openai_chat":
return FoundryChatClient(credential=AzureCliCredential())
if client_name == "azure_openai_responses":
return FoundryChatClient(credential=AzureCliCredential(), api_version="preview")
if client_name == "azure_openai_responses_foundry":
return OpenAIChatClient(credential=AzureCliCredential())
if client_name == "azure_openai_chat_completion":
return OpenAIChatCompletionClient(credential=AzureCliCredential())
if client_name == "foundry_chat":
return FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
if client_name == "azure_openai_assistants":
return AzureOpenAIAssistantsClient(credential=AzureCliCredential())
# 3. Create Azure AI client.
if client_name == "azure_ai_agent":
return FoundryChatClient(credential=AsyncAzureCliCredential())
raise ValueError(f"Unsupported client name: {client_name}")
async def main(client_name: ClientName = "openai_chat") -> None:
async def main(client_name: ClientName = "openai_responses") -> None:
"""Run a basic prompt using a selected built-in client."""
client = get_client(client_name)
# 1. Configure prompt and streaming mode.
message = Message("user", text="What's the weather in Amsterdam and in Paris?")
stream = os.getenv("STREAM", "false").lower() == "true"
print(f"Client: {client_name}")
print(f"User: {message.text}")
# 2. Run with context-managed clients.
if isinstance(client, OpenAIAssistantsClient | AzureOpenAIAssistantsClient | FoundryChatClient):
if isinstance(client, FoundryChatClient):
async with client:
if stream:
response_stream = client.get_response([message], stream=True, options={"tools": get_weather})
@@ -134,7 +110,6 @@ async def main(client_name: ClientName = "openai_chat") -> None:
)
return
# 3. Run with non-context-managed clients.
if stream:
response_stream = client.get_response([message], stream=True, options={"tools": get_weather})
print("Assistant: ", end="")
@@ -147,7 +122,7 @@ async def main(client_name: ClientName = "openai_chat") -> None:
if __name__ == "__main__":
asyncio.run(main("openai_chat"))
asyncio.run(main("openai_responses"))
"""
python/samples/02-agents/context_providers/azure_ai_search/README.md
+12 -8
View File
@@ -49,14 +49,14 @@ Run `az login` if using Entra ID authentication.
**Common (both modes):**
- `AZURE_SEARCH_ENDPOINT`: Your Azure AI Search endpoint (e.g., `https://myservice.search.windows.net`)
- `AZURE_SEARCH_INDEX_NAME`: Name of your search index
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_AI_MODEL_DEPLOYMENT_NAME`: Model deployment name (e.g., `gpt-4o`, defaults to `gpt-4o`)
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL`: Model deployment name (e.g., `gpt-4o`, defaults to `gpt-4o`)
- `AZURE_SEARCH_API_KEY`: _(Optional)_ Your search API key - if not provided, uses DefaultAzureCredential
**Agentic mode only:**
- `AZURE_SEARCH_KNOWLEDGE_BASE_NAME`: Name of your Knowledge Base in Azure AI Search
- `AZURE_OPENAI_RESOURCE_URL`: Your Azure OpenAI resource URL (e.g., `https://myresource.openai.azure.com`)
- **Important**: This is different from `AZURE_AI_PROJECT_ENDPOINT` - Knowledge Base needs the OpenAI endpoint for model calls
- **Important**: This is different from `FOUNDRY_PROJECT_ENDPOINT` - Knowledge Base needs the OpenAI endpoint for model calls
### Example .env file
@@ -64,8 +64,8 @@ Run `az login` if using Entra ID authentication.
```env
AZURE_SEARCH_ENDPOINT=https://myservice.search.windows.net
AZURE_SEARCH_INDEX_NAME=my-index
AZURE_AI_PROJECT_ENDPOINT=https://<resource-name>.services.ai.azure.com/api/projects/<project-name>
AZURE_AI_MODEL_DEPLOYMENT_NAME=gpt-4o
FOUNDRY_PROJECT_ENDPOINT=https://<resource-name>.services.ai.azure.com/api/projects/<project-name>
FOUNDRY_MODEL=gpt-4o
# Optional - omit to use Entra ID
AZURE_SEARCH_API_KEY=your-search-key
```
@@ -127,7 +127,8 @@ AZURE_OPENAI_RESOURCE_URL=https://myresource.openai.azure.com
```python
from agent_framework import Agent
from agent_framework.azure import AzureAIAgentClient, AzureAISearchContextProvider
from agent_framework.azure import AzureAISearchContextProvider
from agent_framework.foundry import FoundryChatClient
from azure.identity.aio import DefaultAzureCredential
# Create search provider with semantic mode (default)
@@ -140,10 +141,13 @@ search_provider = AzureAISearchContextProvider(
)
# Create agent with search context
async with AzureAIAgentClient(credential=DefaultAzureCredential()) as client:
async with FoundryChatClient(
project_endpoint=project_endpoint,
model=model_deployment,
credential=DefaultAzureCredential(),
) as client:
async with Agent(
client=client,
model=model_deployment,
context_providers=[search_provider],
) as agent:
response = await agent.run("What information is in the knowledge base?")
python/samples/02-agents/context_providers/azure_ai_search/search_context_agentic.py
+2 -2
View File
@@ -34,7 +34,7 @@ Environment variables:
- AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
- AZURE_SEARCH_API_KEY: (Optional) API key - if not provided, uses AzureCliCredential
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name (e.g., "gpt-4o")
- FOUNDRY_MODEL: Your model deployment name (e.g., "gpt-4o")
For using an existing Knowledge Base (recommended):
- AZURE_SEARCH_KNOWLEDGE_BASE_NAME: Your Knowledge Base name
@@ -59,7 +59,7 @@ async def main() -> None:
search_endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
search_key = os.environ.get("AZURE_SEARCH_API_KEY")
project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
model_deployment = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o")
model_deployment = os.environ.get("FOUNDRY_MODEL", "gpt-4o")
# Agentic mode requires exactly ONE of: knowledge_base_name OR index_name
# Option 1: Use existing Knowledge Base (recommended)
python/samples/02-agents/context_providers/azure_ai_search/search_context_semantic.py
+2 -2
View File
@@ -31,7 +31,7 @@ Prerequisites:
- AZURE_SEARCH_API_KEY: (Optional) Your search API key - if not provided, uses AzureCliCredential for Entra ID
- AZURE_SEARCH_INDEX_NAME: Your search index name
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name (e.g., "gpt-4o")
- FOUNDRY_MODEL: Your model deployment name (e.g., "gpt-4o")
- AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: (Optional) Your Azure OpenAI embedding deployment for hybrid search
- AZURE_OPENAI_ENDPOINT: (Optional) Your Azure OpenAI resource URL, required if using Azure OpenAI embeddings
"""
@@ -54,7 +54,7 @@ async def main() -> None:
search_key = os.environ.get("AZURE_SEARCH_API_KEY")
index_name = os.environ["AZURE_SEARCH_INDEX_NAME"]
project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
model_deployment = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o")
model_deployment = os.environ.get("FOUNDRY_MODEL", "gpt-4o")
openai_endpoint = os.environ.get("AZURE_OPENAI_ENDPOINT")
embedding_deployment = os.environ.get("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME")
python/samples/02-agents/context_providers/mem0/README.md
+2 -2
View File
@@ -33,8 +33,8 @@ Set the following environment variables:
- `OPENAI_API_KEY`: Your OpenAI API key (used by Mem0 OSS for embedding generation and automatic memory extraction)
**For Azure AI:**
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI project endpoint
- `AZURE_AI_MODEL_DEPLOYMENT_NAME`: The name of your model deployment
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI project endpoint
- `FOUNDRY_MODEL`: The name of your model deployment
## Key Concepts
python/samples/02-agents/context_providers/redis/README.md
+6 -6
View File
@@ -51,8 +51,8 @@ See quickstart: `https://learn.microsoft.com/azure/redis/quickstart-create-manag
### Environment variables
- `AZURE_AI_PROJECT_ENDPOINT` (required): Azure AI Foundry project endpoint for `AzureOpenAIResponsesClient`
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` (required): Azure OpenAI Responses deployment name
- `FOUNDRY_PROJECT_ENDPOINT` (required): Azure AI Foundry project endpoint for `FoundryChatClient`
- `FOUNDRY_MODEL` (required): Foundry model deployment name
- `OPENAI_API_KEY` (optional): Required only if you set `vectorizer_choice="openai"` to enable hybrid search.
### Provider configuration highlights
@@ -73,7 +73,7 @@ The provider supports both full‑text only and hybrid vector search:
2. Agent integration: teaches the agent a preference and verifies it is remembered across turns.
3. Agent + tool: calls a sample tool (flight search) and then asks the agent to recall details remembered from the tool output.
It uses `AzureOpenAIResponsesClient` (Foundry project endpoint setup) for chat and, in some steps, optional OpenAI embeddings for hybrid search.
It uses `FoundryChatClient` for chat and, in some steps, optional OpenAI embeddings for hybrid search.
## How to run
@@ -82,8 +82,8 @@ It uses `AzureOpenAIResponsesClient` (Foundry project endpoint setup) for chat a
2) Set Azure Foundry/OpenAI responses environment variables:
```bash
export AZURE_AI_PROJECT_ENDPOINT="https://<resource>.services.ai.azure.com/api/projects/<project>"
export AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="<deployment-name>"
export FOUNDRY_PROJECT_ENDPOINT="https://<resource>.services.ai.azure.com/api/projects/<project>"
export FOUNDRY_MODEL="<deployment-name>"
```
3) (Optional) Set your OpenAI key if using embeddings:
@@ -119,6 +119,6 @@ You should see the agent responses and, when using embeddings, context retrieved
## Troubleshooting
- Ensure at least one of `application_id`, `agent_id`, `user_id`, or `thread_id` is set; the provider requires a scope.
- Verify `AZURE_AI_PROJECT_ENDPOINT` and `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` are set for the chat client.
- Verify `FOUNDRY_PROJECT_ENDPOINT` and `FOUNDRY_MODEL` are set for the chat client.
- If using embeddings, verify `OPENAI_API_KEY` is set and reachable.
- Make sure Redis exposes RediSearch (Redis Stack image or managed service with search enabled).
python/samples/02-agents/declarative/mcp_tool_yaml.py
+3 -3
View File
@@ -10,11 +10,11 @@ Key Features Demonstrated:
1. Loading agent definitions from YAML using AgentFactory
2. Configuring MCP tools with different authentication methods:
- API key authentication (OpenAI.Responses provider)
- Azure AI Foundry connection references (AzureAI.ProjectProvider)
- Azure AI Foundry connection references (Foundry provider)
Authentication Options:
- OpenAI.Responses: Supports inline API key auth via headers
- AzureAI.ProjectProvider: Uses Foundry connections for secure credential storage
- Foundry: Uses project-backed chat with Foundry connections for secure credential storage
(no secrets passed in API calls - connection name references pre-configured auth)
Prerequisites:
@@ -79,7 +79,7 @@ instructions: |
model:
id: gpt-4o
provider: AzureAI.ProjectProvider
provider: Foundry
tools:
- kind: mcp
python/samples/02-agents/devui/README.md
+3 -3
View File
@@ -55,15 +55,15 @@ agent_name/
| Sample | Description | Features | Required Environment Variables |
| ------------------------------------------------ | ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| [**weather_agent_azure/**](weather_agent_azure/) | Weather agent using Azure OpenAI with API key authentication | Azure OpenAI integration, function calling, mock weather tools | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
| [**foundry_agent/**](foundry_agent/) | Weather agent using Azure AI Agent (Foundry) with Azure CLI authentication (run `az login` first) | Azure AI Agent integration, Azure CLI authentication, mock weather tools | `AZURE_AI_PROJECT_ENDPOINT`, `FOUNDRY_MODEL_DEPLOYMENT_NAME` |
| [**weather_agent_azure/**](weather_agent_azure/) | Weather agent using Azure OpenAI with API key authentication | Azure OpenAI integration, function calling, mock weather tools | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
| [**foundry_agent/**](foundry_agent/) | Weather agent using Azure AI Agent (Foundry) with Azure CLI authentication (run `az login` first) | Azure AI Agent integration, Azure CLI authentication, mock weather tools | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL` |
### Workflows
| Sample | Description | Features | Required Environment Variables |
| -------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
| [**declarative/**](declarative/) | Declarative YAML workflow with conditional branching | YAML-based workflow definition, conditional logic, no Python code required | None - uses mock data |
| [**workflow_agents/**](workflow_agents/) | Content review workflow with agents as executors | Agents as workflow nodes, conditional routing based on structured outputs, quality-based paths (Writer -> Reviewer -> Editor/Publisher) | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
| [**workflow_agents/**](workflow_agents/) | Content review workflow with agents as executors | Agents as workflow nodes, conditional routing based on structured outputs, quality-based paths (Writer -> Reviewer -> Editor/Publisher) | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
| [**spam_workflow/**](spam_workflow/) | 5-step email spam detection workflow with branching logic | Sequential execution, conditional branching (spam vs. legitimate), multiple executors, mock spam detection | None - uses mock data |
| [**fanout_workflow/**](fanout_workflow/) | Advanced data processing workflow with parallel execution | Fan-out/fan-in patterns, complex state management, multi-stage processing (validation -> transformation -> quality assurance) | None - uses mock data |
python/samples/02-agents/devui/azure_responses_agent/.env.example
+1 -1
View File
@@ -12,4 +12,4 @@ AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
AZURE_OPENAI_ENDPOINT=https://your-resource.cognitiveservices.azure.com/
# Required: Deployment name (must support Responses API)
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4.1-mini
FOUNDRY_MODEL=gpt-4.1-mini
python/samples/02-agents/devui/foundry_agent/.env.example
+2 -2
View File
@@ -2,5 +2,5 @@
# Get your credentials from Azure AI Foundry portal
# Make sure to run 'az login' before starting devui
AZURE_AI_PROJECT_ENDPOINT=https://your-project.api.azureml.ms
FOUNDRY_MODEL_DEPLOYMENT_NAME=gpt-4o
FOUNDRY_PROJECT_ENDPOINT=https://your-project.api.azureml.ms
FOUNDRY_MODEL=gpt-4o
python/samples/02-agents/devui/foundry_agent/agent.py
+1 -1
View File
@@ -53,7 +53,7 @@ agent = Agent(
name="FoundryWeatherAgent",
client=FoundryChatClient(
project_endpoint=os.environ.get("FOUNDRY_PROJECT_ENDPOINT"),
model_model=os.environ.get("FOUNDRY_MODEL_DEPLOYMENT_NAME"),
model_model=os.environ.get("FOUNDRY_MODEL"),
credential=AzureCliCredential(),
),
instructions="""
python/samples/02-agents/devui/weather_agent_azure/.env.example
+1 -1
View File
@@ -2,5 +2,5 @@
# Get your credentials from Azure Portal
AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
python/samples/02-agents/devui/workflow_agents/.env.example
+1 -1
View File
@@ -2,6 +2,6 @@
# Get your credentials from Azure Portal
AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
AZURE_OPENAI_API_VERSION=2024-10-21
python/samples/02-agents/evaluation/evaluate_multimodal.py
-1
View File
@@ -22,7 +22,6 @@ from agent_framework import (
evaluator,
)
# -- Custom evaluators that inspect multimodal content --
python/samples/02-agents/middleware/README.md
+1 -1
View File
@@ -21,7 +21,7 @@ This folder contains focused middleware samples for `Agent`, chat clients, tools
## Running the usage tracking sample
The new usage tracking sample uses `OpenAIResponsesClient`, so set the usual OpenAI responses environment variables first:
The new usage tracking sample uses `OpenAIChatClient`, so set the usual OpenAI responses environment variables first:
```bash
export OPENAI_API_KEY="your-openai-api-key"
python/samples/02-agents/middleware/override_result_with_middleware.py
+2 -2
View File
@@ -19,7 +19,7 @@ from agent_framework import (
ResponseStream,
tool,
)
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import Field
@@ -190,7 +190,7 @@ async def main() -> None:
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
agent = Agent(
client=OpenAIResponsesClient(
client=OpenAIChatClient(
middleware=[validate_weather_middleware, weather_override_middleware],
),
name="WeatherAgent",
python/samples/02-agents/middleware/usage_tracking_middleware.py
+2 -2
View File
@@ -19,7 +19,7 @@ from agent_framework import (
chat_middleware,
tool,
)
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import Field
@@ -53,7 +53,7 @@ def _reset_usage_counters() -> None:
def _create_agent() -> Agent:
"""Create the shared agent used by both demonstrations."""
return Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
instructions=(
"You are a weather assistant. Always call the weather tool before answering weather questions, "
"then summarize the tool result in one short paragraph."
python/samples/02-agents/multimodal_input/README.md
+6 -6
View File
@@ -32,8 +32,8 @@ Set the following environment variables before running the examples:
**For Azure OpenAI:**
- `AZURE_OPENAI_ENDPOINT`: Your Azure OpenAI endpoint
- `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`: The name of your Azure OpenAI chat model deployment
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your Azure OpenAI responses model deployment
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your Azure OpenAI chat model deployment
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your Azure OpenAI responses model deployment
Optionally for Azure OpenAI:
- `AZURE_OPENAI_API_VERSION`: The API version to use (default is `2024-10-21`)
@@ -41,11 +41,11 @@ Optionally for Azure OpenAI:
**Note:** You can also provide configuration directly in code instead of using environment variables:
```python
# Example: Pass deployment_name directly
client = AzureOpenAIChatClient(
# Example: Pass the Foundry project endpoint directly
client = FoundryChatClient(
credential=AzureCliCredential(),
deployment_name="your-deployment-name",
endpoint="https://your-resource.openai.azure.com"
project_endpoint="https://your-project.services.ai.azure.com",
model="your-deployment-name",
)
```
python/samples/02-agents/observability/.env.example
+2 -2
View File
@@ -45,5 +45,5 @@ OPENAI_CHAT_MODEL="gpt-4o-2024-08-06"
# Azure AI Foundry specific variables
# ====================================
AZURE_AI_PROJECT_ENDPOINT="..."
AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"
FOUNDRY_PROJECT_ENDPOINT="..."
FOUNDRY_MODEL="gpt-4o-mini"
python/samples/02-agents/providers/anthropic/README.md
+2 -1
View File
@@ -33,7 +33,8 @@ This folder contains examples demonstrating how to use Anthropic's Claude models
### Foundry
- `ANTHROPIC_FOUNDRY_API_KEY`: Your Foundry Anthropic API key
- `ANTHROPIC_FOUNDRY_ENDPOINT`: The endpoint URL for your Foundry Anthropic resource
- `ANTHROPIC_FOUNDRY_RESOURCE`: Your Foundry resource name (for example `my-foundry-resource`)
- `ANTHROPIC_FOUNDRY_BASE_URL`: Optional full Foundry Anthropic base URL alternative to `ANTHROPIC_FOUNDRY_RESOURCE`
- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use in Foundry (e.g., `claude-haiku-4-5`)
### Claude Agent
python/samples/02-agents/providers/anthropic/anthropic_foundry.py
+5 -2
View File
@@ -22,8 +22,11 @@ This example requires `anthropic>=0.74.0` and an endpoint in Foundry for Anthrop
To use the Foundry integration ensure you have the following environment variables set:
- ANTHROPIC_FOUNDRY_API_KEY
Alternatively you can pass in a azure_ad_token_provider function to the AsyncAnthropicFoundry constructor.
- ANTHROPIC_FOUNDRY_ENDPOINT
Should be something like https://<your-resource-name>.services.ai.azure.com/anthropic/
- ANTHROPIC_FOUNDRY_RESOURCE
Should be the resource name portion of your Foundry Anthropic URL, such as <your-resource-name>.
- ANTHROPIC_FOUNDRY_BASE_URL
Optional alternative to ANTHROPIC_FOUNDRY_RESOURCE. Should be something like
https://<your-resource-name>.services.ai.azure.com/anthropic/
- ANTHROPIC_CHAT_MODEL_ID
Should be something like claude-haiku-4-5
"""
python/samples/02-agents/providers/azure/openai_chat_completion_client_with_explicit_settings.py
+1 -1
View File
@@ -41,7 +41,7 @@ async def main() -> None:
# authentication option.
agent = Agent(
client=OpenAIChatCompletionClient(
model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT_NAME"],
model=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
credential=AzureCliCredential(),
),
python/samples/02-agents/providers/custom/README.md
+4 -4
View File
@@ -27,7 +27,7 @@ Both approaches allow you to extend the framework for your specific use cases wh
## Understanding Raw Client Classes
The framework provides `Raw...Client` classes (e.g., `RawOpenAIChatClient`, `RawOpenAIChatCompletionClient`, `RawAzureAIClient`) that are intermediate implementations without middleware, telemetry, or function invocation support.
The framework provides `Raw...Client` classes (e.g., `RawOpenAIChatClient`, `RawOpenAIChatCompletionClient`, `RawFoundryChatClient`) that are intermediate implementations without middleware, telemetry, or function invocation support.
### Warning: Raw Clients Should Not Normally Be Used Directly
@@ -62,8 +62,8 @@ For most use cases, use the fully-featured public client classes which already h
- `OpenAIChatCompletionClient` - OpenAI Chat Completions API with all layers
- `OpenAIChatClient` - OpenAI Responses API with all layers
- `AzureOpenAIChatClient` - Azure OpenAI Chat with all layers
- `AzureOpenAIResponsesClient` - Azure OpenAI Responses with all layers
- `AzureAIClient` - Azure AI Project with all layers
- `OpenAIChatCompletionClient` - Azure OpenAI Chat Completions with all layers
- `OpenAIChatClient` - Azure OpenAI Responses with all layers
- `FoundryChatClient` - Azure AI Foundry project-backed chat with all layers
These clients handle the layer composition correctly and provide the full feature set out of the box.
python/samples/02-agents/skills/code_defined_skill/README.md
+2 -2
View File
@@ -27,8 +27,8 @@ code_defined_skill/
Set the required environment variables in a `.env` file (see `python/.env.example`):
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/skills/file_based_skill/README.md
+2 -2
View File
@@ -47,8 +47,8 @@ file_based_skill/
Set the required environment variables in a `.env` file (see `python/.env.example`):
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/skills/mixed_skills/README.md
+2 -2
View File
@@ -60,8 +60,8 @@ File scripts are executed as **local Python subprocesses** via the
Set environment variables (or create a `.env` file):
```
AZURE_AI_PROJECT_ENDPOINT=https://your-project.openai.azure.com/
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4o-mini
FOUNDRY_PROJECT_ENDPOINT=https://your-project.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini
```
Authenticate with Azure CLI:
python/samples/02-agents/skills/script_approval/README.md
+2 -2
View File
@@ -28,8 +28,8 @@ When `require_script_approval=True` is set, the agent pauses before executing an
Set the required environment variables in a `.env` file (see `python/.env.example`):
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/tools/function_invocation_configuration.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -28,7 +28,7 @@ def add(
async def main():
client = OpenAIResponsesClient()
client = OpenAIChatClient()
client.function_invocation_configuration["include_detailed_errors"] = True
client.function_invocation_configuration["max_iterations"] = 40
print(f"Function invocation configured as: \n{client.function_invocation_configuration}")
python/samples/02-agents/tools/function_tool_declaration_only.py
+2 -2
View File
@@ -3,7 +3,7 @@
import asyncio
from agent_framework import Agent, FunctionTool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -26,7 +26,7 @@ async def main():
)
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="DeclarationOnlyToolAgent",
instructions="You are a helpful agent that uses tools.",
tools=function_declaration,
python/samples/02-agents/tools/function_tool_from_dict_with_dependency_injection.py
+2 -2
View File
@@ -22,7 +22,7 @@ Usage:
import asyncio
from agent_framework import Agent, FunctionTool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -62,7 +62,7 @@ async def main() -> None:
tool = FunctionTool.from_dict(definition, dependencies={"function_tool": {"name:add_numbers": {"func": func}}})
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="FunctionToolAgent",
instructions="You are a helpful assistant.",
tools=tool,
python/samples/02-agents/tools/function_tool_with_explicit_schema.py
+2 -2
View File
@@ -18,7 +18,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import BaseModel, Field
@@ -70,7 +70,7 @@ def get_current_time(timezone: str = "UTC") -> str:
async def main():
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="AssistantAgent",
instructions="You are a helpful assistant. Use the available tools to answer questions.",
tools=[get_weather, get_current_time],
python/samples/02-agents/tools/function_tool_with_kwargs.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, FunctionInvocationContext, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import Field
@@ -44,7 +44,7 @@ def get_weather(
async def main() -> None:
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="WeatherAgent",
instructions="You are a helpful weather assistant.",
tools=[get_weather],
python/samples/02-agents/tools/function_tool_with_max_exceptions.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -36,7 +36,7 @@ def safe_divide(
async def main():
# tools = Tools()
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="ToolAgent",
instructions="Use the provided tools.",
tools=[safe_divide],
python/samples/02-agents/tools/function_tool_with_max_invocations.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -25,7 +25,7 @@ def unicorn_function(times: Annotated[int, "The number of unicorns to return."])
async def main():
# tools = Tools()
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="ToolAgent",
instructions="Use the provided tools.",
tools=[unicorn_function],
python/samples/02-agents/tools/function_tool_with_session_injection.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, AgentSession, FunctionInvocationContext, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
from pydantic import Field
@@ -37,7 +37,7 @@ async def get_weather(
async def main() -> None:
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="WeatherAgent",
instructions="You are a helpful weather assistant.",
tools=[get_weather],
python/samples/02-agents/tools/tool_in_class.py
+2 -2
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Annotated
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -50,7 +50,7 @@ async def main():
add_function = tool(description="Add two numbers.")(tools.add)
agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
name="ToolAgent",
instructions="Use the provided tools.",
)
python/samples/03-workflows/README.md
+6 -6
View File
@@ -160,17 +160,17 @@ Sequential orchestration uses a few small adapter nodes for plumbing:
These may appear in event streams (executor_invoked/executor_completed). They're analogous to
concurrent’s dispatcher and aggregator and can be ignored if you only care about agent activity.
### AzureOpenAIResponsesClient vs AzureAIAgent
### Why FoundryChatClient?
Workflow and orchestration samples use `AzureOpenAIResponsesClient` rather than the CRUD-style `AzureAIAgent` client. The key difference:
Workflow and orchestration samples use `FoundryChatClient` because they create agents locally and do not need
server-managed agent resources. This lightweight, project-backed chat client is a good fit for orchestration
patterns such as Sequential, Concurrent, Handoff, GroupChat, and Magentic.
- **`AzureOpenAIResponsesClient`** — A lightweight client that uses the underlying Agent Service V2 (Responses API) for non-CRUD-style agents. Orchestrations use this client because agents are created locally and do not require server-side lifecycle management (create/update/delete). This is the recommended client for orchestration patterns (Sequential, Concurrent, Handoff, GroupChat, Magentic).
- **`AzureAIAgent`** — A CRUD-style client for server-managed agents. Use this when you need persistent, server-side agent definitions with features like file search, code interpreter sessions, or thread management provided by the Azure AI Agent Service.
If you need persistent server-side agent resources, use the hosted-agent flows rather than these workflow samples.
### Environment Variables
Workflow samples that use `AzureOpenAIResponsesClient` expect:
Workflow samples that use `FoundryChatClient` expect:
- `FOUNDRY_PROJECT_ENDPOINT` (Azure AI Foundry Agent Service (V2) project endpoint)
- `FOUNDRY_MODEL` (model deployment name)
python/samples/03-workflows/declarative/function_tools/README.md
+6 -6
View File
@@ -6,7 +6,7 @@ This sample demonstrates an agent with function tools responding to user queries
The workflow showcases:
- **Function Tools**: Agent equipped with tools to query menu data
- **Real Azure OpenAI Agent**: Uses `AzureOpenAIResponsesClient` to create an agent with tools
- **Real Foundry-backed agent**: Uses `FoundryChatClient` to create an agent with tools
- **Agent Registration**: Shows how to register agents with the `WorkflowFactory`
## Tools
@@ -37,7 +37,7 @@ Drinks:
## Prerequisites
- Azure OpenAI configured with required environment variables
- Microsoft Foundry configured with required environment variables
- Authentication via azure-identity (run `az login` before executing)
## Usage
@@ -65,16 +65,16 @@ Session Complete
## How It Works
1. Create an Azure OpenAI chat client
1. Create a Foundry chat client
2. Create an agent with instructions and function tools
3. Register the agent with the workflow factory
4. Load the workflow YAML and run it with `run()` and `stream=True`
```python
# Create the agent with tools
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
menu_agent = client.as_agent(
python/samples/03-workflows/orchestrations/README.md
+7 -5
View File
@@ -92,15 +92,17 @@ from agent_framework.orchestrations import (
These may appear in event streams (executor_invoked/executor_completed). They're analogous to concurrent's dispatcher and aggregator and can be ignored if you only care about agent activity.
## Why AzureOpenAIResponsesClient?
## Why FoundryChatClient?
Orchestration samples use `AzureOpenAIResponsesClient` rather than the CRUD-style `AzureAIAgent` client. Orchestrations create agents locally and do not require server-side lifecycle management (create/update/delete). `AzureOpenAIResponsesClient` is a lightweight client that uses the underlying Agent Service V2 (Responses API) for non-CRUD-style agents, which is ideal for orchestration patterns like Sequential, Concurrent, Handoff, GroupChat, and Magentic.
Orchestration samples use `FoundryChatClient` because they create agents locally and do not require
server-side lifecycle management. `FoundryChatClient` is a lightweight, project-backed client that fits
patterns like Sequential, Concurrent, Handoff, GroupChat, and Magentic.
## Environment Variables
Orchestration samples that use `AzureOpenAIResponsesClient` expect:
Orchestration samples that use `FoundryChatClient` expect:
- `AZURE_AI_PROJECT_ENDPOINT` (Azure AI Foundry Agent Service (V2) project endpoint)
- `AZURE_AI_MODEL_DEPLOYMENT_NAME` (model deployment name)
- `FOUNDRY_PROJECT_ENDPOINT` (Azure AI Foundry Agent Service (V2) project endpoint)
- `FOUNDRY_MODEL` (model deployment name)
These values are passed directly into the client constructor via `os.getenv()` in sample code.
python/samples/04-hosting/a2a/README.md
+5 -5
View File
@@ -22,16 +22,16 @@ The remaining files are supporting modules used by the server:
Make sure to set the following environment variables before running the examples:
### Required (Server)
- `AZURE_AI_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` — Model deployment name (e.g. `gpt-4o`)
- `FOUNDRY_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL` — Model deployment name (e.g. `gpt-4o`)
### Required (Client)
- `A2A_AGENT_HOST` — URL of the A2A server (e.g. `http://localhost:5001/`)
### Required (Function Tools Sample)
- `A2A_AGENT_HOST` — URL of the A2A server (e.g. `http://localhost:5000/`)
- `AZURE_AI_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` — Model deployment name (e.g. `gpt-4o`)
- `FOUNDRY_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL` — Model deployment name (e.g. `gpt-4o`)
## Quick Start
@@ -65,7 +65,7 @@ uv run python agent_with_a2a.py
### 3. Run the Function Tools Sample
This sample resolves the remote agent's skills and registers each one as a function tool
on a host OpenAI-powered agent. The host agent then autonomously selects the right skill
on a host Foundry-backed agent. The host agent then autonomously selects the right skill
to handle the user's request.
```powershell
python/samples/04-hosting/a2a/a2a_agent_as_function_tools.py
+9 -9
View File
@@ -7,7 +7,7 @@ import re
import httpx
from a2a.client import A2ACardResolver
from agent_framework.a2a import A2AAgent
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -29,8 +29,8 @@ Key concepts demonstrated:
Prerequisites:
- Set A2A_AGENT_HOST to the URL of a running A2A server
- Set AZURE_AI_PROJECT_ENDPOINT to your Azure AI Foundry project endpoint
- Set AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME to the model deployment name (e.g. gpt-4o)
- Set FOUNDRY_PROJECT_ENDPOINT to your Azure AI Foundry project endpoint
- Set FOUNDRY_MODEL to the model deployment name (e.g. gpt-4o)
To run this sample:
cd python/samples/04-hosting/a2a
@@ -45,11 +45,11 @@ async def main() -> None:
if not a2a_agent_host:
raise ValueError("A2A_AGENT_HOST environment variable is not set")
project_endpoint = os.getenv("AZURE_AI_PROJECT_ENDPOINT")
deployment_name = os.getenv("AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME")
if not project_endpoint or not deployment_name:
project_endpoint = os.getenv("FOUNDRY_PROJECT_ENDPOINT")
model = os.getenv("FOUNDRY_MODEL")
if not project_endpoint or not model:
raise ValueError(
"AZURE_AI_PROJECT_ENDPOINT and AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME must be set"
"FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL must be set"
)
print(f"Connecting to A2A agent at: {a2a_agent_host}")
@@ -83,9 +83,9 @@ async def main() -> None:
# 5. Create the host agent with the skill tools.
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
client = FoundryChatClient(
project_endpoint=project_endpoint,
deployment_name=deployment_name,
model=model,
credential=credential,
)
host_agent = client.as_agent(
python/samples/04-hosting/azure_functions/08_mcp_server/README.md
+18 -6
View File
@@ -138,23 +138,35 @@ Expected response:
The sample shows how to enable MCP tool triggers with flexible agent configuration:
```python
from agent_framework.azure import AgentFunctionApp, AzureOpenAIChatClient
import os
# Create Azure OpenAI Chat Client
client = AzureOpenAIChatClient()
from agent_framework import Agent
from agent_framework.azure import AgentFunctionApp
from agent_framework.foundry import FoundryChatClient
from azure.identity.aio import AzureCliCredential
# Create Foundry chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
# Define agents with different roles
joker_agent = client.as_agent(
joker_agent = Agent(
client=client,
name="Joker",
instructions="You are good at telling jokes.",
)
stock_agent = client.as_agent(
stock_agent = Agent(
client=client,
name="StockAdvisor",
instructions="Check stock prices.",
)
plant_agent = client.as_agent(
plant_agent = Agent(
client=client,
name="PlantAdvisor",
instructions="Recommend plants.",
description="Get plant recommendations.",
python/samples/05-end-to-end/ag_ui_workflow_handoff/README.md
+2 -2
View File
@@ -27,8 +27,8 @@ The backend uses Azure OpenAI responses and supports intent-driven, non-linear h
- Node.js 18+
- npm 9+
- Azure AI project + model deployment configured in environment variables:
- `AZURE_AI_PROJECT_ENDPOINT`
- `AZURE_AI_MODEL_DEPLOYMENT_NAME`
- `FOUNDRY_PROJECT_ENDPOINT`
- `FOUNDRY_MODEL`
## 1) Run Backend
python/samples/05-end-to-end/ag_ui_workflow_handoff/backend/server.py
+1 -1
View File
@@ -85,7 +85,7 @@ def create_agents() -> tuple[Agent, Agent, Agent]:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/chatkit-integration/README.md
+1 -1
View File
@@ -177,7 +177,7 @@ pip install agent-framework-chatkit fastapi uvicorn azure-identity
```bash
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
export AZURE_OPENAI_API_VERSION="2024-06-01"
export AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="gpt-4o"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o"
```
3. **Authenticate with Azure:**
python/samples/05-end-to-end/evaluation/red_teaming/.env.example
+1 -1
View File
@@ -5,4 +5,4 @@ AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
# Azure AI Project Configuration (for red teaming)
# Create these resources at: https://portal.azure.com
AZURE_AI_PROJECT_ENDPOINT=your-ai-project-name
FOUNDRY_PROJECT_ENDPOINT=your-ai-project-name
python/samples/05-end-to-end/evaluation/red_teaming/README.md
+4 -4
View File
@@ -11,7 +11,7 @@ For more details on the Red Team setup see [the Azure AI Foundry docs](https://l
A focused sample demonstrating Azure AI's RedTeam functionality to assess the safety and resilience of Agent Framework agents against adversarial attacks.
**What it demonstrates:**
1. Creating a financial advisor agent inline using `AzureOpenAIChatClient`
1. Creating a financial advisor agent inline using `FoundryChatClient`
2. Setting up an async callback to interface the agent with RedTeam evaluator
3. Running comprehensive evaluations with 11 different attack strategies:
- Basic: EASY and MODERATE difficulty levels
@@ -47,7 +47,7 @@ AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
# AZURE_OPENAI_API_KEY is optional if using Azure CLI authentication
# Azure AI Project (for red teaming)
AZURE_AI_PROJECT_ENDPOINT=https://your-project.api.azureml.ms
FOUNDRY_PROJECT_ENDPOINT=https://your-project.api.azureml.ms
```
See `.env.example` for a template.
@@ -113,7 +113,7 @@ async def main() -> None:
credential = AzureCliCredential()
# 2. Create agent inline
agent = AzureOpenAIChatClient(credential=credential).as_agent(
agent = FoundryChatClient(credential=credential).as_agent(
model="gpt-4o",
instructions="You are a helpful financial advisor..."
)
@@ -125,7 +125,7 @@ async def main() -> None:
# 4. Run red team scan with multiple strategies
red_team = RedTeam(
azure_ai_project=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
azure_ai_project=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
credential=credential
)
results = await red_team.scan(
python/samples/05-end-to-end/hosted_agents/README.md
+4 -4
View File
@@ -10,7 +10,7 @@ These samples demonstrate how to build and host AI agents in Python using the [A
| [`agent_with_text_search_rag`](./agent_with_text_search_rag/) | Retrieval-augmented generation using a custom `BaseContextProvider` with Contoso Outdoors sample data |
| [`agents_in_workflow`](./agents_in_workflow/) | Concurrent workflow that combines researcher, marketer, and legal specialist agents |
| [`agent_with_local_tools`](./agent_with_local_tools/) | Local Python tool execution for Seattle hotel search |
| [`writer_reviewer_agents_in_workflow`](./writer_reviewer_agents_in_workflow/) | Writer/Reviewer workflow using `AzureOpenAIResponsesClient` |
| [`writer_reviewer_agents_in_workflow`](./writer_reviewer_agents_in_workflow/) | Writer/Reviewer workflow using `FoundryChatClient` |
## Common Prerequisites
@@ -76,14 +76,14 @@ Example `.env` for Azure OpenAI samples:
```dotenv
AZURE_OPENAI_ENDPOINT=https://<your-openai-resource>.openai.azure.com/
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4.1
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4.1
```
Example `.env` for Foundry project samples:
```dotenv
PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
MODEL_DEPLOYMENT_NAME=gpt-4.1
FOUNDRY_PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
FOUNDRY_MODEL=gpt-4.1
```
## Interacting with the Agent
python/samples/05-end-to-end/hosted_agents/agent_with_hosted_mcp/agent.yaml
+1 -1
View File
@@ -22,7 +22,7 @@ template:
environment_variables:
- name: AZURE_OPENAI_ENDPOINT
value: ${AZURE_OPENAI_ENDPOINT}
- name: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
- name: AZURE_OPENAI_DEPLOYMENT_NAME
value: "{{chat}}"
resources:
- kind: model
python/samples/05-end-to-end/hosted_agents/agent_with_text_search_rag/agent.yaml
+1 -1
View File
@@ -25,7 +25,7 @@ template:
environment_variables:
- name: AZURE_OPENAI_ENDPOINT
value: ${AZURE_OPENAI_ENDPOINT}
- name: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
- name: AZURE_OPENAI_DEPLOYMENT_NAME
value: "{{chat}}"
resources:
- kind: model
python/samples/05-end-to-end/hosted_agents/agents_in_workflow/agent.yaml
+1 -1
View File
@@ -20,7 +20,7 @@ template:
environment_variables:
- name: AZURE_OPENAI_ENDPOINT
value: ${AZURE_OPENAI_ENDPOINT}
- name: AZURE_OPENAI_CHAT_DEPLOYMENT_NAME
- name: AZURE_OPENAI_DEPLOYMENT_NAME
value: "{{chat}}"
resources:
- kind: model
python/samples/05-end-to-end/workflow_evaluation/.env.example
+3 -3
View File
@@ -1,3 +1,3 @@
AZURE_AI_PROJECT_ENDPOINT="<your-project-endpoint>"
AZURE_AI_MODEL_DEPLOYMENT_NAME_WORKFLOW="<your-model-deployment>"
AZURE_AI_MODEL_DEPLOYMENT_NAME_EVAL="<your-model-deployment>"
FOUNDRY_PROJECT_ENDPOINT="<your-project-endpoint>"
FOUNDRY_MODEL_WORKFLOW="<your-model-deployment>"
FOUNDRY_MODEL_EVAL="<your-model-deployment>"
python/samples/05-end-to-end/workflow_evaluation/run_evaluation.py
+3 -3
View File
@@ -99,7 +99,7 @@ def fetch_agent_responses(openai_client: OpenAI, workflow_data: dict[str, Any],
def create_evaluation(openai_client: OpenAI, deployment_name: str | None = "gpt-5.2") -> EvalCreateResponse:
"""Create evaluation with multiple evaluators."""
deployment_name = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", deployment_name)
deployment_name = os.environ.get("FOUNDRY_MODEL", deployment_name)
data_source_config = {"type": "azure_ai_source", "scenario": "responses"}
testing_criteria = [
@@ -199,8 +199,8 @@ async def main():
openai_client = create_openai_client()
# Model configuration
workflow_agent_model = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME_WORKFLOW", "gpt-4.1-nano")
eval_model = os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME_EVAL", "gpt-5.2")
workflow_agent_model = os.environ.get("FOUNDRY_MODEL_WORKFLOW", "gpt-4.1-nano")
eval_model = os.environ.get("FOUNDRY_MODEL_EVAL", "gpt-5.2")
# Focus on these agents, uncomment other ones you want to have evals run on
agents_to_evaluate = [
python/samples/AGENTS.md
+7 -7
View File
@@ -66,26 +66,26 @@ python/samples/
## Default provider
All canonical samples (01-get-started) use **Azure OpenAI Responses** via `AzureOpenAIResponsesClient`
All canonical samples (01-get-started) use **Azure AI Foundry project-backed chat** via `FoundryChatClient`
with an Azure AI Foundry project endpoint:
```python
import os
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
credential = AzureCliCredential()
client = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=credential,
)
agent = client.as_agent(name="...", instructions="...")
```
Environment variables:
- `AZURE_AI_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` — Model deployment name (e.g. gpt-4o)
- `FOUNDRY_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
- `FOUNDRY_MODEL` — Model deployment name (e.g. gpt-4o)
For authentication, run `az login` before running samples.
python/samples/README.md
+87 -1
View File
@@ -50,7 +50,7 @@ export FOUNDRY_MODEL="gpt-4o"
**Option 3: Using `env_file_path` parameter** (for per-client configuration):
All client classes (e.g., `OpenAIChatClient`, `AzureOpenAIResponsesClient`) support an `env_file_path` parameter to load environment variables from a specific file:
All client classes (e.g., `OpenAIChatClient`, `OpenAIChatCompletionClient`) support an `env_file_path` parameter to load environment variables from a specific file:
```python
from agent_framework.openai import OpenAIChatClient
@@ -77,6 +77,92 @@ FOUNDRY_PROJECT_ENDPOINT="your-foundry-project-endpoint"
FOUNDRY_MODEL="gpt-4o"
```
#### Consolidated sample env inventory
This is the single source of truth for package-level environment variables read by packages included by
`agent-framework-core[all]`. It intentionally excludes variables that are only read by standalone samples,
package sample folders, or tests. When package code adds, removes, or renames an environment variable,
update this table in the same change.
Example values below are illustrative. For entries not backed by a single public class, the `class`
column names the closest public surface, helper, or package-level initialization point that reads the
variable.
| package | class | env var | example value |
| --- | --- | --- | --- |
| `agent-framework-anthropic` | `AnthropicClient` | `ANTHROPIC_API_KEY` | `sk-ant-api03-...` |
| `agent-framework-anthropic` | `AnthropicClient` | `ANTHROPIC_CHAT_MODEL_ID` | `claude-sonnet-4-5-20250929` |
| `agent-framework-azure-ai` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_ENDPOINT` | `https://my-endpoint.inference.ai.azure.com` |
| `agent-framework-azure-ai` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_API_KEY` | `env-key` |
| `agent-framework-azure-ai` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_EMBEDDING_MODEL_ID` | `text-embedding-3-small` |
| `agent-framework-azure-ai` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL_ID` | `Cohere-embed-v3-english` |
| `agent-framework-azure-ai-search` | `AzureAISearchContextProvider` | `AZURE_SEARCH_ENDPOINT` | `https://my-search.search.windows.net` |
| `agent-framework-azure-ai-search` | `AzureAISearchContextProvider` | `AZURE_SEARCH_API_KEY` | `search-key` |
| `agent-framework-azure-ai-search` | `AzureAISearchContextProvider` | `AZURE_SEARCH_INDEX_NAME` | `hotels-index` |
| `agent-framework-azure-ai-search` | `AzureAISearchContextProvider` | `AZURE_SEARCH_KNOWLEDGE_BASE_NAME` | `hotels-kb` |
| `agent-framework-azure-cosmos` | `CosmosHistoryProvider` | `AZURE_COSMOS_ENDPOINT` | `https://my-cosmos.documents.azure.com:443/` |
| `agent-framework-azure-cosmos` | `CosmosHistoryProvider` | `AZURE_COSMOS_DATABASE_NAME` | `agent-history` |
| `agent-framework-azure-cosmos` | `CosmosHistoryProvider` | `AZURE_COSMOS_CONTAINER_NAME` | `messages` |
| `agent-framework-azure-cosmos` | `CosmosHistoryProvider` | `AZURE_COSMOS_KEY` | `C2F...==` |
| `agent-framework-bedrock` | `BedrockChatClient` | `BEDROCK_REGION` | `us-east-1` |
| `agent-framework-bedrock` | `BedrockChatClient` | `BEDROCK_CHAT_MODEL_ID` | `anthropic.claude-3-5-sonnet-20241022-v2:0` |
| `agent-framework-bedrock` | `BedrockEmbeddingClient` | `BEDROCK_REGION` | `us-east-1` |
| `agent-framework-bedrock` | `BedrockEmbeddingClient` | `BEDROCK_EMBEDDING_MODEL_ID` | `amazon.titan-embed-text-v2:0` |
| `agent-framework-bedrock` | `BedrockChatClient / BedrockEmbeddingClient` | `AWS_ACCESS_KEY_ID` | `AKIAIOSFODNN7EXAMPLE` |
| `agent-framework-bedrock` | `BedrockChatClient / BedrockEmbeddingClient` | `AWS_SECRET_ACCESS_KEY` | `wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY` |
| `agent-framework-bedrock` | `BedrockChatClient / BedrockEmbeddingClient` | `AWS_SESSION_TOKEN` | `IQoJb3JpZ2luX2VjEO7//////////wEaCXVzLXdlc3QtMiJHMEUCIQD...` |
| `agent-framework-copilotstudio` | `CopilotStudioAgent` | `COPILOTSTUDIOAGENT__ENVIRONMENTID` | `00000000-0000-0000-0000-000000000000` |
| `agent-framework-copilotstudio` | `CopilotStudioAgent` | `COPILOTSTUDIOAGENT__SCHEMANAME` | `cr123_agentname` |
| `agent-framework-copilotstudio` | `CopilotStudioAgent` | `COPILOTSTUDIOAGENT__TENANTID` | `11111111-1111-1111-1111-111111111111` |
| `agent-framework-copilotstudio` | `CopilotStudioAgent` | `COPILOTSTUDIOAGENT__AGENTAPPID` | `22222222-2222-2222-2222-222222222222` |
| `agent-framework-core` | `enable_instrumentation()` | `ENABLE_INSTRUMENTATION` | `true` |
| `agent-framework-core` | `enable_instrumentation()` | `ENABLE_SENSITIVE_DATA` | `false` |
| `agent-framework-core` | `enable_instrumentation()` | `ENABLE_CONSOLE_EXPORTERS` | `true` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_ENDPOINT` | `http://localhost:4317` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` | `http://localhost:4318/v1/traces` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT` | `http://localhost:4318/v1/metrics` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_LOGS_ENDPOINT` | `http://localhost:4318/v1/logs` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_PROTOCOL` | `grpc` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_HEADERS` | `api-key=demo` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_TRACES_HEADERS` | `api-key=trace-demo` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_METRICS_HEADERS` | `api-key=metric-demo` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_EXPORTER_OTLP_LOGS_HEADERS` | `api-key=log-demo` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_SERVICE_NAME` | `sample-agent` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_SERVICE_VERSION` | `1.0.0` |
| `agent-framework-core` | `enable_instrumentation()` | `OTEL_RESOURCE_ATTRIBUTES` | `deployment.environment=dev,service.namespace=agent-framework` |
| `agent-framework-devui` | `DevUI server` | `DEVUI_AUTH_TOKEN` | `my-devui-token` |
| `agent-framework-foundry` | `FoundryChatClient` | `FOUNDRY_PROJECT_ENDPOINT` | `https://my-project.services.ai.azure.com/api/projects/my-project` |
| `agent-framework-foundry` | `FoundryChatClient` | `FOUNDRY_MODEL` | `gpt-4o` |
| `agent-framework-foundry` | `FoundryAgent` | `FOUNDRY_AGENT_NAME` | `travel-planner` |
| `agent-framework-foundry` | `FoundryAgent` | `FOUNDRY_AGENT_VERSION` | `v1` |
| `agent-framework-github-copilot` | `GitHubCopilotAgent` | `GITHUB_COPILOT_CLI_PATH` | `copilot` |
| `agent-framework-github-copilot` | `GitHubCopilotAgent` | `GITHUB_COPILOT_MODEL` | `gpt-5` |
| `agent-framework-github-copilot` | `GitHubCopilotAgent` | `GITHUB_COPILOT_TIMEOUT` | `60` |
| `agent-framework-github-copilot` | `GitHubCopilotAgent` | `GITHUB_COPILOT_LOG_LEVEL` | `info` |
| `agent-framework-mem0` | `agent_framework_mem0 package import` | `MEM0_TELEMETRY` | `false` |
| `agent-framework-ollama` | `OllamaChatClient` | `OLLAMA_HOST` | `http://localhost:11434` |
| `agent-framework-ollama` | `OllamaChatClient` | `OLLAMA_MODEL_ID` | `llama3.1:8b` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `OPENAI_API_KEY` | `sk-proj-...` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `OPENAI_MODEL` | `gpt-4o-mini` |
| `agent-framework-openai` | `OpenAIChatClient` | `OPENAI_RESPONSES_MODEL` | `gpt-4.1-mini` |
| `agent-framework-openai` | `OpenAIChatCompletionClient` | `OPENAI_CHAT_MODEL` | `gpt-4o` |
| `agent-framework-openai` | `OpenAIEmbeddingClient` | `OPENAI_EMBEDDING_MODEL` | `text-embedding-3-small` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `OPENAI_BASE_URL` | `https://api.openai.com/v1/` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `OPENAI_ORG_ID` | `org_123456789` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_ENDPOINT` | `https://my-resource.openai.azure.com/` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_API_KEY` | `sk-azure-...` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_API_VERSION` | `2024-10-21` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_BASE_URL` | `https://my-resource.openai.azure.com/openai/v1/` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_DEPLOYMENT_NAME` | `gpt-4o` |
| `agent-framework-openai` | `OpenAIChatClient` | `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` | `gpt-4.1` |
| `agent-framework-openai` | `OpenAIChatCompletionClient` | `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME` | `gpt-4o-mini` |
| `agent-framework-openai` | `OpenAIEmbeddingClient` | `AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME` | `text-embedding-3-large` |
| `agent-framework-openai` | `OpenAIChatClient / OpenAIChatCompletionClient / OpenAIEmbeddingClient` | `AZURE_OPENAI_RESOURCE_URL` | `https://cognitiveservices.azure.com/` |
`agent-framework-openai` supports the Azure OpenAI client-specific deployment aliases listed above; keep
`packages/openai/README.md` as the authoritative reference for the exact fallback order and package-specific
behavior.
**Note for production**: In production environments, set environment variables through your deployment platform (e.g., Azure App Settings, Kubernetes ConfigMaps/Secrets) rather than using `.env` files. The `load_dotenv()` call in samples will have no effect when a `.env` file is not present, allowing environment variables to be loaded from the system.
For Azure authentication, run `az login` before running samples.
python/samples/semantic-kernel-migration/README.md
+4 -4
View File
@@ -14,9 +14,9 @@ This gallery helps Semantic Kernel (SK) developers move to the Microsoft Agent F
### Azure AI agent parity
### OpenAI Assistants API parity
- [01_basic_openai_assistant.py](openai_assistant/01_basic_openai_assistant.py) — Baseline assistant comparison.
- [02_openai_assistant_with_code_interpreter.py](openai_assistant/02_openai_assistant_with_code_interpreter.py) — Code interpreter tool usage.
- [03_openai_assistant_function_tool.py](openai_assistant/03_openai_assistant_function_tool.py) — Custom function tooling.
OpenAI Assistants parity samples were removed alongside the deprecated Python assistants surface and are no longer
part of this migration gallery.
### OpenAI Responses API parity
- [01_basic_responses_agent.py](openai_responses/01_basic_responses_agent.py) — Basic responses agent migration.
@@ -44,7 +44,7 @@ Each script is fully async and the `main()` routine runs both implementations ba
- Python 3.10 or later.
- Access to the necessary model endpoints (Azure OpenAI, OpenAI, Azure AI, Copilot Studio, etc.).
- Installed SDKs: `semantic-kernel` and the Microsoft Agent Framework (`pip install semantic-kernel agent-framework`), or the repo’s editable packages if you are developing locally.
- Service credentials exposed through environment variables (for example `OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_KEY`, or Copilot Studio auth settings).
- Service credentials exposed through environment variables (for example `OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY`, or Copilot Studio auth settings).
## Running Single-Agent Samples
From the repository root:
python/samples/semantic-kernel-migration/openai_assistant/01_basic_openai_assistant.py
-64
View File
@@ -1,64 +0,0 @@
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "semantic-kernel",
# ]
# ///
# Run with any PEP 723 compatible runner, e.g.:
# uv run samples/semantic-kernel-migration/openai_assistant/01_basic_openai_assistant.py
# Copyright (c) Microsoft. All rights reserved.
"""Create an OpenAI Assistant using SK and Agent Framework."""
import asyncio
import os
from agent_framework import Agent
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
ASSISTANT_MODEL = os.environ.get("OPENAI_ASSISTANT_MODEL", "gpt-4o-mini")
async def run_semantic_kernel() -> None:
from semantic_kernel.agents import AssistantAgentThread, OpenAIAssistantAgent
client = OpenAIAssistantAgent.create_client()
# Provision the assistant on the OpenAI Assistants service.
definition = await client.beta.assistants.create(
model=ASSISTANT_MODEL,
name="Helper",
instructions="Answer questions in one concise paragraph.",
)
agent = OpenAIAssistantAgent(client=client, definition=definition)
thread: AssistantAgentThread | None = None
response = await agent.get_response("What is the capital of Denmark?", thread=thread)
thread = response.thread
print("[SK]", response.message.content)
if thread is not None:
print("[SK][thread-id]", thread.id)
async def run_agent_framework() -> None:
from agent_framework.openai import OpenAIAssistantsClient
assistants_client = OpenAIAssistantsClient()
# AF wraps the assistant lifecycle with an async context manager.
async with Agent(
client=assistants_client,
) as assistant_agent:
session = assistant_agent.create_session()
reply = await assistant_agent.run("What is the capital of Denmark?", session=session)
print("[AF]", reply.text)
follow_up = await assistant_agent.run(
"How many residents live there?",
session=session,
)
print("[AF][follow-up]", follow_up.text)
async def main() -> None:
await run_semantic_kernel()
await run_agent_framework()
if __name__ == "__main__":
asyncio.run(main())
python/samples/semantic-kernel-migration/openai_assistant/02_openai_assistant_with_code_interpreter.py
-74
View File
@@ -1,74 +0,0 @@
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "semantic-kernel",
# ]
# ///
# Run with any PEP 723 compatible runner, e.g.:
# uv run samples/semantic-kernel-migration/openai_assistant/02_openai_assistant_with_code_interpreter.py
# Copyright (c) Microsoft. All rights reserved.
"""Enable the code interpreter tool for OpenAI Assistants in SK and AF."""
import asyncio
from agent_framework import Agent
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
async def run_semantic_kernel() -> None:
from semantic_kernel.agents import OpenAIAssistantAgent
from semantic_kernel.connectors.ai.open_ai import OpenAISettings
client = OpenAIAssistantAgent.create_client()
code_interpreter_tool, code_interpreter_tool_resources = OpenAIAssistantAgent.configure_code_interpreter_tool()
# Enable the hosted code interpreter tool on the assistant definition.
definition = await client.beta.assistants.create(
model=OpenAISettings().chat_model_id,
name="CodeRunner",
instructions="Run the provided request as code and return the result.",
tools=code_interpreter_tool,
tool_resources=code_interpreter_tool_resources,
)
agent = OpenAIAssistantAgent(client=client, definition=definition)
response = await agent.get_response(
"Use Python to calculate the mean of [41, 42, 45] and explain the steps.",
)
print(f"[SK]: {response}")
async def run_agent_framework() -> None:
from agent_framework.openai import OpenAIAssistantsClient
assistants_client = OpenAIAssistantsClient()
# Create code interpreter tool using static method
code_interpreter_tool = OpenAIAssistantsClient.get_code_interpreter_tool()
# AF exposes the same tool configuration via create_agent.
async with Agent(client=assistants_client,
name="CodeRunner",
instructions="Use the code interpreter when calculations are required.",
model="gpt-4.1",
tools=[code_interpreter_tool],
) as assistant_agent:
response = await assistant_agent.run(
"Use Python to calculate the mean of [41, 42, 45] and explain the steps.",
tool_choice="auto",
)
print(f"[AF]: {response.text}")
async def main() -> None:
await run_semantic_kernel()
await run_agent_framework()
if __name__ == "__main__":
asyncio.run(main())
python/samples/semantic-kernel-migration/openai_assistant/03_openai_assistant_function_tool.py
-103
View File
@@ -1,103 +0,0 @@
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "semantic-kernel",
# ]
# ///
# Run with any PEP 723 compatible runner, e.g.:
# uv run samples/semantic-kernel-migration/openai_assistant/03_openai_assistant_function_tool.py
# Copyright (c) Microsoft. All rights reserved.
"""Implement a function tool for OpenAI Assistants in SK and AF."""
import asyncio
import os
from typing import Any
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
ASSISTANT_MODEL = os.environ.get("OPENAI_ASSISTANT_MODEL", "gpt-4o-mini")
async def fake_weather_lookup(city: str, day: str) -> dict[str, Any]:
"""Pretend to call a weather service."""
return {
"city": city,
"day": day,
"forecast": "Sunny with scattered clouds",
"high_c": 22,
"low_c": 14,
}
async def run_semantic_kernel() -> None:
from semantic_kernel.agents import AssistantAgentThread, OpenAIAssistantAgent
from semantic_kernel.functions import kernel_function
class WeatherPlugin:
@kernel_function(name="get_forecast", description="Look up the forecast for a city and day.")
async def fake_weather_lookup(self, city: str, day: str) -> dict[str, Any]:
"""Pretend to call a weather service."""
return {
"city": city,
"day": day,
"forecast": "Sunny with scattered clouds",
"high_c": 22,
"low_c": 14,
}
client = OpenAIAssistantAgent.create_client()
# Tool schema is registered on the assistant definition.
definition = await client.beta.assistants.create(
model=ASSISTANT_MODEL,
name="WeatherHelper",
instructions="Call get_forecast to fetch weather details.",
)
agent = OpenAIAssistantAgent(client=client, definition=definition, plugins=[WeatherPlugin()])
thread: AssistantAgentThread | None = None
response = await agent.get_response(
"What will the weather be like in Seattle tomorrow?",
thread=thread,
)
thread = response.thread
print("[SK][initial]", response.message.content)
async def run_agent_framework() -> None:
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIAssistantsClient
@tool(
name="get_forecast",
description="Look up the forecast for a city and day.",
)
async def get_forecast(city: str, day: str) -> dict[str, Any]:
return await fake_weather_lookup(city, day)
assistants_client = OpenAIAssistantsClient()
# AF converts the decorated function into an assistant-compatible tool.
async with Agent(client=assistants_client,
name="WeatherHelper",
instructions="Call get_forecast to fetch weather details.",
model=ASSISTANT_MODEL,
tools=[get_forecast],
) as assistant_agent:
reply = await assistant_agent.run(
"What will the weather be like in Seattle tomorrow?",
tool_choice="auto",
)
print("[AF]", reply.text)
async def main() -> None:
await run_semantic_kernel()
await run_agent_framework()
if __name__ == "__main__":
asyncio.run(main())
python/samples/semantic-kernel-migration/openai_responses/01_basic_responses_agent.py
+3 -3
View File
@@ -36,11 +36,11 @@ async def run_semantic_kernel() -> None:
async def run_agent_framework() -> None:
from agent_framework import Agent
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
# AF Agent can swap in an OpenAIResponsesClient directly.
# AF Agent can swap in an OpenAIChatClient directly.
chat_agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
instructions="Answer in one concise sentence.",
name="Expert",
)
python/samples/semantic-kernel-migration/openai_responses/02_responses_agent_with_tool.py
+2 -2
View File
@@ -43,14 +43,14 @@ async def run_semantic_kernel() -> None:
async def run_agent_framework() -> None:
from agent_framework import Agent, tool
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
@tool(name="add", description="Add two numbers")
async def add(a: float, b: float) -> float:
return a + b
chat_agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
instructions="Use the add tool when math is required.",
name="MathExpert",
# AF registers the async function as a tool at construction.
python/samples/semantic-kernel-migration/openai_responses/03_responses_agent_structured_output.py
+2 -2
View File
@@ -46,10 +46,10 @@ async def run_semantic_kernel() -> None:
async def run_agent_framework() -> None:
from agent_framework import Agent
from agent_framework.openai import OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
chat_agent = Agent(
client=OpenAIResponsesClient(),
client=OpenAIChatClient(),
instructions="Return launch briefs as structured JSON.",
name="ProductMarketer",
)
python/samples/semantic-kernel-migration/orchestrations/concurrent_basic.py
+2 -2
View File
@@ -16,7 +16,7 @@ from collections.abc import Sequence
from typing import cast
from agent_framework import Agent, Message
from agent_framework.azure import AzureOpenAIChatClient
from agent_framework.openai import OpenAIChatCompletionClient
from agent_framework.orchestrations import ConcurrentBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -89,7 +89,7 @@ def _print_semantic_kernel_outputs(outputs: Sequence[ChatMessageContent]) -> Non
async def run_agent_framework_example(prompt: str) -> Sequence[list[Message]]:
client = AzureOpenAIChatClient(credential=AzureCliCredential())
client = OpenAIChatCompletionClient(credential=AzureCliCredential())
physics = Agent(client=client,
instructions=("You are an expert in physics. Answer questions from a physics perspective."),
python/samples/semantic-kernel-migration/orchestrations/magentic.py
+3 -3
View File
@@ -15,7 +15,7 @@ import asyncio
from collections.abc import Sequence
from agent_framework import Agent
from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient
from agent_framework.openai import OpenAIChatClient
from agent_framework.orchestrations import MagenticBuilder
from dotenv import load_dotenv
from semantic_kernel.agents import (
@@ -141,8 +141,8 @@ async def run_agent_framework_example(prompt: str) -> str | None:
)
# Create code interpreter tool using static method
coder_client = OpenAIResponsesClient()
code_interpreter_tool = OpenAIResponsesClient.get_code_interpreter_tool()
coder_client = OpenAIChatClient()
code_interpreter_tool = OpenAIChatClient.get_code_interpreter_tool()
coder = Agent(
name="CoderAgent",
python/samples/semantic-kernel-migration/orchestrations/sequential.py
+2 -2
View File
@@ -16,7 +16,7 @@ from collections.abc import Sequence
from typing import cast
from agent_framework import Agent, Message
from agent_framework.azure import AzureOpenAIChatClient
from agent_framework.openai import OpenAIChatCompletionClient
from agent_framework.orchestrations import SequentialBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -76,7 +76,7 @@ async def sk_agent_response_callback(
async def run_agent_framework_example(prompt: str) -> list[Message]:
client = AzureOpenAIChatClient(credential=AzureCliCredential())
client = OpenAIChatCompletionClient(credential=AzureCliCredential())
writer = Agent(client=client,
instructions=("You are a concise copywriter. Provide a single, punchy marketing sentence based on the prompt."),