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

Python: [BREAKING] Standardize model selection on model (#4999)

Browse Source 
* Refactor Anthropic model option and provider clients

Rename the Anthropic client model option from model_id to model, add provider-specific Anthropic wrappers for Foundry, Bedrock, and Vertex, and expose them through the Anthropic, Foundry, Amazon, and Google namespaces. Update core option handling, docs, samples, and tests accordingly.

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

* Fix Anthropic skills sample typing

Cast the Anthropic beta client to Any in the skills sample so the pre-commit sample pyright check no longer fails on beta skills and files endpoints that are not exposed by the current SDK stubs.

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

* undo sample mypy

* Retry CI after transient external failures

Retrigger PR validation after an unrelated Copilot review workflow SAML failure and a transient external tau2 git fetch failure in the Windows Python test setup.

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

* Address review feedback on model option merging

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

* Address Anthropic compatibility review feedback

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

* moved all to `model`

* fixes for azure ai search

* Python: standardize remaining sample env var names

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

* Python: fix foundry-local pyright compatibility

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

* updated env vars in cicd

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Eduard van Valkenburg
2026-04-01 21:00:18 +02:00
committed by GitHub
Unverified
parent 95550dd0dc
commit 6acab3d1d6
184 changed files with 1749 additions and 1025 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/02-agents/chat_client/README.md
+4 -4
View File
@@ -51,7 +51,7 @@ Depending on the selected client, set the appropriate environment variables:
**For Azure OpenAI clients (`azure_openai_responses` and `azure_openai_chat_completion`):**
- `AZURE_OPENAI_ENDPOINT`: Your Azure OpenAI endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The Azure OpenAI deployment used by the sample
- `AZURE_OPENAI_MODEL`: 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`
@@ -66,13 +66,13 @@ Depending on the selected client, set the appropriate environment variables:
**For Anthropic client (`anthropic`):**
- `ANTHROPIC_API_KEY`: Your Anthropic API key
- `ANTHROPIC_CHAT_MODEL_ID`: The Anthropic model ID (for example, `claude-sonnet-4-5`)
- `ANTHROPIC_CHAT_MODEL`: The Anthropic model to use (for example, `claude-sonnet-4-5`)
**For Ollama client (`ollama`):**
- `OLLAMA_HOST`: Ollama server URL (defaults to `http://localhost:11434` if unset)
- `OLLAMA_MODEL_ID`: Ollama model name (for example, `mistral`, `qwen2.5:8b`)
- `OLLAMA_MODEL`: Ollama model name (for example, `mistral`, `qwen2.5:8b`)
**For Bedrock client (`bedrock`):**
- `BEDROCK_CHAT_MODEL_ID`: Bedrock model ID (for example, `anthropic.claude-3-5-sonnet-20240620-v1:0`)
- `BEDROCK_CHAT_MODEL`: Bedrock model ID (for example, `anthropic.claude-3-5-sonnet-20240620-v1:0`)
- `BEDROCK_REGION`: AWS region (defaults to `us-east-1` if unset)
- AWS credentials via standard environment variables (for example, `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`)
python/samples/02-agents/chat_client/chat_response_cancellation.py
+1 -1
View File
@@ -24,7 +24,7 @@ async def main() -> None:
Creates a task for the chat request, waits briefly, then cancels it to show proper cleanup.
Configuration:
- OpenAI model ID: Use "model_id" parameter or "OPENAI_MODEL" environment variable
- OpenAI model ID: Use "model" parameter or "OPENAI_MODEL" environment variable
- OpenAI API key: Use "api_key" parameter or "OPENAI_API_KEY" environment variable
"""
client = FoundryChatClient(credential=AzureCliCredential())
python/samples/02-agents/chat_client/custom_chat_client.py
+2 -2
View File
@@ -102,7 +102,7 @@ class EchoingChatClient(BaseChatClient[OptionsT]):
response = ChatResponse(
messages=[response_message],
model_id="echo-model-v1",
model="echo-model-v1",
response_id=f"echo-resp-{random.randint(1000, 9999)}",
)
@@ -120,7 +120,7 @@ class EchoingChatClient(BaseChatClient[OptionsT]):
contents=[Content.from_text(char)],
role="assistant",
response_id=f"echo-stream-resp-{random.randint(1000, 9999)}",
model_id="echo-model-v1",
model="echo-model-v1",
)
await asyncio.sleep(stream_delay_seconds)
python/samples/02-agents/compaction/tiktoken_tokenizer.py
+3 -3
View File
@@ -33,9 +33,9 @@ Key components:
class TiktokenTokenizer(TokenizerProtocol):
"""TokenizerProtocol implementation backed by tiktoken's o200k_base (gpt-4.1 and up default) encoding."""
def __init__(self, *, encoding_name: str = "o200k_base", model_name: str | None = None) -> None:
if model_name is not None:
self._encoding = tiktoken.encoding_for_model(model_name)
def __init__(self, *, encoding_name: str = "o200k_base", model: str | None = None) -> None:
if model is not None:
self._encoding = tiktoken.encoding_for_model(model)
else:
self._encoding: Any = tiktoken.get_encoding(encoding_name)
python/samples/02-agents/context_providers/azure_ai_foundry_memory.py
+2 -2
View File
@@ -33,7 +33,7 @@ rather than chat history. The memory store is deleted at the end of the run.
Prerequisites:
1. Set FOUNDRY_PROJECT_ENDPOINT environment variable
2. Set FOUNDRY_MODEL for the chat/responses model
3. Set AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME for the embedding model
3. Set AZURE_OPENAI_EMBEDDING_MODEL for the embedding model
4. Deploy both a chat model (e.g. gpt-4) and an embedding model (e.g. text-embedding-3-small)
"""
load_dotenv()
@@ -55,7 +55,7 @@ async def main() -> None:
)
memory_store_definition = MemoryStoreDefaultDefinition(
chat_model=os.environ["FOUNDRY_MODEL"],
embedding_model=os.environ["AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME"],
embedding_model=os.environ["AZURE_OPENAI_EMBEDDING_MODEL"],
options=options,
)
print(f"Creating memory store '{memory_store_name}'...")
python/samples/02-agents/context_providers/azure_ai_search/search_context_semantic.py
+2 -2
View File
@@ -32,7 +32,7 @@ Prerequisites:
- AZURE_SEARCH_INDEX_NAME: Your search index name
- FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
- 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_EMBEDDING_MODEL: (Optional) Your Azure OpenAI embedding deployment for hybrid search
- AZURE_OPENAI_ENDPOINT: (Optional) Your Azure OpenAI resource URL, required if using Azure OpenAI embeddings
"""
@@ -56,7 +56,7 @@ async def main() -> None:
project_endpoint = os.environ["FOUNDRY_PROJECT_ENDPOINT"]
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")
embedding_deployment = os.environ.get("AZURE_OPENAI_EMBEDDING_MODEL")
embedding_client = None
if openai_endpoint and embedding_deployment:
python/samples/02-agents/declarative/README.md
+2 -2
View File
@@ -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.
python/samples/02-agents/devui/.env.example
+2 -2
View File
@@ -8,8 +8,8 @@ FOUNDRY_MODEL=gpt-4o
# Azure OpenAI workflow sample
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_RESPONSES_MODEL=gpt-4o
# Optional fallback env name also supported by workflow_with_agents/workflow.py:
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_MODEL=gpt-4o
# Optional if you need to override the default API version:
AZURE_OPENAI_API_VERSION=2024-10-21
python/samples/02-agents/devui/README.md
+3 -3
View File
@@ -94,7 +94,7 @@ workflow_name/
| Sample | What it demonstrates | Required keys / auth |
| ------ | -------------------- | -------------------- |
| [**workflow_declarative/**](workflow_declarative/) | A YAML-defined workflow loaded through `WorkflowFactory`, with nested age-based branching and no model client code. | None |
| [**workflow_with_agents/**](workflow_with_agents/) | A content review workflow that uses agents as executors and routes based on structured review output (`Writer -> Reviewer -> Editor/Publisher -> Summarizer`). | `AZURE_OPENAI_ENDPOINT`, plus `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` or `AZURE_OPENAI_DEPLOYMENT_NAME`; Azure CLI auth via `az login`; `AZURE_OPENAI_API_VERSION` is optional |
| [**workflow_with_agents/**](workflow_with_agents/) | A content review workflow that uses agents as executors and routes based on structured review output (`Writer -> Reviewer -> Editor/Publisher -> Summarizer`). | `AZURE_OPENAI_ENDPOINT`, plus `AZURE_OPENAI_RESPONSES_MODEL` or `AZURE_OPENAI_MODEL`; Azure CLI auth via `az login`; `AZURE_OPENAI_API_VERSION` is optional |
| [**workflow_spam/**](workflow_spam/) | A multi-step spam detection workflow with human-in-the-loop approval, branching for spam vs. legitimate messages, and a final reporting step. | None |
| [**workflow_fanout/**](workflow_fanout/) | A larger fan-out/fan-in data processing workflow with parallel validation, multiple transformations, QA, aggregation, and demo failure toggles. | None |
@@ -130,8 +130,8 @@ export FOUNDRY_MODEL="gpt-4o"
# Azure OpenAI workflow_with_agents sample
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com"
export AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o"
export AZURE_OPENAI_RESPONSES_MODEL="gpt-4o"
export AZURE_OPENAI_MODEL="gpt-4o"
az login
```
python/samples/02-agents/devui/workflow_with_agents/.env.example
+2 -2
View File
@@ -2,8 +2,8 @@
# This sample uses Azure CLI auth, so run `az login` before starting DevUI.
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_RESPONSES_MODEL=gpt-4o
# Optional fallback env name also supported by the client:
# AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
# AZURE_OPENAI_MODEL=gpt-4o
# Optional if you need to override the default API version:
AZURE_OPENAI_API_VERSION=2024-10-21
python/samples/02-agents/devui/workflow_with_agents/workflow.py
+1 -1
View File
@@ -65,7 +65,7 @@ def is_approved(message: Any) -> bool:
# Create Azure OpenAI Responses chat client
client = OpenAIChatClient(
model=os.environ.get("AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME") or os.environ.get("AZURE_OPENAI_DEPLOYMENT_NAME"),
model=os.environ.get("AZURE_OPENAI_RESPONSES_MODEL") or os.environ.get("AZURE_OPENAI_MODEL"),
azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"),
api_version=os.environ.get("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),
python/samples/02-agents/embeddings/azure_ai_inference_embeddings.py
+3 -3
View File
@@ -31,9 +31,9 @@ Prerequisites:
- AZURE_AI_INFERENCE_ENDPOINT: Your Azure AI model inference endpoint URL, for instance:
https://<apim-instance>.azure-api.net/<foundry-instance>/models
- AZURE_AI_INFERENCE_API_KEY: Your API key
- AZURE_AI_INFERENCE_EMBEDDING_MODEL_ID: The text embedding model name
- AZURE_AI_INFERENCE_EMBEDDING_MODEL: The text embedding model name
(e.g. "text-embedding-3-small")
- AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL_ID: The image embedding model name
- AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL: The image embedding model name
(e.g. "Cohere-embed-v3-english")
"""
@@ -49,7 +49,7 @@ async def main() -> None:
result = await client.get_embeddings([image_content])
print(f"Image embedding dimensions: {result[0].dimensions}")
print(f"First 5 values: {result[0].vector[:5]}")
print(f"Model: {result[0].model_id}")
print(f"Model: {result[0].model}")
print(f"Usage: {result.usage}")
print()
python/samples/02-agents/embeddings/azure_openai_embeddings.py
+2 -2
View File
@@ -14,7 +14,7 @@ from dotenv import load_dotenv
Prerequisites:
Set the following environment variables or add them to a local ``.env`` file:
- ``AZURE_OPENAI_ENDPOINT``: Your Azure OpenAI endpoint URL
- ``AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME``: The embedding deployment name
- ``AZURE_OPENAI_EMBEDDING_MODEL``: The embedding deployment name
- ``AZURE_OPENAI_API_VERSION``: Optional API version override
Sign in with ``az login`` before running the sample.
@@ -27,7 +27,7 @@ async def main() -> None:
"""Generate embeddings with Azure OpenAI."""
async with AzureCliCredential() as credential:
client = OpenAIEmbeddingClient(
model=os.getenv("AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME"),
model=os.getenv("AZURE_OPENAI_EMBEDDING_MODEL"),
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
credential=credential,
python/samples/02-agents/evaluation/evaluate_with_expected.py
+1 -1
View File
@@ -41,7 +41,7 @@ def response_matches_expected(response: str, expected_output: str) -> float:
async def main() -> None:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/02-agents/multimodal_input/README.md
+2 -2
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_DEPLOYMENT_NAME`: The name of your Azure OpenAI chat model deployment
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your Azure OpenAI responses model deployment
- `AZURE_OPENAI_MODEL`: The name of your Azure OpenAI chat model deployment
- `AZURE_OPENAI_MODEL`: 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`)
python/samples/02-agents/multimodal_input/azure_chat_multimodal.py
+1 -1
View File
@@ -23,7 +23,7 @@ async def test_image() -> None:
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option. Requires AZURE_OPENAI_ENDPOINT and FOUNDRY_MODEL
# environment variables to be set.
# Alternatively, you can pass deployment_name explicitly:
# Alternatively, you can pass model explicitly:
# client = FoundryChatClient(credential=AzureCliCredential(), model="your-deployment-name")
client = FoundryChatClient(credential=AzureCliCredential())
image_uri = create_sample_image()
python/samples/02-agents/multimodal_input/azure_responses_multimodal.py
+1 -1
View File
@@ -32,7 +32,7 @@ async def test_image() -> None:
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option. Requires AZURE_OPENAI_ENDPOINT and FOUNDRY_MODEL
# environment variables to be set.
# Alternatively, you can pass deployment_name explicitly:
# Alternatively, you can pass model explicitly:
# client = FoundryChatClient(credential=AzureCliCredential(), model="your-deployment-name")
client = FoundryChatClient(credential=AzureCliCredential())
python/samples/02-agents/providers/amazon/README.md
+2 -2
View File
@@ -1,7 +1,7 @@
# Bedrock Examples
This folder contains examples demonstrating how to use AWS Bedrock models with the Agent Framework. The sample
uses `BEDROCK_CHAT_MODEL_ID`, `BEDROCK_REGION`, and AWS credentials (`AWS_ACCESS_KEY_ID`,
uses `BEDROCK_CHAT_MODEL`, `BEDROCK_REGION`, and AWS credentials (`AWS_ACCESS_KEY_ID`,
`AWS_SECRET_ACCESS_KEY`, optional `AWS_SESSION_TOKEN`).
## Examples
@@ -12,6 +12,6 @@ uses `BEDROCK_CHAT_MODEL_ID`, `BEDROCK_REGION`, and AWS credentials (`AWS_ACCESS
## Environment Variables
- `BEDROCK_CHAT_MODEL_ID`: Bedrock model ID (for example, `anthropic.claude-3-5-sonnet-20240620-v1:0`)
- `BEDROCK_CHAT_MODEL`: Bedrock model ID (for example, `anthropic.claude-3-5-sonnet-20240620-v1:0`)
- `BEDROCK_REGION`: AWS region (defaults to `us-east-1` if unset)
- AWS credentials via standard variables (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, optional `AWS_SESSION_TOKEN`)
python/samples/02-agents/providers/amazon/bedrock_chat_client.py
+1 -1
View File
@@ -17,7 +17,7 @@ Bedrock Chat Client Example
This sample demonstrates using `BedrockChatClient` with an agent and a simple tool.
Environment variables used:
- `BEDROCK_CHAT_MODEL_ID`
- `BEDROCK_CHAT_MODEL`
- `BEDROCK_REGION` (defaults to `us-east-1` if unset)
- AWS credentials via standard variables (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`,
optional `AWS_SESSION_TOKEN`)
python/samples/02-agents/providers/anthropic/README.md
+2 -2
View File
@@ -28,14 +28,14 @@ This folder contains examples demonstrating how to use Anthropic's Claude models
### Anthropic Client
- `ANTHROPIC_API_KEY`: Your Anthropic API key (get one from [Anthropic Console](https://console.anthropic.com/))
- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use (e.g., `claude-haiku-4-5`, `claude-sonnet-4-5-20250929`)
- `ANTHROPIC_CHAT_MODEL`: The Claude model to use (e.g., `claude-haiku-4-5`, `claude-sonnet-4-5-20250929`)
### Foundry
- `ANTHROPIC_FOUNDRY_API_KEY`: Your Foundry Anthropic API key
- `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`)
- `ANTHROPIC_CHAT_MODEL`: The Claude model to use in Foundry (e.g., `claude-haiku-4-5`)
### Claude Agent
python/samples/02-agents/providers/anthropic/anthropic_basic.py
+2 -2
View File
@@ -35,7 +35,7 @@ async def non_streaming_example() -> None:
print("=== Non-streaming Response Example ===")
agent = Agent(
client=AnthropicClient(model_id="claude-sonnet-4-5-20250929"),
client=AnthropicClient(model="claude-sonnet-4-5-20250929"),
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
@@ -52,7 +52,7 @@ async def streaming_example() -> None:
print("=== Streaming Response Example ===")
agent = Agent(
client=AnthropicClient(model_id="claude-sonnet-4-5-20250929"),
client=AnthropicClient(model="claude-sonnet-4-5-20250929"),
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
python/samples/02-agents/providers/anthropic/anthropic_foundry.py
+3 -4
View File
@@ -2,8 +2,7 @@
import asyncio
from agent_framework import Agent
from agent_framework.anthropic import AnthropicClient
from anthropic import AsyncAnthropicFoundry
from agent_framework.foundry import AnthropicFoundryClient
from dotenv import load_dotenv
# Load environment variables from .env file
@@ -27,14 +26,14 @@ To use the Foundry integration ensure you have the following environment variabl
- 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
- ANTHROPIC_CHAT_MODEL
Should be something like claude-haiku-4-5
"""
async def main() -> None:
"""Example of streaming response (get results as they are generated)."""
client = AnthropicClient(anthropic_client=AsyncAnthropicFoundry())
client = AnthropicFoundryClient()
# Create MCP tool configuration using instance method
mcp_tool = client.get_mcp_tool(
python/samples/02-agents/providers/anthropic/anthropic_skills.py
+2 -2
View File
@@ -29,7 +29,7 @@ async def main() -> None:
client = AnthropicClient[AnthropicChatOptions](additional_beta_flags=["skills-2025-10-02"])
# List Anthropic-managed Skills
skills = await client.anthropic_client.beta.skills.list(source="anthropic", betas=["skills-2025-10-02"])
skills = await client.anthropic_client.beta.skills.list(source="anthropic", betas=["skills-2025-10-02"]) # type: ignore
for skill in skills.data:
print(f"{skill.source}: {skill.id} (version: {skill.latest_version})")
@@ -81,7 +81,7 @@ async def main() -> None:
# Since I'm using the pptx skill, the files will be PowerPoint presentations
print("Generated files:")
for idx, file in enumerate(files):
file_content = await client.anthropic_client.beta.files.download(
file_content = await client.anthropic_client.beta.files.download( # type: ignore
file_id=file.file_id, betas=["files-api-2025-04-14"]
)
with open(Path(__file__).parent / f"python_programming-{idx}.pptx", "wb") as f:
python/samples/02-agents/providers/azure/README.md
+1 -1
View File
@@ -26,7 +26,7 @@ This folder contains Azure-backed samples for the generic OpenAI clients in
Set these before running the Azure provider samples:
- `AZURE_OPENAI_ENDPOINT`
- `AZURE_OPENAI_DEPLOYMENT_NAME`
- `AZURE_OPENAI_MODEL`
Optionally, you can also set:
python/samples/02-agents/providers/azure/openai_chat_completion_client_basic.py
+2 -2
View File
@@ -38,7 +38,7 @@ async def non_streaming_example() -> None:
agent = Agent(
client=OpenAIChatCompletionClient(
model=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
model=os.getenv("AZURE_OPENAI_MODEL"),
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),
@@ -60,7 +60,7 @@ async def streaming_example() -> None:
agent = Agent(
client=OpenAIChatCompletionClient(
model=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
model=os.getenv("AZURE_OPENAI_MODEL"),
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),
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_DEPLOYMENT_NAME"],
model=os.environ["AZURE_OPENAI_MODEL"],
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
credential=AzureCliCredential(),
),
python/samples/02-agents/providers/azure/openai_client_basic.py
+2 -2
View File
@@ -38,7 +38,7 @@ async def non_streaming_example() -> None:
agent = Agent(
client=OpenAIChatClient(
model=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
model=os.getenv("AZURE_OPENAI_MODEL"),
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),
@@ -60,7 +60,7 @@ async def streaming_example() -> None:
agent = Agent(
client=OpenAIChatClient(
model=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
model=os.getenv("AZURE_OPENAI_MODEL"),
azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
credential=AzureCliCredential(),
python/samples/02-agents/providers/foundry/README.md
+1 -1
View File
@@ -45,4 +45,4 @@ This folder contains Azure AI Foundry and Foundry Local samples for Agent Framew
### Environment Variables
- `FOUNDRY_LOCAL_MODEL_ID`: Optional model alias/ID to use by default when `model_id` is not passed to `FoundryLocalClient`.
- `FOUNDRY_LOCAL_MODEL`: Optional model alias/ID to use by default when `model` is not passed to `FoundryLocalClient`.
python/samples/02-agents/providers/ollama/README.md
+2 -2
View File
@@ -40,8 +40,8 @@ Set the following environment variables:
- `OLLAMA_HOST`: The base URL for your Ollama server (optional, defaults to `http://localhost:11434`)
- Example: `export OLLAMA_HOST="http://localhost:11434"`
- `OLLAMA_MODEL_ID`: The model name to use
- Example: `export OLLAMA_MODEL_ID="qwen2.5:8b"`
- `OLLAMA_MODEL`: The model name to use
- Example: `export OLLAMA_MODEL="qwen2.5:8b"`
- Must be a model you have pulled with Ollama
### For OpenAI Client with Ollama (`ollama_with_openai_chat_client.py`)
python/samples/02-agents/providers/ollama/ollama_agent_basic.py
+1 -1
View File
@@ -17,7 +17,7 @@ This sample demonstrates implementing a Ollama agent with basic tool usage.
Ensure to install Ollama and have a model running locally before running the sample
Not all Models support function calling, to test function calling try llama3.2 or qwen3:4b
Set the model to use via the OLLAMA_MODEL_ID environment variable or modify the code below.
Set the model to use via the OLLAMA_MODEL environment variable or modify the code below.
https://ollama.com/
"""
python/samples/02-agents/providers/ollama/ollama_agent_reasoning.py
+1 -1
View File
@@ -16,7 +16,7 @@ This sample demonstrates implementing a Ollama agent with reasoning.
Ensure to install Ollama and have a model running locally before running the sample
Not all Models support reasoning, to test reasoning try qwen3:8b
Set the model to use via the OLLAMA_MODEL_ID environment variable or modify the code below.
Set the model to use via the OLLAMA_MODEL environment variable or modify the code below.
https://ollama.com/
"""
python/samples/02-agents/providers/ollama/ollama_chat_client.py
+1 -1
View File
@@ -17,7 +17,7 @@ This sample demonstrates using the native Ollama Chat Client directly.
Ensure to install Ollama and have a model running locally before running the sample.
Not all Models support function calling, to test function calling try llama3.2
Set the model to use via the OLLAMA_MODEL_ID environment variable or modify the code below.
Set the model to use via the OLLAMA_MODEL environment variable or modify the code below.
https://ollama.com/
"""
python/samples/02-agents/providers/ollama/ollama_chat_multimodal.py
+1 -1
View File
@@ -16,7 +16,7 @@ This sample demonstrates implementing a Ollama agent with multimodal input capab
Ensure to install Ollama and have a model running locally before running the sample
Not all Models support multimodal input, to test multimodal input try gemma3:4b
Set the model to use via the OLLAMA_MODEL_ID environment variable or modify the code below.
Set the model to use via the OLLAMA_MODEL environment variable or modify the code below.
https://ollama.com/
"""
python/samples/02-agents/skills/code_defined_skill/README.md
+1 -1
View File
@@ -28,7 +28,7 @@ code_defined_skill/
Set the required environment variables in a `.env` file (see `python/.env.example`):
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `AZURE_OPENAI_MODEL`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/skills/file_based_skill/README.md
+1 -1
View File
@@ -48,7 +48,7 @@ file_based_skill/
Set the required environment variables in a `.env` file (see `python/.env.example`):
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `AZURE_OPENAI_MODEL`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/skills/mixed_skills/README.md
+1 -1
View File
@@ -61,7 +61,7 @@ Set environment variables (or create a `.env` file):
```
FOUNDRY_PROJECT_ENDPOINT=https://your-project.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o-mini
AZURE_OPENAI_MODEL=gpt-4o-mini
```
Authenticate with Azure CLI:
python/samples/02-agents/skills/script_approval/README.md
+1 -1
View File
@@ -29,7 +29,7 @@ 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`):
- `FOUNDRY_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
- `AZURE_OPENAI_DEPLOYMENT_NAME`: The name of your model deployment (defaults to `gpt-4o-mini`)
- `AZURE_OPENAI_MODEL`: The name of your model deployment (defaults to `gpt-4o-mini`)
### Authentication
python/samples/02-agents/typed_options.py
+4 -4
View File
@@ -38,7 +38,7 @@ async def demo_anthropic_chat_client() -> None:
print("\n=== Anthropic ChatClient with TypedDict Options ===\n")
# Create Anthropic client
client = AnthropicClient(model_id="claude-sonnet-4-5-20250929")
client = AnthropicClient(model="claude-sonnet-4-5-20250929")
# Standard options work great:
response = await client.get_response(
@@ -53,14 +53,14 @@ async def demo_anthropic_chat_client() -> None:
)
print(f"Anthropic Response: {response.text}")
print(f"Model used: {response.model_id}")
print(f"Model used: {response.model}")
async def demo_anthropic_agent() -> None:
"""Demonstrate Agent with Anthropic client and typed options."""
print("\n=== Agent with Anthropic and Typed Options ===\n")
client = AnthropicClient(model_id="claude-sonnet-4-5-20250929")
client = AnthropicClient(model="claude-sonnet-4-5-20250929")
# Create a typed agent for Anthropic - IDE knows Anthropic-specific options!
agent = Agent(
@@ -129,7 +129,7 @@ async def demo_openai_chat_client_reasoning_models() -> None:
)
print(f"OpenAI Response: {response.text}")
print(f"Model used: {response.model_id}")
print(f"Model used: {response.model}")
async def demo_openai_agent() -> None:
python/samples/04-hosting/a2a/a2a_server.py
+3 -3
View File
@@ -67,12 +67,12 @@ def main() -> None:
# Validate environment
project_endpoint = os.getenv("FOUNDRY_PROJECT_ENDPOINT")
deployment_name = os.getenv("FOUNDRY_MODEL")
model = os.getenv("FOUNDRY_MODEL")
if not project_endpoint:
print("Error: FOUNDRY_PROJECT_ENDPOINT environment variable is not set.")
sys.exit(1)
if not deployment_name:
if not model:
print("Error: FOUNDRY_MODEL environment variable is not set.")
sys.exit(1)
@@ -80,7 +80,7 @@ def main() -> None:
credential = AzureCliCredential()
client = FoundryChatClient(
project_endpoint=project_endpoint,
model=deployment_name,
model=model,
credential=credential,
)
python/samples/04-hosting/azure_functions/02_multi_agent/function_app.py
+1 -1
View File
@@ -7,7 +7,7 @@ Components used in this sample:
- AgentFunctionApp to register multiple agents and expose dedicated HTTP endpoints.
- Custom tool functions to demonstrate tool invocation from different agents.
Prerequisites: set `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT_NAME`, and sign in with Azure CLI before starting the Functions host."""
Prerequisites: set `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_MODEL`, and sign in with Azure CLI before starting the Functions host."""
import logging
from typing import Any
python/samples/04-hosting/azure_functions/11_workflow_parallel/.env.template
+1 -1
View File
@@ -10,4 +10,4 @@ TASKHUB_NAME=default
# Azure OpenAI Configuration
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=your-deployment-name
AZURE_OPENAI_MODEL=your-deployment-name
python/samples/04-hosting/azure_functions/11_workflow_parallel/README.md
+1 -1
View File
@@ -99,7 +99,7 @@ The sample can run locally without Azure Functions infrastructure using DevUI:
```
2. Configure `.env` with your Azure OpenAI credentials (`AZURE_OPENAI_ENDPOINT` and
`AZURE_OPENAI_DEPLOYMENT_NAME`)
`AZURE_OPENAI_MODEL`)
3. Install dependencies:
```bash
python/samples/04-hosting/azure_functions/11_workflow_parallel/function_app.py
+2 -2
View File
@@ -21,7 +21,7 @@ Key architectural points:
- Mixed agent/executor fan-outs execute concurrently
Prerequisites:
- Configure `AZURE_OPENAI_ENDPOINT` and `AZURE_OPENAI_DEPLOYMENT_NAME`
- Configure `AZURE_OPENAI_ENDPOINT` and `AZURE_OPENAI_MODEL`
- Sign in with Azure CLI (`az login`) for `AzureCliCredential`
- Ensure Azurite and the Durable Task Scheduler emulator are running
"""
@@ -362,7 +362,7 @@ def _create_workflow() -> Workflow:
credential = AzureCliCredential()
chat_client = OpenAIChatCompletionClient(
model=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
model=os.environ["AZURE_OPENAI_MODEL"],
api_key=get_bearer_token_provider(credential, "https://cognitiveservices.azure.com/.default"),
)
python/samples/04-hosting/azure_functions/11_workflow_parallel/local.settings.json.sample
+1 -1
View File
@@ -6,6 +6,6 @@
"DURABLE_TASK_SCHEDULER_CONNECTION_STRING": "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None",
"TASKHUB_NAME": "default",
"AZURE_OPENAI_ENDPOINT": "<AZURE_OPENAI_ENDPOINT>",
"AZURE_OPENAI_DEPLOYMENT_NAME": "<AZURE_OPENAI_DEPLOYMENT_NAME>"
"AZURE_OPENAI_MODEL": "<AZURE_OPENAI_MODEL>"
}
}
python/samples/04-hosting/durabletask/02_multi_agent/client.py
+1 -1
View File
@@ -8,7 +8,7 @@ each with their own specialized capabilities and tools.
Prerequisites:
- The worker must be running with both agents registered
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME when running the worker
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL when running the worker
- Sign in with Azure CLI for AzureCliCredential authentication
- Durable Task Scheduler must be running
"""
python/samples/04-hosting/durabletask/02_multi_agent/sample.py
+1 -1
View File
@@ -5,7 +5,7 @@ This sample demonstrates running both the worker and client in a single process
for multiple agents with different tools. The worker registers two agents
(WeatherAgent and MathAgent), each with their own specialized capabilities.
Prerequisites:
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL
- Sign in with Azure CLI for AzureCliCredential authentication
- Durable Task Scheduler must be running (e.g., using Docker)
To run this sample:
python/samples/04-hosting/durabletask/02_multi_agent/worker.py
+1 -1
View File
@@ -7,7 +7,7 @@ with their own specialized tools. This demonstrates how to host multiple agents
with different capabilities in a single worker process.
Prerequisites:
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL
- Sign in with Azure CLI for AzureCliCredential authentication
- Start a Durable Task Scheduler (e.g., using Docker)
"""
python/samples/04-hosting/durabletask/06_multi_agent_orchestration_conditionals/README.md
+1 -1
View File
@@ -17,7 +17,7 @@ See the [README.md](../README.md) file in the parent directory for more informat
This sample uses Azure OpenAI credentials:
- `AZURE_OPENAI_ENDPOINT`
- `AZURE_OPENAI_DEPLOYMENT_NAME`
- `AZURE_OPENAI_MODEL`
## Running the Sample
python/samples/04-hosting/durabletask/06_multi_agent_orchestration_conditionals/client.py
+1 -1
View File
@@ -7,7 +7,7 @@ that uses conditional logic to either handle spam emails or draft professional r
Prerequisites:
- The worker must be running with both agents, orchestration, and activities registered
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL
- Sign in with Azure CLI for AzureCliCredential authentication
- Durable Task Scheduler must be running
"""
python/samples/04-hosting/durabletask/06_multi_agent_orchestration_conditionals/sample.py
+1 -1
View File
@@ -10,7 +10,7 @@ The orchestration branches based on spam detection results, calling different
activity functions to handle spam or send legitimate email responses.
Prerequisites:
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL
- Sign in with Azure CLI for AzureCliCredential authentication
- Durable Task Scheduler must be running (e.g., using Docker)
python/samples/04-hosting/durabletask/06_multi_agent_orchestration_conditionals/worker.py
+3 -3
View File
@@ -7,7 +7,7 @@ orchestration function that routes execution based on spam detection results. Ac
handle side effects (spam handling and email sending).
Prerequisites:
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_DEPLOYMENT_NAME
- Set AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_MODEL
- Sign in with Azure CLI for AzureCliCredential authentication
- Start a Durable Task Scheduler (e.g., using Docker)
"""
@@ -69,7 +69,7 @@ def create_spam_agent() -> "Agent":
"""
return Agent(
client=OpenAIChatCompletionClient(
model=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
model=os.environ["AZURE_OPENAI_MODEL"],
api_key=get_async_bearer_token_provider(
AsyncAzureCliCredential(), "https://cognitiveservices.azure.com/.default"
),
@@ -87,7 +87,7 @@ def create_email_agent() -> "Agent":
"""
return Agent(
client=OpenAIChatCompletionClient(
model=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
model=os.environ["AZURE_OPENAI_MODEL"],
api_key=get_async_bearer_token_provider(
AsyncAzureCliCredential(), "https://cognitiveservices.azure.com/.default"
),
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_DEPLOYMENT_NAME="gpt-4o"
export AZURE_OPENAI_MODEL="gpt-4o"
```
3. **Authenticate with Azure:**
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_agent_sample.py
+1 -1
View File
@@ -10,7 +10,7 @@ See ``evaluate_tool_calls_sample.py`` for tool-call accuracy evaluation.
Prerequisites:
- An Azure AI Foundry project with a deployed model
- Set FOUNDRY_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME in .env
- Set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL in .env
"""
import asyncio
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_mixed_sample.py
+1 -1
View File
@@ -48,7 +48,7 @@ async def main() -> None:
# 1. Set up the chat client
chat_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_multiturn_sample.py
+2 -2
View File
@@ -11,7 +11,7 @@ a different aspect of agent behavior:
Prerequisites:
- An Azure AI Foundry project with a deployed model
- Set FOUNDRY_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME in .env
- Set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL in .env
"""
import asyncio
@@ -94,7 +94,7 @@ def print_split(item: EvalItem, split: ConversationSplit = ConversationSplit.LAS
async def main() -> None:
chat_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_tool_calls_sample.py
+2 -2
View File
@@ -7,7 +7,7 @@ by using ``FoundryEvals.evaluate()`` with ``TOOL_CALL_ACCURACY``.
Prerequisites:
- An Azure AI Foundry project with a deployed model
- Set FOUNDRY_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME in .env
- Set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL in .env
"""
import asyncio
@@ -39,7 +39,7 @@ def get_flight_price(origin: str, destination: str) -> str:
async def main() -> None:
chat_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_traces_sample.py
+2 -2
View File
@@ -13,7 +13,7 @@ Prerequisites:
- An Azure AI Foundry project with a deployed model
- Response IDs from prior agent runs (for Pattern 1)
- OTel traces exported to App Insights (for Pattern 2)
- Set FOUNDRY_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME in .env
- Set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL in .env
"""
import asyncio
@@ -30,7 +30,7 @@ async def main() -> None:
# 1. Set up the chat client
chat_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/evaluation/foundry_evals/evaluate_workflow_sample.py
+2 -2
View File
@@ -11,7 +11,7 @@ breakdown in sub_results so you can identify which agent is underperforming.
Prerequisites:
- An Azure AI Foundry project with a deployed model
- Set FOUNDRY_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME in .env
- Set FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL in .env
"""
import asyncio
@@ -46,7 +46,7 @@ async def main() -> None:
# 1. Set up the chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ.get("AZURE_AI_MODEL_DEPLOYMENT_NAME", "gpt-4o"),
model=os.environ.get("FOUNDRY_MODEL", "gpt-4o"),
credential=AzureCliCredential(),
)
python/samples/05-end-to-end/evaluation/red_teaming/.env.example
+1 -1
View File
@@ -1,6 +1,6 @@
# Azure OpenAI Configuration (for the agent being tested)
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_MODEL=gpt-4o
# AZURE_OPENAI_API_KEY=your-api-key-here
# Azure AI Project Configuration (for red teaming)
python/samples/05-end-to-end/evaluation/red_teaming/README.md
+1 -1
View File
@@ -43,7 +43,7 @@ Create a `.env` file in this directory or set these environment variables:
```bash
# Azure OpenAI (for the agent being tested)
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
AZURE_OPENAI_MODEL=gpt-4o
# AZURE_OPENAI_API_KEY is optional if using Azure CLI authentication
# Azure AI Project (for red teaming)
python/samples/05-end-to-end/evaluation/red_teaming/red_team_agent_sample.py
+1 -1
View File
@@ -51,7 +51,7 @@ async def main() -> None:
credential = AzureCliCredential()
# Create the agent
# Constructor automatically reads from environment variables:
# AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_DEPLOYMENT_NAME, AZURE_OPENAI_API_KEY
# AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_MODEL, AZURE_OPENAI_API_KEY
agent = Agent(
client=FoundryChatClient(credential=credential),
name="FinancialAdvisor",
python/samples/05-end-to-end/hosted_agents/README.md
+1 -1
View File
@@ -76,7 +76,7 @@ Example `.env` for Azure OpenAI samples:
```dotenv
AZURE_OPENAI_ENDPOINT=https://<your-openai-resource>.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4.1
AZURE_OPENAI_MODEL=gpt-4.1
```
Example `.env` for Foundry project samples:
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_DEPLOYMENT_NAME
- name: AZURE_OPENAI_MODEL
value: "{{chat}}"
resources:
- kind: model
python/samples/05-end-to-end/hosted_agents/agent_with_local_tools/.env.sample
+2 -2
View File
@@ -1,3 +1,3 @@
# IMPORTANT: Never commit .env to version control - add it to .gitignore
PROJECT_ENDPOINT=
MODEL_DEPLOYMENT_NAME=
FOUNDRY_PROJECT_ENDPOINT=
FOUNDRY_MODEL=
python/samples/05-end-to-end/hosted_agents/agent_with_local_tools/README.md
+6 -6
View File
@@ -59,24 +59,24 @@ Before running this sample, ensure you have:
Set the following environment variables (matching `agent.yaml`):
- `PROJECT_ENDPOINT` - Your Microsoft Foundry project endpoint URL (required)
- `MODEL_DEPLOYMENT_NAME` - The deployment name for your chat model (defaults to `gpt-4.1-mini`)
- `FOUNDRY_PROJECT_ENDPOINT` - Your Microsoft Foundry project endpoint URL (required)
- `FOUNDRY_MODEL` - The deployment name for your chat model (defaults to `gpt-4.1-mini`)
This sample loads environment variables from a local `.env` file if present.
Create a `.env` file in this directory with the following content:
```
PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
MODEL_DEPLOYMENT_NAME=gpt-4.1-mini
FOUNDRY_PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
FOUNDRY_MODEL=gpt-4.1-mini
```
Or set them via PowerShell:
```powershell
# Replace with your actual values
$env:PROJECT_ENDPOINT="https://<your-resource>.services.ai.azure.com/api/projects/<your-project>"
$env:MODEL_DEPLOYMENT_NAME="gpt-4.1-mini"
$env:FOUNDRY_PROJECT_ENDPOINT="https://<your-resource>.services.ai.azure.com/api/projects/<your-project>"
$env:FOUNDRY_MODEL="gpt-4.1-mini"
```
### Running the Sample
python/samples/05-end-to-end/hosted_agents/agent_with_local_tools/agent.yaml
+4 -4
View File
@@ -21,7 +21,7 @@ protocols:
- protocol: responses
version: v1
environment_variables:
- name: PROJECT_ENDPOINT
value: ${PROJECT_ENDPOINT}
- name: MODEL_DEPLOYMENT_NAME
value: ${MODEL_DEPLOYMENT_NAME}
- name: FOUNDRY_PROJECT_ENDPOINT
value: ${FOUNDRY_PROJECT_ENDPOINT}
- name: FOUNDRY_MODEL
value: ${FOUNDRY_MODEL}
python/samples/05-end-to-end/hosted_agents/agent_with_local_tools/main.py
+4 -6
View File
@@ -18,10 +18,8 @@ from azure.identity.aio import AzureCliCredential, ManagedIdentityCredential
# Configure these for your Foundry project
# Read the explicit variables present in the .env file
PROJECT_ENDPOINT = os.getenv("PROJECT_ENDPOINT") # e.g., "https://<project>.services.ai.azure.com"
MODEL_DEPLOYMENT_NAME = os.getenv(
"MODEL_DEPLOYMENT_NAME", "gpt-4.1-mini"
) # Your model deployment name e.g., "gpt-4.1-mini"
FOUNDRY_PROJECT_ENDPOINT = os.getenv("FOUNDRY_PROJECT_ENDPOINT") # e.g., "https://<project>.services.ai.azure.com"
FOUNDRY_MODEL = os.getenv("FOUNDRY_MODEL", "gpt-4.1-mini") # Your model deployment name e.g., "gpt-4.1-mini"
# Simulated hotel data for Seattle
@@ -116,8 +114,8 @@ async def main():
"""Main function to run the agent as a web server."""
async with get_credential() as credential:
client = FoundryChatClient(
project_endpoint=PROJECT_ENDPOINT,
model=MODEL_DEPLOYMENT_NAME,
project_endpoint=FOUNDRY_PROJECT_ENDPOINT,
model=FOUNDRY_MODEL,
credential=credential,
)
agent = Agent(
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_DEPLOYMENT_NAME
- name: AZURE_OPENAI_MODEL
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_DEPLOYMENT_NAME
- name: AZURE_OPENAI_MODEL
value: "{{chat}}"
resources:
- kind: model
python/samples/05-end-to-end/hosted_agents/writer_reviewer_agents_in_workflow/.env.sample
+2 -2
View File
@@ -1,3 +1,3 @@
# IMPORTANT: Never commit .env to version control - add it to .gitignore
PROJECT_ENDPOINT=
MODEL_DEPLOYMENT_NAME=
FOUNDRY_PROJECT_ENDPOINT=
FOUNDRY_MODEL=
python/samples/05-end-to-end/hosted_agents/writer_reviewer_agents_in_workflow/README.md
+6 -6
View File
@@ -56,24 +56,24 @@ Before running this sample, ensure you have:
Set the following environment variables (matching `agent.yaml`):
- `PROJECT_ENDPOINT` - Your Microsoft Foundry project endpoint URL (required)
- `MODEL_DEPLOYMENT_NAME` - The deployment name for your chat model (defaults to `gpt-4.1-mini`)
- `FOUNDRY_PROJECT_ENDPOINT` - Your Microsoft Foundry project endpoint URL (required)
- `FOUNDRY_MODEL` - The deployment name for your chat model (defaults to `gpt-4.1-mini`)
This sample loads environment variables from a local `.env` file if present.
Create a `.env` file in this directory with the following content:
```
PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
MODEL_DEPLOYMENT_NAME=gpt-4.1-mini
FOUNDRY_PROJECT_ENDPOINT=https://<your-resource>.services.ai.azure.com/api/projects/<your-project>
FOUNDRY_MODEL=gpt-4.1-mini
```
Or set them via PowerShell:
```powershell
# Replace with your actual values
$env:PROJECT_ENDPOINT="https://<your-resource>.services.ai.azure.com/api/projects/<your-project>"
$env:MODEL_DEPLOYMENT_NAME="gpt-4.1-mini"
$env:FOUNDRY_PROJECT_ENDPOINT="https://<your-resource>.services.ai.azure.com/api/projects/<your-project>"
$env:FOUNDRY_MODEL="gpt-4.1-mini"
```
### Running the Sample
python/samples/05-end-to-end/hosted_agents/writer_reviewer_agents_in_workflow/agent.yaml
+4 -4
View File
@@ -18,7 +18,7 @@ protocols:
- protocol: responses
version: v1
environment_variables:
- name: PROJECT_ENDPOINT
value: ${PROJECT_ENDPOINT}
- name: MODEL_DEPLOYMENT_NAME
value: ${MODEL_DEPLOYMENT_NAME}
- name: FOUNDRY_PROJECT_ENDPOINT
value: ${FOUNDRY_PROJECT_ENDPOINT}
- name: FOUNDRY_MODEL
value: ${FOUNDRY_MODEL}
python/samples/05-end-to-end/hosted_agents/writer_reviewer_agents_in_workflow/main.py
+7 -9
View File
@@ -14,12 +14,10 @@ load_dotenv(override=True)
# Configure these for your Foundry project
# Read the explicit variables present in the .env file
PROJECT_ENDPOINT = os.getenv(
"PROJECT_ENDPOINT"
FOUNDRY_PROJECT_ENDPOINT = os.getenv(
"FOUNDRY_PROJECT_ENDPOINT"
) # e.g., "https://<project>.services.ai.azure.com/api/projects/<project-name>"
MODEL_DEPLOYMENT_NAME = os.getenv(
"MODEL_DEPLOYMENT_NAME", "gpt-4.1-mini"
) # Your model deployment name e.g., "gpt-4.1-mini"
FOUNDRY_MODEL = os.getenv("FOUNDRY_MODEL", "gpt-4.1-mini") # Your model deployment name e.g., "gpt-4.1-mini"
def get_credential():
@@ -31,8 +29,8 @@ def get_credential():
async def create_agents():
async with get_credential() as credential:
client = FoundryChatClient(
project_endpoint=PROJECT_ENDPOINT,
model=MODEL_DEPLOYMENT_NAME,
project_endpoint=FOUNDRY_PROJECT_ENDPOINT,
model=FOUNDRY_MODEL,
credential=credential,
)
writer = Agent(
@@ -60,8 +58,8 @@ async def main() -> None:
The writer and reviewer multi-agent workflow.
Environment variables required:
- PROJECT_ENDPOINT: Your Microsoft Foundry project endpoint
- MODEL_DEPLOYMENT_NAME: Your Microsoft Foundry model deployment name
- FOUNDRY_PROJECT_ENDPOINT: Your Microsoft Foundry project endpoint
- FOUNDRY_MODEL: Your Microsoft Foundry model deployment name
"""
async with create_agents() as (writer, reviewer):
python/samples/05-end-to-end/purview_agent/README.md
+1 -1
View File
@@ -18,7 +18,7 @@ This getting-started sample shows how to attach Microsoft Purview policy evaluat
| Variable | Required | Purpose |
|----------|----------|---------|
| `AZURE_OPENAI_ENDPOINT` | Yes | Azure OpenAI endpoint (https://<name>.openai.azure.com) |
| `AZURE_OPENAI_DEPLOYMENT_NAME` | Optional | Model deployment name (defaults inside SDK if omitted) |
| `AZURE_OPENAI_MODEL` | Optional | Model deployment name (defaults inside SDK if omitted) |
| `PURVIEW_CLIENT_APP_ID` | Yes* | Client (application) ID used for Purview authentication |
| `PURVIEW_USE_CERT_AUTH` | Optional (`true`/`false`) | Switch between certificate and interactive auth |
| `PURVIEW_TENANT_ID` | Yes (when cert auth on) | Tenant ID for certificate authentication |
python/samples/05-end-to-end/purview_agent/sample_purview_agent.py
+5 -5
View File
@@ -12,7 +12,7 @@ Note: Caching is automatic and enabled by default.
Environment variables:
- AZURE_OPENAI_ENDPOINT (required)
- AZURE_OPENAI_DEPLOYMENT_NAME (optional, defaults to gpt-4o-mini)
- AZURE_OPENAI_MODEL (optional, defaults to gpt-4o-mini)
- PURVIEW_CLIENT_APP_ID (required)
- PURVIEW_USE_CERT_AUTH (optional, set to "true" for certificate auth)
- PURVIEW_TENANT_ID (required if certificate auth)
@@ -143,7 +143,7 @@ async def run_with_agent_middleware() -> None:
print("Skipping run: AZURE_OPENAI_ENDPOINT not set")
return
deployment = os.environ.get("AZURE_OPENAI_DEPLOYMENT_NAME", "gpt-4o-mini")
deployment = os.environ.get("AZURE_OPENAI_MODEL", "gpt-4o-mini")
user_id = os.environ.get("PURVIEW_DEFAULT_USER_ID")
client = FoundryChatClient(model=deployment, endpoint=endpoint, credential=AzureCliCredential())
@@ -179,7 +179,7 @@ async def run_with_chat_middleware() -> None:
print("Skipping chat middleware run: AZURE_OPENAI_ENDPOINT not set")
return
deployment = os.environ.get("AZURE_OPENAI_DEPLOYMENT_NAME", default="gpt-4o-mini")
deployment = os.environ.get("AZURE_OPENAI_MODEL", default="gpt-4o-mini")
user_id = os.environ.get("PURVIEW_DEFAULT_USER_ID")
client = FoundryChatClient(
@@ -229,7 +229,7 @@ async def run_with_custom_cache_provider() -> None:
print("Skipping custom cache provider run: AZURE_OPENAI_ENDPOINT not set")
return
deployment = os.environ.get("AZURE_OPENAI_DEPLOYMENT_NAME", "gpt-4o-mini")
deployment = os.environ.get("AZURE_OPENAI_MODEL", "gpt-4o-mini")
user_id = os.environ.get("PURVIEW_DEFAULT_USER_ID")
client = FoundryChatClient(model=deployment, endpoint=endpoint, credential=AzureCliCredential())
@@ -269,7 +269,7 @@ async def run_with_custom_cache_provider() -> None:
print("Skipping default cache run: AZURE_OPENAI_ENDPOINT not set")
return
deployment = os.environ.get("AZURE_OPENAI_DEPLOYMENT_NAME", "gpt-4o-mini")
deployment = os.environ.get("AZURE_OPENAI_MODEL", "gpt-4o-mini")
user_id = os.environ.get("PURVIEW_DEFAULT_USER_ID")
client = FoundryChatClient(model=deployment, endpoint=endpoint, credential=AzureCliCredential())
python/samples/05-end-to-end/workflow_evaluation/create_workflow.py
+6 -6
View File
@@ -145,14 +145,14 @@ class ResearchLead(Executor):
async def run_workflow_with_response_tracking(
query: str, client: FoundryChatClient | None = None, deployment_name: str | None = None
query: str, client: FoundryChatClient | None = None, model: str | None = None
) -> dict:
"""Run multi-agent workflow and track conversation IDs, response IDs, and interaction sequence.
Args:
query: The user query to process through the multi-agent workflow
client: Optional FoundryChatClient instance
deployment_name: Optional model deployment name for the workflow agents
model: Optional model for the workflow agents
Returns:
Dictionary containing interaction sequence, conversation/response IDs, and conversation analysis
@@ -166,7 +166,7 @@ async def run_workflow_with_response_tracking(
)
async with project_client:
client = FoundryChatClient(project_client=project_client, model=deployment_name)
client = FoundryChatClient(project_client=project_client, model=model)
return await _run_workflow_with_client(query, client)
except Exception as e:
print(f"Error during workflow execution: {e}")
@@ -347,11 +347,11 @@ def _track_agent_ids(event, agent, response_ids, conversation_ids):
conversation_ids[agent].append(raw.conversation_id)
async def create_and_run_workflow(deployment_name: str | None = None):
async def create_and_run_workflow(model: str | None = None):
"""Run the workflow evaluation and display results.
Args:
deployment_name: Optional model deployment name for the workflow agents
model: Optional model for the workflow agents
Returns:
Dictionary containing agents data with conversation IDs, response IDs, and query information
@@ -365,7 +365,7 @@ async def create_and_run_workflow(deployment_name: str | None = None):
query = example_queries[0]
print(f"Query: {query}\n")
result = await run_workflow_with_response_tracking(query, model=deployment_name)
result = await run_workflow_with_response_tracking(query, model=model)
# Create output data structure
output_data = {"agents": {}, "query": result["query"], "output": result.get("output", "")}
python/samples/05-end-to-end/workflow_evaluation/run_evaluation.py
+9 -9
View File
@@ -46,11 +46,11 @@ def print_section(title: str):
print(f"{'=' * 80}")
async def run_workflow(deployment_name: str | None = None) -> dict[str, Any]:
async def run_workflow(model: str | None = None) -> dict[str, Any]:
"""Execute the multi-agent travel planning workflow.
Args:
deployment_name: Optional model deployment name for the workflow agents
model: Optional model for the workflow agents
Returns:
Dictionary containing workflow data with agent response IDs
@@ -58,7 +58,7 @@ async def run_workflow(deployment_name: str | None = None) -> dict[str, Any]:
print("Executing multi-agent travel planning workflow...")
print("This may take a few minutes...")
workflow_data = await create_and_run_workflow(model=deployment_name)
workflow_data = await create_and_run_workflow(model=model)
print("Workflow execution completed")
return workflow_data
@@ -97,9 +97,9 @@ def fetch_agent_responses(openai_client: OpenAI, workflow_data: dict[str, Any],
print(f" Error: {e}")
def create_evaluation(openai_client: OpenAI, deployment_name: str | None = "gpt-5.2") -> EvalCreateResponse:
def create_evaluation(openai_client: OpenAI, model: str | None = "gpt-5.2") -> EvalCreateResponse:
"""Create evaluation with multiple evaluators."""
deployment_name = os.environ.get("FOUNDRY_MODEL", deployment_name)
model = os.environ.get("FOUNDRY_MODEL", model)
data_source_config = {"type": "azure_ai_source", "scenario": "responses"}
testing_criteria = [
@@ -107,25 +107,25 @@ def create_evaluation(openai_client: OpenAI, deployment_name: str | None = "gpt-
"type": "azure_ai_evaluator",
"name": "relevance",
"evaluator_name": "builtin.relevance",
"initialization_parameters": {"deployment_name": deployment_name},
"initialization_parameters": {"deployment_name": model},
},
{
"type": "azure_ai_evaluator",
"name": "groundedness",
"evaluator_name": "builtin.groundedness",
"initialization_parameters": {"deployment_name": deployment_name},
"initialization_parameters": {"deployment_name": model},
},
{
"type": "azure_ai_evaluator",
"name": "tool_call_accuracy",
"evaluator_name": "builtin.tool_call_accuracy",
"initialization_parameters": {"deployment_name": deployment_name},
"initialization_parameters": {"deployment_name": model},
},
{
"type": "azure_ai_evaluator",
"name": "tool_output_utilization",
"evaluator_name": "builtin.tool_output_utilization",
"initialization_parameters": {"deployment_name": deployment_name},
"initialization_parameters": {"deployment_name": model},
},
]
python/samples/README.md
+10 -10
View File
@@ -91,11 +91,11 @@ 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-anthropic` | `AnthropicClient` | `ANTHROPIC_CHAT_MODEL` | `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` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_EMBEDDING_MODEL` | `text-embedding-3-small` |
| `agent-framework-azure-ai` | `AzureAIInferenceEmbeddingClient` | `AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL` | `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` |
@@ -105,9 +105,9 @@ variable.
| `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` | `BedrockChatClient` | `BEDROCK_CHAT_MODEL` | `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` | `BedrockEmbeddingClient` | `BEDROCK_EMBEDDING_MODEL` | `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...` |
@@ -141,7 +141,7 @@ variable.
| `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-ollama` | `OllamaChatClient` | `OLLAMA_MODEL` | `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` |
@@ -153,10 +153,10 @@ variable.
| `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_MODEL` | `gpt-4o` |
| `agent-framework-openai` | `OpenAIChatClient` | `AZURE_OPENAI_RESPONSES_MODEL` | `gpt-4.1` |
| `agent-framework-openai` | `OpenAIChatCompletionClient` | `AZURE_OPENAI_CHAT_MODEL` | `gpt-4o-mini` |
| `agent-framework-openai` | `OpenAIEmbeddingClient` | `AZURE_OPENAI_EMBEDDING_MODEL` | `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
python/samples/semantic-kernel-migration/openai_responses/01_basic_responses_agent.py
+2 -2
View File
@@ -23,12 +23,12 @@ async def run_semantic_kernel() -> None:
from semantic_kernel.connectors.ai.open_ai import OpenAISettings
openai_settings = OpenAISettings()
assert openai_settings.responses_model_id is not None, "Responses model ID must be set in OpenAISettings"
assert openai_settings.responses_model is not None, "Responses model ID must be set in OpenAISettings"
client = OpenAIResponsesAgent.create_client()
# SK response agents wrap OpenAI's hosted Responses API.
agent = OpenAIResponsesAgent(
ai_model_id=openai_settings.responses_model_id,
ai_model=openai_settings.responses_model,
client=client,
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
@@ -29,12 +29,12 @@ async def run_semantic_kernel() -> None:
return a + b
openai_settings = OpenAISettings()
assert openai_settings.responses_model_id is not None, "Responses model ID must be set in OpenAISettings"
assert openai_settings.responses_model is not None, "Responses model ID must be set in OpenAISettings"
client = OpenAIResponsesAgent.create_client()
# Plugins advertise callable tools to the Responses agent.
agent = OpenAIResponsesAgent(
ai_model_id=openai_settings.responses_model_id,
ai_model=openai_settings.responses_model,
client=client,
instructions="Use the add tool when math is required.",
name="MathExpert",
python/samples/semantic-kernel-migration/openai_responses/03_responses_agent_structured_output.py
+2 -2
View File
@@ -30,12 +30,12 @@ async def run_semantic_kernel() -> None:
from semantic_kernel.connectors.ai.open_ai import OpenAISettings
openai_settings = OpenAISettings()
assert openai_settings.responses_model_id is not None, "Responses model ID must be set in OpenAISettings"
assert openai_settings.responses_model is not None, "Responses model ID must be set in OpenAISettings"
client = OpenAIResponsesAgent.create_client()
# response_format requests schema-constrained output from the model.
agent = OpenAIResponsesAgent(
ai_model_id=openai_settings.responses_model_id,
ai_model=openai_settings.responses_model,
client=client,
instructions="Return launch briefs as structured JSON.",
name="ProductMarketer",
python/samples/semantic-kernel-migration/orchestrations/magentic.py
+3 -3
View File
@@ -54,15 +54,15 @@ async def build_semantic_kernel_agents() -> list[ChatCompletionAgent | OpenAIAss
instructions=(
"You are a Researcher. You find information without additional computation or quantitative analysis."
),
service=OpenAIChatCompletion(ai_model_id="gpt-4o-mini-search-preview"),
service=OpenAIChatCompletion(ai_model="gpt-4o-mini-search-preview"),
)
client = OpenAIAssistantAgent.create_client()
code_interpreter_tool, code_interpreter_tool_resources = OpenAIAssistantAgent.configure_code_interpreter_tool()
openai_settings = OpenAISettings()
model_id = openai_settings.chat_model_id if openai_settings.chat_model_id else "gpt-5"
model = openai_settings.chat_model if openai_settings.chat_model else "gpt-5"
definition = await client.beta.assistants.create( # pyright: ignore[reportDeprecated]
model=model_id,
model=model,
name="CoderAgent",
description="A helpful assistant that writes and executes code to process and analyze data.",
instructions="You solve questions using code. Please provide detailed analysis and computation process.",