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: Fix samples (#4980)

Browse Source 
* First samples 1st batch

* Fix sample paths

* Fix workflow samples

* Fix workflow dependency

* Correct env vars

* Increase idle timeout

* Fix workflows HIL sample

* Fix more workflow samples
This commit is contained in:
Tao Chen
2026-03-31 08:20:35 -07:00
committed by GitHub
Unverified
parent 0f81c277d9
commit 016daf3b98
69 changed files with 234 additions and 306 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/01-get-started/README.md
-7
View File
@@ -9,13 +9,6 @@ concepts of **Agent Framework** one step at a time.
pip install agent-framework --pre
```
Set the required environment variables:
```bash
export AZURE_AI_PROJECT_ENDPOINT="https://your-project-endpoint"
export AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o" # optional, defaults to gpt-4o
```
## Samples
| # | File | What you'll learn |
python/samples/02-agents/compaction/compaction_provider.py
+1 -1
View File
@@ -70,7 +70,7 @@ async def log_model_input(context: ChatContext, call_next: Any) -> None:
async def main() -> None:
client = OpenAIChatClient(model_id="gpt-4o-mini")
client = OpenAIChatClient(model="gpt-4o-mini")
# History provider loads/stores conversation messages in session.state.
# skip_excluded=True means get_messages() will omit messages that were
python/samples/02-agents/context_providers/redis/redis_conversation.py
+2 -2
View File
@@ -25,11 +25,11 @@ from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from agent_framework.redis import RedisContextProvider
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from redisvl.extensions.cache.embeddings import EmbeddingsCache
from redisvl.utils.vectorize import OpenAITextVectorizer
# Copyright (c) Microsoft. All rights reserved.
load_dotenv()
# Default Redis URL for local Redis Stack.
# Override via the REDIS_URL environment variable for remote or authenticated instances.
python/samples/02-agents/typed_options.py
+6 -6
View File
@@ -3,7 +3,7 @@
import asyncio
from typing import Literal
from agent_framework import Agent
from agent_framework import Agent, Message
from agent_framework.anthropic import AnthropicClient
from agent_framework.foundry import FoundryChatClient
from agent_framework.openai import OpenAIChatClient, OpenAIChatOptions
@@ -40,11 +40,11 @@ async def demo_anthropic_chat_client() -> None:
print("\n=== Anthropic ChatClient with TypedDict Options ===\n")
# Create Anthropic client
client = AnthropicClient(model="claude-sonnet-4-5-20250929")
client = AnthropicClient(model_id="claude-sonnet-4-5-20250929")
# Standard options work great:
response = await client.get_response(
"What is the capital of France?",
[Message("user", text="What is the capital of France?")],
options={
"temperature": 0.5,
"max_tokens": 1000,
@@ -62,7 +62,7 @@ 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="claude-sonnet-4-5-20250929")
client = AnthropicClient(model_id="claude-sonnet-4-5-20250929")
# Create a typed agent for Anthropic - IDE knows Anthropic-specific options!
agent = Agent(
@@ -119,12 +119,12 @@ async def demo_openai_chat_client_reasoning_models() -> None:
print("\n=== OpenAI ChatClient with TypedDict Options ===\n")
# Create OpenAI client
client = OpenAIChatClient[OpenAIReasoningChatOptions](model_id="o3")
client = OpenAIChatClient[OpenAIReasoningChatOptions](model="o3")
# With specific options, you get full IDE autocomplete!
# Try typing `client.get_response("Hello", options={` and see the suggestions
response = await client.get_response(
"What is 2 + 2?",
[Message("user", text="What is 2 + 2?")],
options={
"max_tokens": 100,
"allow_multiple_tool_calls": True,
python/samples/03-workflows/README.md
+2 -2
View File
@@ -172,7 +172,7 @@ Workflow and orchestration samples use `AzureOpenAIResponsesClient` rather than
Workflow samples that use `AzureOpenAIResponsesClient` 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/03-workflows/_start-here/step2_agents_in_a_workflow.py
+2 -2
View File
@@ -24,7 +24,7 @@ how agents can be used in a workflow.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be the deployment name of a model in your Foundry project.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, and streaming or non-streaming runs.
"""
@@ -35,7 +35,7 @@ async def main():
# Create the Azure chat client. AzureCliCredential uses your current az login.
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
writer_agent = Agent(
python/samples/03-workflows/_start-here/step3_streaming.py
+2 -2
View File
@@ -23,7 +23,7 @@ how agents can be used in a workflow.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be the deployment name of a model in your Foundry project.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, executors, edges, events, and streaming runs.
"""
@@ -34,7 +34,7 @@ async def main():
# Create the Azure chat client. AzureCliCredential uses your current az login.
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
writer_agent = Agent(
python/samples/03-workflows/agents/azure_ai_agents_streaming.py
+2 -2
View File
@@ -18,7 +18,7 @@ This sample shows how to create agents backed by Azure OpenAI Responses and use
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- AZURE_AI_MODEL_DEPLOYMENT_NAME must be set to your Azure OpenAI model deployment name.
- FOUNDRY_MODEL must be the deployment name of a model in your Foundry project.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, and streaming runs.
"""
@@ -27,7 +27,7 @@ Prerequisites:
async def main() -> None:
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/03-workflows/agents/azure_ai_agents_with_shared_session.py
+2 -2
View File
@@ -39,7 +39,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- AZURE_AI_MODEL_DEPLOYMENT_NAME must be set to your Azure OpenAI model deployment name.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with agents, workflows, and executors in the agent framework.
"""
@@ -60,7 +60,7 @@ async def intercept_agent_response(
async def main() -> None:
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/03-workflows/agents/azure_chat_agents_and_executor.py
+3 -3
View File
@@ -37,7 +37,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Run `az login` before executing.
"""
@@ -104,7 +104,7 @@ async def main() -> None:
research_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(),
),
name="research_agent",
@@ -116,7 +116,7 @@ async def main() -> None:
final_editor_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(),
),
name="final_editor_agent",
python/samples/03-workflows/agents/azure_chat_agents_streaming.py
+3 -3
View File
@@ -18,7 +18,7 @@ This sample shows how to create AzureOpenAI Chat Agents and use them in a workfl
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, and streaming runs.
"""
@@ -29,7 +29,7 @@ async def main():
# Create the agents
_writer_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
writer_agent = Agent(
@@ -42,7 +42,7 @@ async def main():
_reviewer_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
reviewer_agent = Agent(
python/samples/03-workflows/agents/azure_chat_agents_tool_calls_with_feedback.py
+7 -9
View File
@@ -49,7 +49,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Run `az login` before executing.
"""
@@ -122,11 +122,7 @@ class Coordinator(Executor):
# Writer agent response; request human feedback.
# Preserve the full conversation so the final editor
# can see tool traces and the initial prompt.
conversation: list[Message]
if draft.full_conversation is not None:
conversation = list(draft.full_conversation)
else:
conversation = list(draft.agent_response.messages)
conversation = list(draft.full_conversation)
draft_text = draft.agent_response.text.strip()
if not draft_text:
draft_text = "No draft text was produced."
@@ -178,7 +174,7 @@ def create_writer_agent() -> Agent:
return 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(),
),
name="writer_agent",
@@ -188,7 +184,9 @@ def create_writer_agent() -> Agent:
"produce a 3-sentence draft."
),
tools=[fetch_product_brief, get_brand_voice_profile],
tool_choice="required",
default_options={
"tool_choice": "required",
},
)
@@ -197,7 +195,7 @@ def create_final_editor_agent() -> Agent:
return 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(),
),
name="final_editor_agent",
python/samples/03-workflows/agents/concurrent_workflow_as_agent.py
+3 -3
View File
@@ -25,7 +25,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for FoundryChatClient (use az login + env vars)
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Familiarity with Workflow events (WorkflowEvent with type "output")
"""
@@ -34,7 +34,7 @@ async def main() -> None:
# 1) Create three domain agents using FoundryChatClient
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -69,7 +69,7 @@ async def main() -> None:
workflow = ConcurrentBuilder(participants=[researcher, marketer, legal]).build()
# 3) Expose the concurrent workflow as an agent for easy reuse
agent = Agent(client=workflow, name="ConcurrentWorkflowAgent")
agent = workflow.as_agent()
prompt = "We are launching a new budget-friendly electric bike for urban commuters."
agent_response = await agent.run(prompt)
python/samples/03-workflows/agents/custom_agent_executors.py
+3 -3
View File
@@ -33,7 +33,7 @@ Note: When an agent is passed to a workflow, the workflow wraps the agent in a m
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, executors, edges, events, and streaming or non streaming runs.
"""
@@ -54,7 +54,7 @@ class Writer(Executor):
self.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(),
),
instructions=(
@@ -101,7 +101,7 @@ class Reviewer(Executor):
self.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(),
),
instructions=(
python/samples/03-workflows/agents/group_chat_workflow_as_agent.py
+4 -4
View File
@@ -32,7 +32,7 @@ async def main() -> None:
instructions="Gather concise facts that help a teammate answer the question.",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -43,14 +43,14 @@ async def main() -> None:
instructions="Compose clear and structured answers using any notes provided.",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
_orch_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -72,7 +72,7 @@ async def main() -> None:
print(f"Input: {task}\n")
try:
workflow_agent = Agent(client=workflow, name="GroupChatWorkflowAgent")
workflow_agent = workflow.as_agent()
agent_result = await workflow_agent.run(task)
if agent_result.messages:
python/samples/03-workflows/agents/handoff_workflow_as_agent.py
+17 -18
View File
@@ -31,7 +31,7 @@ them to transfer control to each other based on the conversation context.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- `az login` (Azure CLI authentication)
- Environment variables configured for FoundryChatClient (AZURE_AI_MODEL_DEPLOYMENT_NAME)
- Environment variables configured for FoundryChatClient (FOUNDRY_MODEL)
Key Concepts:
- Auto-registered handoff tools: HandoffBuilder automatically creates handoff tools
@@ -159,7 +159,7 @@ async def main() -> None:
# Initialize the Azure OpenAI chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -174,21 +174,20 @@ async def main() -> None:
# Without this, the default behavior continues requesting user input until max_turns
# is reached. Here we use a custom condition that checks if the conversation has ended
# naturally (when one of the agents says something like "you're welcome").
agent = Agent(
client=(
HandoffBuilder(
name="customer_support_handoff",
participants=[triage, refund, order, support],
# Custom termination: Check if one of the agents has provided a closing message.
# This looks for the last message containing "welcome", which indicates the
# conversation has concluded naturally.
termination_condition=lambda conversation: (
len(conversation) > 0 and "welcome" in conversation[-1].text.lower()
),
)
.with_start_agent(triage)
.build()
),
agent = (
HandoffBuilder(
name="customer_support_handoff",
participants=[triage, refund, order, support],
# Custom termination: Check if one of the agents has provided a closing message.
# This looks for the last message containing "welcome", which indicates the
# conversation has concluded naturally.
termination_condition=lambda conversation: (
len(conversation) > 0 and "welcome" in conversation[-1].text.lower()
),
)
.with_start_agent(triage)
.build()
.as_agent()
)
# Scripted user responses for reproducible demo
@@ -226,7 +225,7 @@ async def main() -> None:
responses = {req_id: HandoffAgentUserRequest.create_response(user_response) for req_id in pending_requests}
function_results = [
Content.from_function_result(call_id=req_id, result=response) for req_id, response in responses.items()
Content("function_result", call_id=req_id, result=response) for req_id, response in responses.items()
]
response = await agent.run(Message("tool", function_results))
pending_requests = handle_response_and_requests(response)
python/samples/03-workflows/agents/magentic_workflow_as_agent.py
+5 -5
View File
@@ -23,7 +23,7 @@ like any other agent while still emitting callback telemetry.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI credentials configured for `FoundryChatClient` and `FoundryChatClient`.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -37,7 +37,7 @@ async def main() -> None:
# This agent requires the gpt-4o-search-preview model to perform web searches.
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -45,7 +45,7 @@ async def main() -> None:
# Create code interpreter tool using instance method
coder_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
code_interpreter_tool = coder_client.get_code_interpreter_tool()
@@ -65,7 +65,7 @@ async def main() -> None:
instructions="You coordinate a team to complete complex tasks efficiently.",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -98,7 +98,7 @@ async def main() -> None:
try:
# Wrap the workflow as an agent for composition scenarios
print("\nWrapping workflow as an agent and running...")
workflow_agent = Agent(client=workflow, name="MagenticWorkflowAgent")
workflow_agent = workflow.as_agent()
last_response_id: str | None = None
async for update in workflow_agent.run(task, stream=True):
python/samples/03-workflows/agents/sequential_workflow_as_agent.py
+3 -3
View File
@@ -27,7 +27,7 @@ Note on internal adapters:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI access configured for FoundryChatClient (use az login + env vars)
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -35,7 +35,7 @@ async def main() -> None:
# 1) Create agents
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -55,7 +55,7 @@ async def main() -> None:
workflow = SequentialBuilder(participants=[writer, reviewer]).build()
# 3) Treat the workflow itself as an agent for follow-up invocations
agent = Agent(client=workflow, name="SequentialWorkflowAgent")
agent = workflow.as_agent()
prompt = "Write a tagline for a budget-friendly eBike."
agent_response = await agent.run(prompt)
python/samples/03-workflows/agents/workflow_as_agent_human_in_the_loop.py
+6 -6
View File
@@ -8,7 +8,6 @@ from dataclasses import dataclass
from pathlib import Path
from typing import Any
from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -50,7 +49,7 @@ to the Worker. The workflow completes when idle.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for FoundryChatClient.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Familiarity with WorkflowBuilder, Executor, and WorkflowContext from agent_framework.
- Understanding of request-response message handling in executors.
- (Optional) Review of reflection and escalation patterns, such as those in
@@ -113,14 +112,14 @@ async def main() -> None:
id="worker",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
reviewer = ReviewerWithHumanInTheLoop(worker_id="worker")
agent = Agent(
client=(WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build()),
agent = (
WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build().as_agent()
)
print("Running workflow agent with user query...")
@@ -165,7 +164,8 @@ async def main() -> None:
human_response = ReviewResponse(request_id=request_id, feedback="", approved=True)
# Create the function call result object to send back to the agent.
human_review_function_result = Content.from_function_result(
human_review_function_result = Content(
"function_result",
call_id=human_review_function_call.call_id, # type: ignore
result=human_response,
)
python/samples/03-workflows/agents/workflow_as_agent_kwargs.py
+3 -3
View File
@@ -35,7 +35,7 @@ When to use Agent(client=workflow,):
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -89,7 +89,7 @@ async def main() -> None:
# Create chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -109,7 +109,7 @@ async def main() -> None:
workflow = SequentialBuilder(participants=[agent]).build()
# Expose the workflow as an agent Agent(client=using,)
workflow_agent = Agent(client=workflow, name="WorkflowAgent")
workflow_agent = workflow.as_agent()
# Define custom context that will flow to tools via kwargs
custom_data = {
python/samples/03-workflows/agents/workflow_as_agent_reflection_pattern.py
+5 -6
View File
@@ -6,7 +6,6 @@ from dataclasses import dataclass
from uuid import uuid4
from agent_framework import (
Agent,
AgentResponse,
Executor,
Message,
@@ -41,7 +40,7 @@ Key Concepts Demonstrated:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI account configured and accessible for FoundryChatClient.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Familiarity with WorkflowBuilder, Executor, WorkflowContext, and event handling.
- Understanding of how agent messages are generated, reviewed, and re-submitted.
"""
@@ -198,7 +197,7 @@ async def main() -> None:
id="worker",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -206,13 +205,13 @@ async def main() -> None:
id="reviewer",
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
agent = Agent(
client=(WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build()),
agent = (
WorkflowBuilder(start_executor=worker).add_edge(worker, reviewer).add_edge(reviewer, worker).build().as_agent()
)
print("Running workflow agent with user query...")
python/samples/03-workflows/agents/workflow_as_agent_with_session.py
+5 -5
View File
@@ -38,7 +38,7 @@ Use cases:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for FoundryChatClient
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -46,7 +46,7 @@ async def main() -> None:
# Create a chat client
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -72,7 +72,7 @@ async def main() -> None:
workflow = SequentialBuilder(participants=[assistant, summarizer]).build()
# Wrap the workflow as an agent
agent = Agent(client=workflow, name="ConversationalWorkflowAgent")
agent = workflow.as_agent()
# Create a session to maintain history
session = agent.create_session()
@@ -133,7 +133,7 @@ async def demonstrate_session_serialization() -> None:
"""
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -144,7 +144,7 @@ async def demonstrate_session_serialization() -> None:
)
workflow = SequentialBuilder(participants=[memory_assistant]).build()
agent = Agent(client=workflow, name="MemoryWorkflowAgent")
agent = workflow.as_agent()
# Create initial session and have a conversation
session = agent.create_session()
python/samples/03-workflows/checkpoint/checkpoint_with_human_in_the_loop.py
+1 -1
View File
@@ -182,7 +182,7 @@ def create_workflow(checkpoint_storage: FileCheckpointStorage) -> Workflow:
writer_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(),
),
instructions="Write concise, warm release notes that sound human and helpful.",
python/samples/03-workflows/checkpoint/workflow_as_agent_checkpoint.py
+7 -7
View File
@@ -21,7 +21,7 @@ Key concepts:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured for FoundryChatClient
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
import asyncio
@@ -50,7 +50,7 @@ async def basic_checkpointing() -> None:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -67,7 +67,7 @@ async def basic_checkpointing() -> None:
)
workflow = SequentialBuilder(participants=[assistant, reviewer]).build()
agent = Agent(client=workflow, name="CheckpointedAgent")
agent = workflow.as_agent()
# Create checkpoint storage
checkpoint_storage = InMemoryCheckpointStorage()
@@ -97,7 +97,7 @@ async def checkpointing_with_thread() -> None:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -108,7 +108,7 @@ async def checkpointing_with_thread() -> None:
)
workflow = SequentialBuilder(participants=[assistant]).build()
agent = Agent(client=workflow, name="MemoryAgent")
agent = workflow.as_agent()
# Create both session (for conversation) and checkpoint storage (for workflow state)
session = agent.create_session()
@@ -145,7 +145,7 @@ async def streaming_with_checkpoints() -> None:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
@@ -156,7 +156,7 @@ async def streaming_with_checkpoints() -> None:
)
workflow = SequentialBuilder(participants=[assistant]).build()
agent = Agent(client=workflow, name="StreamingCheckpointAgent")
agent = workflow.as_agent()
checkpoint_storage = InMemoryCheckpointStorage()
python/samples/03-workflows/composition/sub_workflow_kwargs.py
+2 -2
View File
@@ -34,7 +34,7 @@ Key Concepts:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -84,7 +84,7 @@ async def main() -> None:
# Create chat client
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/03-workflows/control-flow/edge_condition.py
+2 -2
View File
@@ -139,7 +139,7 @@ def create_spam_detector_agent() -> Agent:
return 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(),
),
instructions=(
@@ -158,7 +158,7 @@ def create_email_assistant_agent() -> Agent:
return 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(),
),
instructions=(
python/samples/03-workflows/control-flow/multi_selection_edge_group.py
+3 -3
View File
@@ -191,7 +191,7 @@ def create_email_analysis_agent() -> Agent:
return 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(),
),
instructions=(
@@ -209,7 +209,7 @@ def create_email_assistant_agent() -> Agent:
return 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(),
),
instructions=("You are an email assistant that helps users draft responses to emails with professionalism."),
@@ -223,7 +223,7 @@ def create_email_summary_agent() -> Agent:
return 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(),
),
instructions=("You are an assistant that helps users summarize emails."),
python/samples/03-workflows/control-flow/simple_loop.py
+2 -2
View File
@@ -33,7 +33,7 @@ What it does:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure AI/ Azure OpenAI for `FoundryChatClient` agent.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via `azure-identity` — uses `AzureCliCredential()` (run `az login`).
"""
@@ -126,7 +126,7 @@ def create_judge_agent() -> Agent:
return 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(),
),
instructions=("You strictly respond with one of: MATCHED, ABOVE, BELOW based on the given target and guess."),
python/samples/03-workflows/control-flow/switch_case_edge_group.py
+2 -2
View File
@@ -162,7 +162,7 @@ def create_spam_detection_agent() -> Agent:
return 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(),
),
instructions=(
@@ -181,7 +181,7 @@ def create_email_assistant_agent() -> Agent:
return 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(),
),
instructions=("You are an email assistant that helps users draft responses to emails with professionalism."),
python/samples/03-workflows/declarative/agent_to_function_tool/main.py
+1 -1
View File
@@ -204,7 +204,7 @@ async def main():
# Create Azure OpenAI Responses client
chat_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/03-workflows/declarative/customer_support/main.py
+1 -1
View File
@@ -173,7 +173,7 @@ async def main() -> None:
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
# This sample has been tested only on `gpt-5.1` and may not work as intended on other models
# This sample is known to fail on `gpt-5-mini` reasoning input (GH issue #4059)
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
python/samples/03-workflows/declarative/deep_research/main.py
+4 -3
View File
@@ -29,10 +29,11 @@ from agent_framework import Agent
from agent_framework.declarative import WorkflowFactory
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import BaseModel, Field
# Copyright (c) Microsoft. All rights reserved.
# Load environment variables from .env file
load_dotenv()
# Agent Instructions
RESEARCH_INSTRUCTIONS = """In order to help begin addressing the user request, please answer the following pre-survey to the best of your ability.
@@ -126,7 +127,7 @@ async def main() -> None:
# Create Azure OpenAI client
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/03-workflows/declarative/function_tools/main.py
+1 -1
View File
@@ -71,7 +71,7 @@ async def main():
# Create agent with tools
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
menu_agent = Agent(
python/samples/03-workflows/declarative/marketing/main.py
+1 -1
View File
@@ -56,7 +56,7 @@ async def main() -> None:
"""Run the marketing workflow with real Azure AI agents."""
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/03-workflows/declarative/student_teacher/main.py
+5 -3
View File
@@ -16,7 +16,7 @@ Prerequisites:
- Azure OpenAI deployment with chat completion capability
- Environment variables:
FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry Agent Service (V2) project endpoint
AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name
FOUNDRY_MODEL: Your model deployment name
"""
import asyncio
@@ -27,8 +27,10 @@ from agent_framework import Agent
from agent_framework.declarative import WorkflowFactory
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential
from dotenv.main import load_dotenv
# Copyright (c) Microsoft. All rights reserved.
# Load environment variables from .env file
load_dotenv()
STUDENT_INSTRUCTIONS = """You are a curious math student working on understanding mathematical concepts.
@@ -58,7 +60,7 @@ async def main() -> None:
# Create chat client
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/03-workflows/human-in-the-loop/agents_with_HITL.py
+7 -9
View File
@@ -44,7 +44,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Run `az login` before executing.
"""
@@ -78,11 +78,7 @@ class Coordinator(Executor):
# Writer agent response; request human feedback.
# Preserve the full conversation so that the final editor has context.
conversation: list[Message]
if draft.full_conversation is not None:
conversation = list(draft.full_conversation)
else:
conversation = list(draft.agent_response.messages)
conversation = list(draft.full_conversation)
prompt = (
"Review the draft from the writer and provide a short directional note "
@@ -172,18 +168,20 @@ async def main() -> None:
writer_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(),
),
name="writer_agent",
instructions=("You are a marketing writer."),
tool_choice="required",
default_options={
"tool_choice": "required",
},
)
final_editor_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(),
),
name="final_editor_agent",
python/samples/03-workflows/human-in-the-loop/agents_with_approval_requests.py
+2 -2
View File
@@ -53,7 +53,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure AI Agent Service configured, along with the required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, edges, events, request_info events (type='request_info'), and streaming runs.
"""
@@ -228,7 +228,7 @@ async def main() -> None:
email_writer_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(),
),
name="EmailWriter",
python/samples/03-workflows/human-in-the-loop/agents_with_declaration_only_tools.py
+1 -1
View File
@@ -53,7 +53,7 @@ get_user_location = FunctionTool(
async def main() -> None:
_client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
agent = Agent(
python/samples/03-workflows/human-in-the-loop/concurrent_request_info.py
+2 -2
View File
@@ -18,7 +18,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity (run az login before executing)
"""
@@ -151,7 +151,7 @@ async def main() -> None:
global _chat_client
_chat_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/03-workflows/human-in-the-loop/group_chat_request_info.py
+2 -2
View File
@@ -19,7 +19,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity (run az login before executing)
"""
@@ -99,7 +99,7 @@ async def process_event_stream(stream: AsyncIterable[WorkflowEvent]) -> dict[str
async def main() -> None:
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/03-workflows/human-in-the-loop/guessing_game_with_human_input.py
+2 -2
View File
@@ -44,7 +44,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Basic familiarity with WorkflowBuilder, executors, edges, events, and streaming runs.
"""
@@ -200,7 +200,7 @@ async def main() -> None:
guessing_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(),
),
name="GuessingAgent",
python/samples/03-workflows/human-in-the-loop/sequential_request_info.py
+2 -2
View File
@@ -18,7 +18,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity (run az login before executing)
"""
@@ -96,7 +96,7 @@ async def process_event_stream(stream: AsyncIterable[WorkflowEvent]) -> dict[str
async def main() -> None:
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/03-workflows/orchestrations/concurrent_agents.py
+2 -2
View File
@@ -28,7 +28,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Familiarity with Workflow events (WorkflowEvent)
"""
@@ -38,7 +38,7 @@ async def main() -> None:
# 1) Create three domain agents using FoundryChatClient
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/03-workflows/orchestrations/concurrent_custom_agent_executors.py
+2 -2
View File
@@ -38,7 +38,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -109,7 +109,7 @@ class LegalExec(Executor):
async def main() -> None:
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/03-workflows/orchestrations/concurrent_custom_aggregator.py
+2 -2
View File
@@ -30,7 +30,7 @@ Demonstrates:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -38,7 +38,7 @@ Prerequisites:
async def main() -> None:
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/03-workflows/orchestrations/group_chat_agent_manager.py
+2 -2
View File
@@ -27,7 +27,7 @@ What it does:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -45,7 +45,7 @@ async def main() -> None:
# Create a Responses client using Azure OpenAI and Azure CLI credentials for all agents
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/03-workflows/orchestrations/group_chat_philosophical_debate.py
+2 -2
View File
@@ -40,7 +40,7 @@ Participants represent:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -51,7 +51,7 @@ load_dotenv()
def _get_chat_client() -> FoundryChatClient:
return 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/03-workflows/orchestrations/group_chat_simple_selector.py
+2 -2
View File
@@ -26,7 +26,7 @@ What it does:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -42,7 +42,7 @@ async def main() -> None:
# Create a Responses client using Azure OpenAI and Azure CLI credentials for all agents
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/03-workflows/orchestrations/handoff_autonomous.py
+1 -1
View File
@@ -84,7 +84,7 @@ async def main() -> None:
"""Run an autonomous handoff workflow with specialist iteration enabled."""
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
coordinator, research_agent, summary_agent = create_agents(client)
python/samples/03-workflows/orchestrations/handoff_simple.py
+2 -2
View File
@@ -27,7 +27,7 @@ them to transfer control to each other based on the conversation context.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run `az login` before executing the sample.
Key Concepts:
@@ -201,7 +201,7 @@ async def main() -> None:
# Initialize the Azure OpenAI Responses client
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/03-workflows/orchestrations/handoff_with_code_interpreter_file.py
+2 -2
View File
@@ -13,8 +13,8 @@ HandoffBuilder workflows can be properly retrieved.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- `az login` (Azure CLI authentication)
- AZURE_AI_MODEL_DEPLOYMENT_NAME
"""
import asyncio
@@ -93,7 +93,7 @@ async def main() -> None:
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/03-workflows/orchestrations/handoff_with_tool_approval_checkpoint_resume.py
+2 -2
View File
@@ -46,8 +46,8 @@ Pattern:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Azure CLI authentication (az login).
- Environment variables configured for FoundryChatClient.
"""
CHECKPOINT_DIR = Path(__file__).parent / "tmp" / "handoff_checkpoints"
@@ -102,7 +102,7 @@ def create_workflow(checkpoint_storage: FileCheckpointStorage) -> Workflow:
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
triage, refund, order = create_agents(client)
python/samples/03-workflows/orchestrations/magentic.py
+2 -2
View File
@@ -43,7 +43,7 @@ events, and prints the final answer. The workflow completes when idle.
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -54,7 +54,7 @@ load_dotenv()
async def main() -> None:
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/03-workflows/orchestrations/magentic_checkpoint.py
+4 -4
View File
@@ -40,7 +40,7 @@ Concepts highlighted here:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -66,7 +66,7 @@ def build_workflow(checkpoint_storage: FileCheckpointStorage):
instructions=("You are the research lead. Gather crisp bullet points the team should know."),
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -77,7 +77,7 @@ def build_workflow(checkpoint_storage: FileCheckpointStorage):
instructions=("You convert the research notes into a structured brief with milestones and risks."),
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
),
)
@@ -89,7 +89,7 @@ def build_workflow(checkpoint_storage: FileCheckpointStorage):
instructions="You coordinate a team to complete complex tasks efficiently.",
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/03-workflows/orchestrations/magentic_human_plan_review.py
+2 -2
View File
@@ -38,7 +38,7 @@ Plan review options:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -102,7 +102,7 @@ async def process_event_stream(stream: AsyncIterable[WorkflowEvent]) -> dict[str
async def main() -> None:
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/03-workflows/orchestrations/sequential_agents.py
+2 -2
View File
@@ -30,7 +30,7 @@ Note on internal adapters:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -39,7 +39,7 @@ async def main() -> None:
# 1) Create agents
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/03-workflows/orchestrations/sequential_chain_only_agent_responses.py
+13 -10
View File
@@ -3,8 +3,8 @@
import asyncio
import os
from agent_framework import AgentResponseUpdate
from agent_framework.azure import AzureOpenAIResponsesClient
from agent_framework import Agent, AgentResponseUpdate
from agent_framework.foundry import FoundryChatClient
from agent_framework.orchestrations import SequentialBuilder
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
@@ -25,8 +25,8 @@ Compare with `sequential_agents.py`, which uses the default behavior where the f
conversation context is passed to each agent.
Prerequisites:
- AZURE_AI_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for AzureOpenAIResponsesClient with required environment variables.
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_MODEL must be the deployment name of a model in your Foundry project.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -36,23 +36,26 @@ load_dotenv()
async def main() -> None:
# 1) Create agents
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(),
)
writer = client.as_agent(
writer = Agent(
client=client,
instructions="You are a concise copywriter. Provide a single, punchy marketing sentence based on the prompt.",
name="writer",
)
translator = client.as_agent(
translator = Agent(
client=client,
instructions="You are a translator. Translate the given text into French. Output only the translation.",
name="translator",
)
reviewer = client.as_agent(
reviewer = Agent(
client=client,
instructions="You are a reviewer. Evaluate the quality of the marketing tagline.",
name="reviewer",
)
python/samples/03-workflows/orchestrations/sequential_custom_executors.py
+2 -2
View File
@@ -35,7 +35,7 @@ Custom executor contract:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
"""
@@ -68,7 +68,7 @@ async def main() -> None:
# 1) Create a content 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(),
)
content = Agent(
python/samples/03-workflows/parallelism/fan_out_fan_in_edges.py
+4 -4
View File
@@ -37,8 +37,8 @@ Show how to construct a parallel branch pattern in workflows. Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Familiarity with WorkflowBuilder, executors, edges, events, and streaming runs.
- Azure OpenAI access configured for FoundryChatClient. Log in with Azure CLI and set any required environment variables.
- Comfort reading AgentExecutorResponse.agent_response.text for assistant output aggregation.
"""
@@ -118,7 +118,7 @@ async def main() -> None:
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(),
),
instructions=(
@@ -132,7 +132,7 @@ async def main() -> None:
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(),
),
instructions=(
@@ -146,7 +146,7 @@ async def main() -> None:
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(),
),
instructions=(
python/samples/03-workflows/state-management/state_with_agents.py
+3 -3
View File
@@ -40,7 +40,7 @@ Show how to:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure OpenAI configured for FoundryChatClient with required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via azure-identity. Use AzureCliCredential and run az login before executing the sample.
- Familiarity with WorkflowBuilder, executors, conditional edges, and streaming runs.
"""
@@ -165,7 +165,7 @@ def create_spam_detection_agent() -> Agent:
return 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(),
),
instructions=(
@@ -183,7 +183,7 @@ def create_email_assistant_agent() -> Agent:
return 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(),
),
instructions=(
python/samples/03-workflows/state-management/workflow_kwargs.py
+2 -2
View File
@@ -29,7 +29,7 @@ Key Concepts:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Environment variables configured
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
"""
@@ -83,7 +83,7 @@ async def main() -> None:
# Create chat client
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/03-workflows/tool-approval/concurrent_builder_tool_approval.py
+2 -2
View File
@@ -46,7 +46,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI or Azure OpenAI configured with the required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Basic familiarity with ConcurrentBuilder and streaming workflow events.
"""
@@ -136,7 +136,7 @@ async def main() -> None:
# 3. Create two agents focused on different stocks but with the same tool sets
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/03-workflows/tool-approval/group_chat_builder_tool_approval.py
+2 -2
View File
@@ -45,7 +45,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI or Azure OpenAI configured with the required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Basic familiarity with GroupChatBuilder and streaming workflow events.
"""
@@ -136,7 +136,7 @@ async def main() -> None:
# 3. Create specialized agents
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/03-workflows/tool-approval/sequential_builder_tool_approval.py
+2 -2
View File
@@ -46,7 +46,7 @@ Demonstrate:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- OpenAI or Azure OpenAI configured with the required environment variables.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Basic familiarity with SequentialBuilder and streaming workflow events.
"""
@@ -109,7 +109,7 @@ async def main() -> None:
# 2. Create the agent with tools (approval mode is set per-tool via decorator)
client = FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential(),
)
database_agent = Agent(
python/samples/03-workflows/visualization/concurrent_with_visualization.py
+4 -4
View File
@@ -34,7 +34,7 @@ What it does:
Prerequisites:
- FOUNDRY_PROJECT_ENDPOINT must be your Azure AI Foundry Agent Service (V2) project endpoint.
- Azure AI/ Azure OpenAI for `FoundryChatClient` agents.
- FOUNDRY_MODEL must be set to your Azure OpenAI model deployment name.
- Authentication via `azure-identity` — uses `AzureCliCredential()` (run `az login`).
- For visualization export: `pip install graphviz>=0.20.0` and install GraphViz binaries.
"""
@@ -100,7 +100,7 @@ async def main() -> None:
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(),
),
instructions=(
@@ -115,7 +115,7 @@ async def main() -> None:
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(),
),
instructions=(
@@ -130,7 +130,7 @@ async def main() -> None:
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(),
),
instructions=(
python/samples/README.md
+4 -4
View File
@@ -44,8 +44,8 @@ Samples call `load_dotenv()` to automatically load environment variables from a
**Option 2: Export environment variables directly**:
```bash
export AZURE_AI_PROJECT_ENDPOINT="your-foundry-project-endpoint"
export AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o"
export FOUNDRY_PROJECT_ENDPOINT="your-foundry-project-endpoint"
export FOUNDRY_MODEL="gpt-4o"
```
**Option 3: Using `env_file_path` parameter** (for per-client configuration):
@@ -73,8 +73,8 @@ you pass an explicit Azure input.
For the getting-started samples, you'll need at minimum:
```bash
AZURE_AI_PROJECT_ENDPOINT="your-foundry-project-endpoint"
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o"
FOUNDRY_PROJECT_ENDPOINT="your-foundry-project-endpoint"
FOUNDRY_MODEL="gpt-4o"
```
**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.