mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
fix and unify devui samples (#5025)
This commit is contained in:
Eduard van Valkenburg
committed by
GitHub
Unverified
GitHub
parent
cee0a458fe
commit
2cb78ea12e
@@ -0,0 +1,15 @@
|
||||
# Shared configuration for samples/02-agents/devui
|
||||
# Used by in_memory_mode.py, main.py, and as a fallback for discovered samples.
|
||||
# Run `az login` before starting Azure-backed samples.
|
||||
|
||||
# Microsoft Foundry samples
|
||||
FOUNDRY_PROJECT_ENDPOINT=https://your-project.services.ai.azure.com
|
||||
FOUNDRY_MODEL=gpt-4o
|
||||
|
||||
# Azure OpenAI workflow sample
|
||||
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
||||
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME=gpt-4o
|
||||
# Optional fallback env name also supported by workflow_with_agents/workflow.py:
|
||||
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
|
||||
# Optional if you need to override the default API version:
|
||||
AZURE_OPENAI_API_VERSION=2024-10-21
|
||||
@@ -16,76 +16,124 @@ DevUI is a sample application that provides:
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Option 1: In-Memory Mode (Simplest)
|
||||
### Option 1: In-Memory Mode (Programmatic Registration)
|
||||
|
||||
Run a single sample directly. This demonstrates how to wrap agents and workflows programmatically without needing a directory structure:
|
||||
Run a single sample directly. This demonstrates how to register agents and workflows in code without using DevUI's directory discovery.
|
||||
|
||||
This sample uses Azure AI Foundry. Before running it:
|
||||
|
||||
1. Copy `.env.example` in this folder to `.env`, or export the same values in your shell
|
||||
2. Set `FOUNDRY_PROJECT_ENDPOINT` and `FOUNDRY_MODEL`
|
||||
3. Run `az login`
|
||||
|
||||
Then start the sample:
|
||||
|
||||
```bash
|
||||
cd python/samples/02-agents/devui
|
||||
python in_memory_mode.py
|
||||
```
|
||||
|
||||
This opens your browser at http://localhost:8090 with pre-configured agents and a basic workflow.
|
||||
This opens your browser at http://localhost:8090 with two Foundry-backed agents and a simple text transformation workflow.
|
||||
|
||||
### Option 2: Directory Discovery
|
||||
### Option 2: Directory Discovery with Shared Root `.env`
|
||||
|
||||
Launch DevUI to discover all samples in this folder:
|
||||
Run the folder-level launcher to load `samples/02-agents/devui/.env` and then start DevUI with directory discovery for this folder:
|
||||
|
||||
```bash
|
||||
cd python/samples/02-agents/devui
|
||||
devui
|
||||
python main.py
|
||||
```
|
||||
|
||||
This starts the server at http://localhost:8080 with all agents and workflows available.
|
||||
This starts the server at http://localhost:8080 with all discoverable agents and workflows available. The root `.env` acts as shared fallback configuration for discovered samples.
|
||||
|
||||
### Option 3: Directory Discovery with the `devui` CLI
|
||||
|
||||
If you prefer the CLI directly, you can still launch DevUI from this folder:
|
||||
|
||||
```bash
|
||||
cd python/samples/02-agents/devui
|
||||
devui .
|
||||
```
|
||||
|
||||
DevUI discovery checks for a sample-specific `.env` first and then falls back to `.env` in `samples/02-agents/devui/`.
|
||||
|
||||
## Sample Structure
|
||||
|
||||
Each agent/workflow follows a strict structure required by DevUI's discovery system:
|
||||
DevUI discovers samples from Python packages that export either `agent` or `workflow`.
|
||||
|
||||
Typical agent layout:
|
||||
|
||||
```
|
||||
agent_name/
|
||||
├── __init__.py # Must export: agent = Agent(...)
|
||||
├── __init__.py # Must export: agent = ...
|
||||
├── agent.py # Agent implementation
|
||||
└── .env.example # Example environment variables
|
||||
└── .env.example # Optional example environment variables
|
||||
```
|
||||
|
||||
Typical workflow layout:
|
||||
|
||||
```
|
||||
workflow_name/
|
||||
├── __init__.py # Must export: workflow = ...
|
||||
├── workflow.py # Workflow implementation
|
||||
├── workflow.yaml # Optional declarative definition
|
||||
└── .env.example # Optional example environment variables
|
||||
```
|
||||
|
||||
## Available Samples
|
||||
|
||||
### Agents
|
||||
|
||||
| Sample | Description | Features | Required Environment Variables |
|
||||
| ------------------------------------------------ | ------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
|
||||
| [**weather_agent_azure/**](weather_agent_azure/) | Weather agent using Azure OpenAI with API key authentication | Azure OpenAI integration, function calling, mock weather tools | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
|
||||
| [**foundry_agent/**](foundry_agent/) | Weather agent using Azure AI Agent (Foundry) with Azure CLI authentication (run `az login` first) | Azure AI Agent integration, Azure CLI authentication, mock weather tools | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL` |
|
||||
| Sample | What it demonstrates | Required keys / auth |
|
||||
| ------ | -------------------- | -------------------- |
|
||||
| [**agent_weather/**](agent_weather/) | A richer Foundry-backed weather agent that shows chat middleware, function middleware, tool calling, and an approval-required tool alongside auto-approved tools. | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL`, plus Azure CLI auth via `az login` |
|
||||
| [**agent_foundry/**](agent_foundry/) | A minimal Foundry-backed weather agent with current weather and forecast tools. Use this when you want the smallest possible directory-discovered agent sample. | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL`, plus Azure CLI auth via `az login` |
|
||||
|
||||
### Workflows
|
||||
|
||||
| Sample | Description | Features | Required Environment Variables |
|
||||
| -------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------- |
|
||||
| [**declarative/**](declarative/) | Declarative YAML workflow with conditional branching | YAML-based workflow definition, conditional logic, no Python code required | None - uses mock data |
|
||||
| [**workflow_agents/**](workflow_agents/) | Content review workflow with agents as executors | Agents as workflow nodes, conditional routing based on structured outputs, quality-based paths (Writer -> Reviewer -> Editor/Publisher) | `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_DEPLOYMENT_NAME`, `AZURE_OPENAI_ENDPOINT` |
|
||||
| [**spam_workflow/**](spam_workflow/) | 5-step email spam detection workflow with branching logic | Sequential execution, conditional branching (spam vs. legitimate), multiple executors, mock spam detection | None - uses mock data |
|
||||
| [**fanout_workflow/**](fanout_workflow/) | Advanced data processing workflow with parallel execution | Fan-out/fan-in patterns, complex state management, multi-stage processing (validation -> transformation -> quality assurance) | None - uses mock data |
|
||||
| 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_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 |
|
||||
|
||||
### Standalone Examples
|
||||
|
||||
| Sample | Description | Features |
|
||||
| ------------------------------------------ | ------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| [**in_memory_mode.py**](in_memory_mode.py) | Demonstrates programmatic entity registration without directory structure | In-memory agent and workflow registration, multiple entities served from a single file, includes basic workflow, simplest way to get started |
|
||||
| Sample | What it demonstrates | Required keys / auth |
|
||||
| ------ | -------------------- | -------------------- |
|
||||
| [**in_memory_mode.py**](in_memory_mode.py) | Registers multiple entities directly in Python: two Foundry-backed agents plus a simple workflow, all served from one file without directory discovery. | `FOUNDRY_PROJECT_ENDPOINT`, `FOUNDRY_MODEL`, plus Azure CLI auth via `az login` |
|
||||
|
||||
## Environment Variables
|
||||
|
||||
Each sample that requires API keys includes a `.env.example` file. To use:
|
||||
For samples that require external services:
|
||||
|
||||
1. Copy `.env.example` to `.env` in the same directory
|
||||
2. Fill in your actual API keys
|
||||
3. DevUI automatically loads `.env` files from entity directories
|
||||
1. Copy `.env.example` to `.env`
|
||||
2. Fill in the required values
|
||||
3. Run `az login` for samples that use Azure CLI authentication
|
||||
|
||||
Directory discovery checks `.env` files in this order:
|
||||
|
||||
1. The entity directory itself, for example `agent_weather/.env`
|
||||
2. The root DevUI samples folder, `samples/02-agents/devui/.env`
|
||||
|
||||
That means the root `.env.example` can hold shared defaults for multiple samples, while a sample-specific `.env` can override those values when needed.
|
||||
|
||||
`in_memory_mode.py` and `main.py` both load `.env` from `samples/02-agents/devui/`, so the root `.env.example` in this folder is the right starting point for both commands.
|
||||
|
||||
Alternatively, set environment variables globally:
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY="your-key-here"
|
||||
export OPENAI_CHAT_MODEL="gpt-4o"
|
||||
# Foundry-backed samples
|
||||
export FOUNDRY_PROJECT_ENDPOINT="https://your-project.services.ai.azure.com"
|
||||
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"
|
||||
|
||||
az login
|
||||
```
|
||||
|
||||
## Using DevUI with Your Own Agents
|
||||
@@ -145,7 +193,7 @@ curl http://localhost:8080/v1/entities
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**Missing API keys**: Check your `.env` files or environment variables.
|
||||
**Missing credentials or settings**: Check your `.env` files, confirm the required variables for the sample you are running, and make sure `az login` has completed for Azure-authenticated samples.
|
||||
|
||||
**Import errors**: Make sure you've installed the devui package:
|
||||
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
# Azure AI Foundry Configuration
|
||||
# Make sure to run 'az login' before starting devui
|
||||
|
||||
FOUNDRY_PROJECT_ENDPOINT=https://your-project.services.ai.azure.com
|
||||
FOUNDRY_MODEL=gpt-4o
|
||||
+1
-1
@@ -53,7 +53,7 @@ agent = Agent(
|
||||
name="FoundryWeatherAgent",
|
||||
client=FoundryChatClient(
|
||||
project_endpoint=os.environ.get("FOUNDRY_PROJECT_ENDPOINT"),
|
||||
model_model=os.environ.get("FOUNDRY_MODEL"),
|
||||
model=os.environ.get("FOUNDRY_MODEL"),
|
||||
credential=AzureCliCredential(),
|
||||
),
|
||||
instructions="""
|
||||
@@ -0,0 +1,5 @@
|
||||
# Azure AI Foundry Configuration
|
||||
# Make sure to run 'az login' before starting devui
|
||||
|
||||
FOUNDRY_PROJECT_ENDPOINT=https://your-project.services.ai.azure.com
|
||||
FOUNDRY_MODEL=gpt-4o
|
||||
+8
-5
@@ -22,6 +22,7 @@ from agent_framework import (
|
||||
)
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework_devui import register_cleanup
|
||||
from azure.identity.aio import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# Load environment variables from .env file
|
||||
@@ -145,7 +146,7 @@ def send_email(
|
||||
|
||||
# Agent instance following Agent Framework conventions
|
||||
agent = Agent(
|
||||
name="AzureWeatherAgent",
|
||||
name="WeatherAgent",
|
||||
description="A helpful agent that provides weather information and forecasts",
|
||||
instructions="""
|
||||
You are a weather assistant. You can provide current weather information
|
||||
@@ -153,7 +154,9 @@ agent = Agent(
|
||||
weather information when asked.
|
||||
""",
|
||||
client=FoundryChatClient(
|
||||
api_key=os.environ.get("AZURE_OPENAI_API_KEY", ""),
|
||||
project_endpoint=os.environ.get("FOUNDRY_PROJECT_ENDPOINT"),
|
||||
model=os.environ.get("FOUNDRY_MODEL"),
|
||||
credential=AzureCliCredential(),
|
||||
),
|
||||
tools=[get_weather, get_forecast, send_email],
|
||||
middleware=[security_filter_middleware, atlantis_location_filter_middleware],
|
||||
@@ -164,7 +167,7 @@ register_cleanup(agent, cleanup_resources)
|
||||
|
||||
|
||||
def main():
|
||||
"""Launch the Azure weather agent in DevUI."""
|
||||
"""Launch the Weather Agent in DevUI."""
|
||||
import logging
|
||||
|
||||
from agent_framework.devui import serve
|
||||
@@ -173,9 +176,9 @@ def main():
|
||||
logging.basicConfig(level=logging.INFO, format="%(message)s")
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
logger.info("Starting Azure Weather Agent")
|
||||
logger.info("Starting Weather Agent")
|
||||
logger.info("Available at: http://localhost:8090")
|
||||
logger.info("Entity ID: agent_AzureWeatherAgent")
|
||||
logger.info("Entity ID: agent_WeatherAgent")
|
||||
|
||||
# Launch server with the agent
|
||||
serve(entities=[agent], port=8090, auto_open=True)
|
||||
@@ -1,15 +0,0 @@
|
||||
# Azure OpenAI Responses API Configuration
|
||||
# The Responses API supports PDF uploads, images, and other multimodal content.
|
||||
# Requires api-version 2025-03-01-preview or later.
|
||||
|
||||
# Option 1: Use API key authentication
|
||||
AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
|
||||
|
||||
# Option 2: Use Azure CLI authentication (run 'az login' first)
|
||||
# No API key needed - just leave AZURE_OPENAI_API_KEY unset
|
||||
|
||||
# Required: Azure OpenAI endpoint with Responses API support
|
||||
AZURE_OPENAI_ENDPOINT=https://your-resource.cognitiveservices.azure.com/
|
||||
|
||||
# Required: Deployment name (must support Responses API)
|
||||
FOUNDRY_MODEL=gpt-4.1-mini
|
||||
@@ -1,6 +0,0 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
"""Azure Responses Agent sample for DevUI."""
|
||||
|
||||
from .agent import agent
|
||||
|
||||
__all__ = ["agent"]
|
||||
@@ -1,128 +0,0 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
"""Sample agent using Azure OpenAI Responses API for Agent Framework DevUI.
|
||||
|
||||
This agent uses the Responses API which supports:
|
||||
- PDF file uploads
|
||||
- Image uploads
|
||||
- Audio inputs
|
||||
- And other multimodal content
|
||||
|
||||
The Chat Completions API (FoundryChatClient) does NOT support PDF uploads.
|
||||
Use this agent when you need to process documents or other file types.
|
||||
|
||||
Required environment variables:
|
||||
- AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint
|
||||
- FOUNDRY_MODEL: Deployment name for Responses API
|
||||
(falls back to FOUNDRY_MODEL if not set)
|
||||
- AZURE_OPENAI_API_KEY: Your API key (or use Azure CLI auth)
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Annotated
|
||||
|
||||
from agent_framework import Agent, tool
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from dotenv import load_dotenv
|
||||
|
||||
# Load environment variables from .env file
|
||||
load_dotenv()
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Get deployment name - try responses-specific env var first, fall back to chat deployment
|
||||
_deployment_name = os.environ.get(
|
||||
"FOUNDRY_MODEL",
|
||||
os.environ.get("FOUNDRY_MODEL", ""),
|
||||
)
|
||||
|
||||
# Get endpoint - try responses-specific env var first, fall back to default
|
||||
_endpoint = os.environ.get(
|
||||
"AZURE_OPENAI_RESPONSES_ENDPOINT",
|
||||
os.environ.get("AZURE_OPENAI_ENDPOINT", ""),
|
||||
)
|
||||
|
||||
|
||||
def analyze_content(
|
||||
query: Annotated[str, "What to analyze or extract from the uploaded content"],
|
||||
) -> str:
|
||||
"""Analyze uploaded content based on the user's query.
|
||||
|
||||
This is a placeholder - the actual analysis is done by the model
|
||||
when processing the uploaded files.
|
||||
"""
|
||||
return f"Analyzing content for: {query}"
|
||||
|
||||
|
||||
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/02-agents/tools/function_tool_with_approval.py and samples/02-agents/tools/function_tool_with_approval_and_sessions.py.
|
||||
@tool(approval_mode="never_require")
|
||||
def summarize_document(
|
||||
length: Annotated[str, "Desired summary length: 'brief', 'medium', or 'detailed'"] = "medium",
|
||||
) -> str:
|
||||
"""Generate a summary of the uploaded document."""
|
||||
return f"Generating {length} summary of the document..."
|
||||
|
||||
|
||||
@tool(approval_mode="never_require")
|
||||
def extract_key_points(
|
||||
max_points: Annotated[int, "Maximum number of key points to extract"] = 5,
|
||||
) -> str:
|
||||
"""Extract key points from the uploaded document."""
|
||||
return f"Extracting up to {max_points} key points..."
|
||||
|
||||
|
||||
# Agent using Azure OpenAI Responses API (supports PDF uploads!)
|
||||
agent = Agent(
|
||||
name="AzureResponsesAgent",
|
||||
description="An agent that can analyze PDFs, images, and other documents using Azure OpenAI Responses API",
|
||||
instructions="""
|
||||
You are a helpful document analysis assistant. You can:
|
||||
|
||||
1. Analyze uploaded PDF documents and extract information
|
||||
2. Summarize document contents
|
||||
3. Answer questions about uploaded files
|
||||
4. Extract key points and insights
|
||||
|
||||
When a user uploads a file, carefully analyze its contents and provide
|
||||
helpful, accurate information based on what you find.
|
||||
|
||||
For PDFs, you can read and understand the text, tables, and structure.
|
||||
For images, you can describe what you see and extract any text.
|
||||
""",
|
||||
client=FoundryChatClient(
|
||||
model=_deployment_name,
|
||||
endpoint=_endpoint,
|
||||
api_version="2025-03-01-preview", # Required for Responses API
|
||||
),
|
||||
tools=[summarize_document, extract_key_points],
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
"""Launch the Azure Responses agent in DevUI."""
|
||||
from agent_framework_devui import serve
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(message)s")
|
||||
|
||||
logger.info("=" * 60)
|
||||
logger.info("Starting Azure Responses Agent")
|
||||
logger.info("=" * 60)
|
||||
logger.info("")
|
||||
logger.info("This agent uses the Azure OpenAI Responses API which supports:")
|
||||
logger.info(" - PDF file uploads")
|
||||
logger.info(" - Image uploads")
|
||||
logger.info(" - Audio inputs")
|
||||
logger.info("")
|
||||
logger.info("Try uploading a PDF and asking questions about it!")
|
||||
logger.info("")
|
||||
logger.info("Required environment variables:")
|
||||
logger.info(" - AZURE_OPENAI_ENDPOINT")
|
||||
logger.info(" - FOUNDRY_MODEL")
|
||||
logger.info(" - AZURE_OPENAI_API_KEY (or use Azure CLI auth)")
|
||||
logger.info("")
|
||||
|
||||
serve(entities=[agent], port=8090, auto_open=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,6 +0,0 @@
|
||||
# Azure AI Foundry Configuration
|
||||
# Get your credentials from Azure AI Foundry portal
|
||||
# Make sure to run 'az login' before starting devui
|
||||
|
||||
FOUNDRY_PROJECT_ENDPOINT=https://your-project.api.azureml.ms
|
||||
FOUNDRY_MODEL=gpt-4o
|
||||
@@ -20,6 +20,7 @@ from agent_framework import (
|
||||
)
|
||||
from agent_framework.devui import serve
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from azure.identity.aio import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
from typing_extensions import Never
|
||||
|
||||
@@ -80,14 +81,13 @@ def main():
|
||||
|
||||
# Create Azure OpenAI chat client
|
||||
client = FoundryChatClient(
|
||||
api_key=os.environ.get("AZURE_OPENAI_API_KEY"),
|
||||
model=os.environ["FOUNDRY_MODEL"],
|
||||
endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"),
|
||||
api_version=os.environ.get("AZURE_OPENAI_API_VERSION", "2024-10-21"),
|
||||
project_endpoint=os.environ.get("FOUNDRY_PROJECT_ENDPOINT"),
|
||||
credential=AzureCliCredential(),
|
||||
)
|
||||
|
||||
# Create agents
|
||||
weather_agent = Agent(
|
||||
weather_assistant = Agent(
|
||||
name="weather-assistant",
|
||||
description="Provides weather information and time",
|
||||
instructions=(
|
||||
@@ -120,7 +120,7 @@ def main():
|
||||
)
|
||||
|
||||
# Collect entities for serving
|
||||
entities = [weather_agent, simple_agent, basic_workflow]
|
||||
entities = [weather_assistant, simple_agent, basic_workflow]
|
||||
|
||||
logger.info("Starting DevUI on http://localhost:8090")
|
||||
logger.info("Entities available:")
|
||||
|
||||
@@ -0,0 +1,32 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
"""Launch DevUI with folder discovery for the samples in this directory.
|
||||
|
||||
This sample demonstrates:
|
||||
- Loading a shared root `.env` file for the DevUI samples folder
|
||||
- Starting DevUI in directory discovery mode for this folder
|
||||
- Using root-level settings as fallbacks for discovered samples
|
||||
"""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from agent_framework.devui import serve
|
||||
from dotenv import load_dotenv
|
||||
|
||||
|
||||
def main() -> None:
|
||||
"""Load the root .env file and launch DevUI with folder discovery."""
|
||||
samples_dir = Path(__file__).resolve().parent
|
||||
|
||||
# 1. Load shared defaults for the samples in this folder.
|
||||
load_dotenv(samples_dir / ".env")
|
||||
|
||||
# 2. Start DevUI and discover entities from this directory.
|
||||
serve(entities_dir=str(samples_dir), auto_open=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
# Sample output:
|
||||
# Starting Agent Framework DevUI on 127.0.0.1:8080
|
||||
@@ -1,6 +0,0 @@
|
||||
# Azure OpenAI API Configuration
|
||||
# Get your credentials from Azure Portal
|
||||
|
||||
AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
|
||||
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
|
||||
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
||||
@@ -1,7 +0,0 @@
|
||||
# Azure OpenAI API Configuration
|
||||
# Get your credentials from Azure Portal
|
||||
|
||||
AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
|
||||
AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
|
||||
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
||||
AZURE_OPENAI_API_VERSION=2024-10-21
|
||||
@@ -0,0 +1,9 @@
|
||||
# Azure OpenAI configuration for the Responses-based workflow sample
|
||||
# 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
|
||||
# Optional fallback env name also supported by the client:
|
||||
# AZURE_OPENAI_DEPLOYMENT_NAME=gpt-4o
|
||||
# Optional if you need to override the default API version:
|
||||
AZURE_OPENAI_API_VERSION=2024-10-21
|
||||
+9
-3
@@ -18,7 +18,8 @@ import os
|
||||
from typing import Any
|
||||
|
||||
from agent_framework import Agent, AgentExecutorResponse, WorkflowBuilder
|
||||
from agent_framework.foundry import FoundryChatClient
|
||||
from agent_framework.openai import OpenAIChatClient
|
||||
from azure.identity import AzureCliCredential
|
||||
from dotenv import load_dotenv
|
||||
from pydantic import BaseModel
|
||||
|
||||
@@ -62,8 +63,13 @@ def is_approved(message: Any) -> bool:
|
||||
return True
|
||||
|
||||
|
||||
# Create Azure OpenAI chat client
|
||||
client = FoundryChatClient(api_key=os.environ.get("AZURE_OPENAI_API_KEY", ""))
|
||||
# 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"),
|
||||
azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"),
|
||||
api_version=os.environ.get("AZURE_OPENAI_API_VERSION"),
|
||||
credential=AzureCliCredential(),
|
||||
)
|
||||
|
||||
# Create Writer agent - generates content
|
||||
writer = Agent(
|
||||
@@ -48,9 +48,7 @@ async def main() -> None:
|
||||
project_endpoint = os.getenv("FOUNDRY_PROJECT_ENDPOINT")
|
||||
model = os.getenv("FOUNDRY_MODEL")
|
||||
if not project_endpoint or not model:
|
||||
raise ValueError(
|
||||
"FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL must be set"
|
||||
)
|
||||
raise ValueError("FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL must be set")
|
||||
|
||||
print(f"Connecting to A2A agent at: {a2a_agent_host}")
|
||||
|
||||
|
||||
@@ -48,8 +48,7 @@ async def main() -> None:
|
||||
client=chat_client,
|
||||
name="travel-assistant",
|
||||
instructions=(
|
||||
"You are a helpful travel assistant. "
|
||||
"Use your tools to answer questions about weather and flights."
|
||||
"You are a helpful travel assistant. Use your tools to answer questions about weather and flights."
|
||||
),
|
||||
tools=[get_weather, get_flight_price],
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user