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

First samples 1st batch

Browse Source
This commit is contained in:
Tao Chen
2026-03-25 11:00:17 -07:00
parent 49d69b3bf5
commit 5f68216863
8 changed files with 23 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/actions/sample-validation-setup/action.yml
+1 -1
View File
@@ -34,7 +34,7 @@ runs:
- name: Test Copilot CLI
shell: bash
run: copilot -p "What can you do in one sentence?"
run: copilot --version && copilot -p "What can you do in one sentence?"
- name: Azure CLI Login
uses: azure/login@v2
.github/workflows/python-sample-validation.yml
+8 -2
View File
@@ -67,11 +67,13 @@ jobs:
# Azure AI configuration
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY__PROJECT_ENDPOINT }}
FOUNDRY_MODEL: ${{ vars.FOUNDRY__MODEL }}
# Azure OpenAI configuration
AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
# OpenAI configuration
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
@@ -97,6 +99,8 @@ jobs:
- name: Create .env for samples
run: |
echo "FOUNDRY_PROJECT_ENDPOINT=$FOUNDRY_PROJECT_ENDPOINT" >> .env
echo "FOUNDRY_MODEL=$FOUNDRY_MODEL" >> .env
echo "AZURE_AI_PROJECT_ENDPOINT=$AZURE_AI_PROJECT_ENDPOINT" >> .env
echo "AZURE_AI_MODEL_DEPLOYMENT_NAME=$AZURE_AI_MODEL_DEPLOYMENT_NAME" >> .env
echo "AZURE_OPENAI_ENDPOINT=$AZURE_OPENAI_ENDPOINT" >> .env
@@ -125,6 +129,7 @@ jobs:
environment: integration
env:
OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
OPENAI_MODEL: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_CHAT_MODEL_ID: ${{ vars.OPENAI__CHATMODELID }}
OPENAI_RESPONSES_MODEL_ID: ${{ vars.OPENAI__RESPONSESMODELID }}
defaults:
@@ -144,6 +149,7 @@ jobs:
- name: Create .env for samples
run: |
echo "OPENAI_API_KEY=$OPENAI_API_KEY" >> .env
echo "OPENAI_MODEL=$OPENAI_MODEL" >> .env
echo "OPENAI_CHAT_MODEL_ID=$OPENAI_CHAT_MODEL_ID" >> .env
echo "OPENAI_RESPONSES_MODEL_ID=$OPENAI_RESPONSES_MODEL_ID" >> .env
@@ -207,7 +213,7 @@ jobs:
AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME: ${{ vars.AZUREOPENAI__EMBEDDINGDEPLOYMENTNAME }}
AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
BING_CONNECTION_ID: ${{ secrets.BING_CONNECTION_ID }}
defaults:
run:
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/providers/openai/README.md
+1 -2
View File
@@ -45,8 +45,7 @@ This folder contains examples demonstrating different ways to create and use age
Make sure to set the following environment variables before running the examples:
- `OPENAI_API_KEY`: Your OpenAI API key
- `OPENAI_CHAT_MODEL_ID`: The OpenAI model to use (e.g., `gpt-4o`, `gpt-4o-mini`, `gpt-3.5-turbo`)
- `OPENAI_RESPONSES_MODEL_ID`: The OpenAI model to use (e.g., `gpt-4o`, `gpt-4o-mini`, `gpt-3.5-turbo`)
- `OPENAI_MODEL`: The OpenAI model to use (e.g., `gpt-4o`, `gpt-4o-mini`, `gpt-3.5-turbo`)
- For image processing examples, use a vision-capable model like `gpt-4o` or `gpt-4o-mini`
Optionally, you can set:
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/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):
@@ -63,8 +63,8 @@ This allows different clients to use different configuration files if needed.
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.