mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Python: Azure AI Search Support Update + Refactored Samples & Unit Tests (#1683)
* azure ai search sample update * azure ai search update * small fix
This commit is contained in:
Giles Odigwe
committed by
GitHub
Unverified
GitHub
parent
943d92674e
commit
2059e7b3e8
@@ -1,9 +1,12 @@
|
||||
# Copyright (c) Microsoft. All rights reserved.
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from agent_framework import ChatAgent, HostedFileSearchTool
|
||||
from agent_framework import ChatAgent, CitationAnnotation
|
||||
from agent_framework.azure import AzureAIAgentClient
|
||||
from azure.ai.projects.aio import AIProjectClient
|
||||
from azure.ai.projects.models import ConnectionType
|
||||
from azure.identity.aio import AzureCliCredential
|
||||
|
||||
"""
|
||||
@@ -18,55 +21,98 @@ Prerequisites:
|
||||
3. The search index "hotels-sample-index" should exist in your Azure AI Search service
|
||||
(you can create this using the Azure portal with sample hotel data)
|
||||
|
||||
Environment variables:
|
||||
- AZURE_AI_PROJECT_ENDPOINT: Your Azure AI project endpoint
|
||||
- AZURE_AI_MODEL_DEPLOYMENT_NAME: The name of your model deployment
|
||||
"""
|
||||
NOTE: To ensure consistent search tool usage:
|
||||
- Include explicit instructions for the agent to use the search tool
|
||||
- Mention the search requirement in your queries
|
||||
- Use `tool_choice="required"` to force tool usage
|
||||
|
||||
# Test queries to verify Azure AI Search is working with the hotels-sample-index
|
||||
USER_INPUTS = [
|
||||
"Search the hotel database for Stay-Kay City Hotel and give me detailed information.",
|
||||
]
|
||||
More info on `query type` can be found here:
|
||||
https://learn.microsoft.com/en-us/python/api/azure-ai-agents/azure.ai.agents.models.aisearchindexresource?view=azure-python-preview
|
||||
"""
|
||||
|
||||
|
||||
async def main() -> None:
|
||||
"""Main function demonstrating Azure AI agent with Azure AI Search capabilities."""
|
||||
"""Main function demonstrating Azure AI agent with raw Azure AI Search tool."""
|
||||
print("=== Azure AI Agent with Raw Azure AI Search Tool ===")
|
||||
|
||||
# 1. Create Azure AI Search tool using HostedFileSearchTool
|
||||
# The tool will automatically use the default Azure AI Search connection from your project
|
||||
azure_ai_search_tool = HostedFileSearchTool(
|
||||
additional_properties={
|
||||
"index_name": "hotels-sample-index", # Name of your search index
|
||||
"query_type": "simple", # Use simple search
|
||||
"top_k": 10, # Get more comprehensive results
|
||||
},
|
||||
)
|
||||
|
||||
# 2. Use AzureAIAgentClient as async context manager for automatic cleanup
|
||||
# Create the client and manually create an agent with Azure AI Search tool
|
||||
async with (
|
||||
AzureAIAgentClient(async_credential=AzureCliCredential()) as client,
|
||||
ChatAgent(
|
||||
chat_client=client,
|
||||
name="HotelSearchAgent",
|
||||
instructions=("You are a helpful travel assistant that searches hotel information."),
|
||||
tools=azure_ai_search_tool,
|
||||
) as agent,
|
||||
AzureCliCredential() as credential,
|
||||
AIProjectClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as client,
|
||||
):
|
||||
print("=== Azure AI Agent with Azure AI Search ===")
|
||||
print("This agent can search through hotel data to help you find accommodations.\n")
|
||||
ai_search_conn_id = ""
|
||||
async for connection in client.connections.list():
|
||||
if connection.type == ConnectionType.AZURE_AI_SEARCH:
|
||||
ai_search_conn_id = connection.id
|
||||
break
|
||||
|
||||
# 3. Simulate conversation with the agent
|
||||
for user_input in USER_INPUTS:
|
||||
print(f"User: {user_input}")
|
||||
print("Agent: ", end="", flush=True)
|
||||
# 1. Create Azure AI agent with the search tool
|
||||
azure_ai_agent = await client.agents.create_agent(
|
||||
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
|
||||
name="HotelSearchAgent",
|
||||
instructions=(
|
||||
"You are a helpful agent that searches hotel information using Azure AI Search. "
|
||||
"Always use the search tool and index to find hotel data and provide accurate information."
|
||||
),
|
||||
tools=[{"type": "azure_ai_search"}],
|
||||
tool_resources={
|
||||
"azure_ai_search": {
|
||||
"indexes": [
|
||||
{
|
||||
"index_connection_id": ai_search_conn_id,
|
||||
"index_name": "hotels-sample-index",
|
||||
"query_type": "vector",
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
# Stream the response for better user experience
|
||||
async for chunk in agent.run_stream(user_input):
|
||||
if chunk.text:
|
||||
print(chunk.text, end="", flush=True)
|
||||
print("\n" + "=" * 50 + "\n")
|
||||
# 2. Create chat client with the existing agent
|
||||
chat_client = AzureAIAgentClient(project_client=client, agent_id=azure_ai_agent.id)
|
||||
|
||||
print("Hotel search conversation completed!")
|
||||
try:
|
||||
async with ChatAgent(
|
||||
chat_client=chat_client,
|
||||
# Additional instructions for this specific conversation
|
||||
instructions=("You are a helpful agent that uses the search tool and index to find hotel information."),
|
||||
) as agent:
|
||||
print("This agent uses raw Azure AI Search tool to search hotel data.\n")
|
||||
|
||||
# 3. Simulate conversation with the agent
|
||||
user_input = (
|
||||
"Use Azure AI search knowledge tool to find detailed information about a winter hotel."
|
||||
" Use the search tool and index." # You can modify prompt to force tool usage
|
||||
)
|
||||
print(f"User: {user_input}")
|
||||
print("Agent: ", end="", flush=True)
|
||||
|
||||
# Stream the response and collect citations
|
||||
citations: list[CitationAnnotation] = []
|
||||
async for chunk in agent.run_stream(user_input):
|
||||
if chunk.text:
|
||||
print(chunk.text, end="", flush=True)
|
||||
|
||||
# Collect citations from Azure AI Search responses
|
||||
for content in getattr(chunk, "contents", []):
|
||||
annotations = getattr(content, "annotations", [])
|
||||
if annotations:
|
||||
citations.extend(annotations)
|
||||
|
||||
print()
|
||||
|
||||
# Display collected citations
|
||||
if citations:
|
||||
print("\n\nCitations:")
|
||||
for i, citation in enumerate(citations, 1):
|
||||
print(f"[{i}] Reference: {citation.url}")
|
||||
|
||||
print("\n" + "=" * 50 + "\n")
|
||||
print("Hotel search conversation completed!")
|
||||
|
||||
finally:
|
||||
# Clean up the agent manually
|
||||
await client.agents.delete_agent(azure_ai_agent.id)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -7,21 +7,23 @@ This folder contains examples demonstrating different ways to create and use age
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| [`azure_assistants_basic.py`](azure_assistants_basic.py) | The simplest way to create an agent using `ChatAgent` with `AzureOpenAIAssistantsClient`. Shows both streaming and non-streaming responses with automatic assistant creation and cleanup. |
|
||||
| [`azure_assistants_with_code_interpreter.py`](azure_assistants_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`azure_assistants_with_existing_assistant.py`](azure_assistants_with_existing_assistant.py) | Shows how to work with a pre-existing assistant by providing the assistant ID to the Azure Assistants client. Demonstrates proper cleanup of manually created assistants. |
|
||||
| [`azure_assistants_with_explicit_settings.py`](azure_assistants_with_explicit_settings.py) | Shows how to initialize an agent with a specific assistants client, configuring settings explicitly including endpoint and deployment name. |
|
||||
| [`azure_assistants_with_function_tools.py`](azure_assistants_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
|
||||
| [`azure_assistants_with_code_interpreter.py`](azure_assistants_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`azure_assistants_with_thread.py`](azure_assistants_with_thread.py) | Demonstrates thread management with Azure agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
|
||||
| [`azure_chat_client_basic.py`](azure_chat_client_basic.py) | The simplest way to create an agent using `ChatAgent` with `AzureOpenAIChatClient`. Shows both streaming and non-streaming responses for chat-based interactions with Azure OpenAI models. |
|
||||
| [`azure_chat_client_with_explicit_settings.py`](azure_chat_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific chat client, configuring settings explicitly including endpoint and deployment name. |
|
||||
| [`azure_chat_client_with_function_tools.py`](azure_chat_client_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
|
||||
| [`azure_chat_client_with_thread.py`](azure_chat_client_with_thread.py) | Demonstrates thread management with Azure agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
|
||||
| [`azure_responses_client_basic.py`](azure_responses_client_basic.py) | The simplest way to create an agent using `ChatAgent` with `AzureOpenAIResponsesClient`. Shows both streaming and non-streaming responses for structured response generation with Azure OpenAI models. |
|
||||
| [`azure_responses_client_code_interpreter_files.py`](azure_responses_client_code_interpreter_files.py) | Demonstrates using HostedCodeInterpreterTool with file uploads for data analysis. Shows how to create, upload, and analyze CSV files using Python code execution with Azure OpenAI Responses. |
|
||||
| [`azure_responses_client_image_analysis.py`](azure_responses_client_image_analysis.py) | Shows how to use Azure OpenAI Responses for image analysis and vision tasks. Demonstrates multi-modal messages combining text and image content using remote URLs. |
|
||||
| [`azure_responses_client_with_code_interpreter.py`](azure_responses_client_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`azure_responses_client_with_explicit_settings.py`](azure_responses_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific responses client, configuring settings explicitly including endpoint and deployment name. |
|
||||
| [`azure_responses_client_with_function_tools.py`](azure_responses_client_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
|
||||
| [`azure_responses_client_with_code_interpreter.py`](azure_responses_client_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`azure_responses_client_with_local_mcp.py`](azure_responses_client_with_local_mcp.py) | Shows how to integrate Azure OpenAI Responses Client with local Model Context Protocol (MCP) servers using MCPStreamableHTTPTool for extended functionality. |
|
||||
| [`azure_responses_client_with_thread.py`](azure_responses_client_with_thread.py) | Demonstrates thread management with Azure agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
|
||||
| [`azure_responses_client_image_analysis.py`](azure_responses_client_image_analysis.py) | Shows how to use Azure OpenAI Responses for image analysis and vision tasks. Demonstrates multi-modal messages combining text and image content using remote URLs. |
|
||||
|
||||
## Environment Variables
|
||||
|
||||
|
||||
@@ -7,11 +7,11 @@ This folder contains examples demonstrating different ways to create and use age
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| [`openai_assistants_basic.py`](openai_assistants_basic.py) | The simplest way to create an agent using `ChatAgent` with `OpenAIAssistantsClient`. Shows both streaming and non-streaming responses with automatic assistant creation and cleanup. |
|
||||
| [`openai_assistants_with_code_interpreter.py`](openai_assistants_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with OpenAI agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`openai_assistants_with_existing_assistant.py`](openai_assistants_with_existing_assistant.py) | Shows how to work with a pre-existing assistant by providing the assistant ID to the OpenAI Assistants client. Demonstrates proper cleanup of manually created assistants. |
|
||||
| [`openai_assistants_with_explicit_settings.py`](openai_assistants_with_explicit_settings.py) | Shows how to initialize an agent with a specific assistants client, configuring settings explicitly including API key and model ID. |
|
||||
| [`openai_assistants_with_function_tools.py`](openai_assistants_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
|
||||
| [`openai_assistants_with_code_interpreter.py`](openai_assistants_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with OpenAI agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`openai_assistants_with_file_search.py`](openai_assistants_with_file_search.py) | Demonstrates how to use file search capabilities with OpenAI agents, allowing the agent to search through uploaded files to answer questions. |
|
||||
| [`openai_assistants_with_function_tools.py`](openai_assistants_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
|
||||
| [`openai_assistants_with_thread.py`](openai_assistants_with_thread.py) | Demonstrates thread management with OpenAI agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
|
||||
| [`openai_chat_client_basic.py`](openai_chat_client_basic.py) | The simplest way to create an agent using `ChatAgent` with `OpenAIChatClient`. Shows both streaming and non-streaming responses for chat-based interactions with OpenAI models. |
|
||||
| [`openai_chat_client_with_explicit_settings.py`](openai_chat_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific chat client, configuring settings explicitly including API key and model ID. |
|
||||
@@ -21,6 +21,7 @@ This folder contains examples demonstrating different ways to create and use age
|
||||
| [`openai_chat_client_with_web_search.py`](openai_chat_client_with_web_search.py) | Shows how to use web search capabilities with OpenAI agents to retrieve and use information from the internet in responses. |
|
||||
| [`openai_responses_client_basic.py`](openai_responses_client_basic.py) | The simplest way to create an agent using `ChatAgent` with `OpenAIResponsesClient`. Shows both streaming and non-streaming responses for structured response generation with OpenAI models. |
|
||||
| [`openai_responses_client_image_analysis.py`](openai_responses_client_image_analysis.py) | Demonstrates how to use vision capabilities with agents to analyze images. |
|
||||
| [`openai_responses_client_image_generation.py`](openai_responses_client_image_generation.py) | Demonstrates how to use image generation capabilities with OpenAI agents to create images based on text descriptions. Requires PIL (Pillow) for image display. |
|
||||
| [`openai_responses_client_reasoning.py`](openai_responses_client_reasoning.py) | Demonstrates how to use reasoning capabilities with OpenAI agents, showing how the agent can provide detailed reasoning for its responses. |
|
||||
| [`openai_responses_client_with_code_interpreter.py`](openai_responses_client_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with OpenAI agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
|
||||
| [`openai_responses_client_with_explicit_settings.py`](openai_responses_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific responses client, configuring settings explicitly including API key and model ID. |
|
||||
|
||||
Reference in New Issue
Block a user