使用Azure Cognitive Search和Azure Identity的助手

此笔记本展示了如何将Assistant Agents与Azure Cognitive Search和Azure Identity结合使用。Assistant Agents使用与Azure Cognitive Search交互的工具来提取相关数据。

先决条件

在运行此笔记本之前，请确保满足以下先决条件：

依赖项

Autogen
Azure SDK
认知搜索/AI搜索

如果您在 Azure 门户中启用了 AI 搜索功能，您可以使用以下代码创建一个可以搜索 Azure 认知搜索的助手代理。

AI搜索设置详细信息： - 文档：

创建搜索服务： https://learn.microsoft.com/en-us/azure/search/search-create-service-portal - 搜索索引： https://learn.microsoft.com/en-us/azure/search/search-how-to-create-search-index?tabs=portal 混合搜索： https://learn.microsoft.com/en-us/azure/search/hybrid-search-how-to-query
Youtube 教程：https://www.youtube.com/watch?v=6Zfuw-UJZ7k

安装 Azure CLI

此笔记本需要使用 Azure CLI 进行身份验证。请按照以下步骤安装并配置它：

Download and Install Azure CLI:
- 访问 Azure CLI 安装页面并根据你的操作系统按照指示操作。
- Mac用户可以使用Homebrew安装Azure CLI，命令为 brew install azure-cli
Verify Installation:
- 在下面的单元格中执行az --version以检查Azure CLI是否正确安装。
Login to Azure:
- 在下面的单元格中执行 az login 以登录到您的 Azure 账户。此步骤是必要的，因为笔记本使用 AzureCliCredential，它会根据当前登录的 Azure 账户检索令牌。

检查Azure CLI安装

运行下面的单元格以检查您的系统上是否已安装并正确配置了Azure CLI。

# Check Azure CLI installation and login status
# !az --version
# !az login

安装所需的包

运行下面的单元格以安装此笔记本所需的包。

!pip3 install autogen-agentchat[graph]~=0.2
!pip3 install python-dotenv==1.0.1
!pip3 install azure-search-documents==11.4.0b8
!pip3 install azure-identity==1.12.0

接下来你将导入此笔记本所需的包。

import json
import os

import requests
from azure.identity import DefaultAzureCredential
from azure.search.documents import SearchClient
from dotenv import load_dotenv

import autogen
from autogen import AssistantAgent, UserProxyAgent, register_function
from autogen.cache import Cache

load_dotenv()

# Import Cognitive Search index ENV
AZURE_SEARCH_SERVICE = os.getenv("AZURE_SEARCH_SERVICE")
AZURE_SEARCH_INDEX = os.getenv("AZURE_SEARCH_INDEX")
AZURE_SEARCH_KEY = os.getenv("AZURE_SEARCH_KEY")
AZURE_SEARCH_API_VERSION = os.getenv("AZURE_SEARCH_API_VERSION")
AZURE_SEARCH_SEMANTIC_SEARCH_CONFIG = os.getenv("AZURE_SEARCH_SEMANTIC_SEARCH_CONFIG")
AZURE_SEARCH_SERVICE_ENDPOINT = os.getenv("AZURE_SEARCH_SERVICE_ENDPOINT")

接下来，您需要进行身份验证并创建一个 SearchClient 实例。

credential = DefaultAzureCredential()
endpoint = AZURE_SEARCH_SERVICE_ENDPOINT

from azure.identity import AzureCliCredential

credential = AzureCliCredential()
token = credential.get_token("https://cognitiveservices.azure.com/.default")

print("TOKEN", token.token)

client = SearchClient(endpoint=endpoint, index_name="test-index", credential=credential)

然后，加载配置列表并定义 AssistantAgent 的配置。

config_list = autogen.config_list_from_json(
    env_or_file="OAI_CONFIG_LIST",
)

gpt4_config = {
    "cache_seed": 42,
    "temperature": 0,
    "config_list": config_list,
    "timeout": 120,
}

定义您的工具函数 search，它将与 Azure 认知搜索服务进行交互。

def search(query: str):
    payload = json.dumps(
        {
            "search": query,
            "vectorQueries": [{"kind": "text", "text": query, "k": 5, "fields": "vector"}],
            "queryType": "semantic",
            "semanticConfiguration": AZURE_SEARCH_SEMANTIC_SEARCH_CONFIG,
            "captions": "extractive",
            "answers": "extractive|count-3",
            "queryLanguage": "en-US",
        }
    )

    response = list(client.search(payload))

    output = []
    for result in response:
        result.pop("titleVector")
        result.pop("contentVector")
        output.append(result)

    return output

定义 AssistantAgent 和 UserProxyAgent 实例，并将 search 函数注册到它们中。

cog_search = AssistantAgent(
    name="COGSearch",
    system_message="You are a helpful AI assistant. "
    "You can help with Azure Cognitive Search."
    "Return 'TERMINATE' when the task is done.",
    llm_config=gpt4_config,
)

user_proxy = UserProxyAgent(
    name="User",
    llm_config=False,
    is_termination_msg=lambda msg: msg.get("content") is not None and "TERMINATE" in msg["content"],
    human_input_mode="NEVER",
)

register_function(
    search,
    caller=cog_search,
    executor=user_proxy,
    name="search",
    description="A tool for searching the Cognitive Search index",
)

最后，发起一个聊天。

if __name__ == "__main__":
    import asyncio

    async def main():
        with Cache.disk() as cache:
            await user_proxy.a_initiate_chat(
                cog_search,
                message="Search for 'What is Azure?' in the 'test-index' index",
                cache=cache,
            )

    await main()

User (to COGSearch):

Search for 'What is Azure?' in the 'test-index' index

--------------------------------------------------------------------------------
COGSearch (to User):

***** Suggested tool Call (call_6Db6DFPNEp7J7Dz5dkAbbjDY): search *****
Arguments: 
{"query":"What is Azure?"}
***********************************************************************

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING ASYNC FUNCTION search...
User (to COGSearch):

User (to COGSearch):

***** Response from calling tool "call_6Db6DFPNEp7J7Dz5dkAbbjDY" *****
[{"id": "40", "title": "Azure Cognitive Search", "category": "AI + Machine Learning", "content": "Azure Cognitive Search is a fully managed search-as-a-service that enables you to build rich search experiences for your applications. It provides features like full-text search, faceted navigation, and filters. Azure Cognitive Search supports various data sources, such as Azure SQL Database, Azure Blob Storage, and Azure Cosmos DB. You can use Azure Cognitive Search to index your data, create custom scoring profiles, and integrate with other Azure services. It also integrates with other Azure services, such as Azure Cognitive Services and Azure Machine Learning.", "@search.score": 9.1308, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "90", "title": "Azure Cognitive Services", "category": "AI + Machine Learning", "content": "Azure Cognitive Services is a collection of AI services and APIs that enable you to build intelligent applications using pre-built models and algorithms. It provides features like computer vision, speech recognition, and natural language processing. Cognitive Services supports various platforms, such as .NET, Java, Node.js, and Python. You can use Azure Cognitive Services to build chatbots, analyze images and videos, and process and understand text. It also integrates with other Azure services, such as Azure Machine Learning and Azure Cognitive Search.", "@search.score": 5.9858904, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "68", "title": "Azure Database for MariaDB", "category": "Databases", "content": "Azure Database for MariaDB is a fully managed, scalable, and secure relational database service that enables you to build and manage MariaDB applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for MariaDB supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for MariaDB to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.", "@search.score": 3.9424267, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "69", "title": "Azure SQL Managed Instance", "category": "Databases", "content": "Azure SQL Managed Instance is a fully managed, scalable, and secure SQL Server instance hosted in Azure. It provides features like automatic backups, monitoring, and high availability. SQL Managed Instance supports various data types, such as JSON, spatial, and full-text. You can use Azure SQL Managed Instance to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.", "@search.score": 3.2041788, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "66", "title": "Azure Database for MySQL", "category": "Databases", "content": "Azure Database for MySQL is a fully managed, scalable, and secure relational database service that enables you to build and manage MySQL applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for MySQL supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for MySQL to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.", "@search.score": 3.1852448, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "67", "title": "Azure Database for PostgreSQL", "category": "Databases", "content": "Azure Database for PostgreSQL is a fully managed, scalable, and secure relational database service that enables you to build and manage PostgreSQL applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for PostgreSQL supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for PostgreSQL to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.", "@search.score": 2.8028796, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}, {"id": "3", "title": "Azure Cognitive Services", "category": "AI + Machine Learning", "content": "Azure Cognitive Services are a set of AI services that enable you to build intelligent applications with powerful algorithms using just a few lines of code. These services cover a wide range of capabilities, including vision, speech, language, knowledge, and search. They are designed to be easy to use and integrate into your applications. Cognitive Services are fully managed, scalable, and continuously improved by Microsoft. It allows developers to create AI-powered solutions without deep expertise in machine learning.", "@search.score": 1.9905571, "@search.reranker_score": null, "@search.highlights": null, "@search.captions": null}]
**********************************************************************

--------------------------------------------------------------------------------
COGSearch (to User):

Here are the search results for "What is Azure?" from the index:

1. **Azure Cognitive Search**
   - Category: AI + Machine Learning
   - Content: Azure Cognitive Search is a fully managed search-as-a-service that enables you to build rich search experiences for your applications. It provides features like full-text search, faceted navigation, and filters. Azure Cognitive Search supports various data sources, such as Azure SQL Database, Azure Blob Storage, and Azure Cosmos DB. You can use Azure Cognitive Search to index your data, create custom scoring profiles, and integrate with other Azure services. It also integrates with Azure Cognitive Services and Azure Machine Learning.
   - Search Score: 9.1308

2. **Azure Cognitive Services**
   - Category: AI + Machine Learning
   - Content: Azure Cognitive Services is a collection of AI services and APIs that enable you to build intelligent applications using pre-built models and algorithms. It provides features like computer vision, speech recognition, and natural language processing. Cognitive Services supports various platforms, such as .NET, Java, Node.js, and Python. You can use Azure Cognitive Services to build chatbots, analyze images and videos, and process and understand text. It also integrates with other Azure services, such as Azure Machine Learning and Azure Cognitive Search.
   - Search Score: 5.9858904

3. **Azure Database for MariaDB**
   - Category: Databases
   - Content: Azure Database for MariaDB is a fully managed, scalable, and secure relational database service that enables you to build and manage MariaDB applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for MariaDB supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for MariaDB to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.
   - Search Score: 3.9424267

4. **Azure SQL Managed Instance**
   - Category: Databases
   - Content: Azure SQL Managed Instance is a fully managed, scalable, and secure SQL Server instance hosted in Azure. It provides features like automatic backups, monitoring, and high availability. SQL Managed Instance supports various data types, such as JSON, spatial, and full-text. You can use Azure SQL Managed Instance to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.
   - Search Score: 3.2041788

5. **Azure Database for MySQL**
   - Category: Databases
   - Content: Azure Database for MySQL is a fully managed, scalable, and secure relational database service that enables you to build and manage MySQL applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for MySQL supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for MySQL to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.
   - Search Score: 3.1852448

6. **Azure Database for PostgreSQL**
   - Category: Databases
   - Content: Azure Database for PostgreSQL is a fully managed, scalable, and secure relational database service that enables you to build and manage PostgreSQL applications in Azure. It provides features like automatic backups, monitoring, and high availability. Database for PostgreSQL supports various data types, such as JSON, spatial, and full-text. You can use Azure Database for PostgreSQL to migrate your existing applications, build new applications, and ensure the performance and security of your data. It also integrates with other Azure services, such as Azure App Service and Azure Data Factory.
   - Search Score: 2.8028796

7. **Azure Cognitive Services**
   - Category: AI + Machine Learning
   - Content: Azure Cognitive Services are a set of AI services that enable you to build intelligent applications with powerful algorithms using just a few lines of code. These services cover a wide range of capabilities, including vision, speech, language, knowledge, and search. They are designed to be easy to use and integrate into your applications. Cognitive Services are fully managed, scalable, and continuously improved by Microsoft. It allows developers to create AI-powered solutions without deep expertise in machine learning.
   - Search Score: 1.9905571

The search scores indicate the relevance of each result to the query "What is Azure?" with higher scores representing greater relevance. The top result provides a detailed explanation of Azure Cognitive Search, which is a part of the Azure platform.

--------------------------------------------------------------------------------
User (to COGSearch):



--------------------------------------------------------------------------------
COGSearch (to User):

TERMINATE

--------------------------------------------------------------------------------

使用Azure Cognitive Search和Azure Identity的助手

先决条件​

依赖项​

安装 Azure CLI​

检查Azure CLI安装​

检查Azure CLI的安装和登录状态​

安装所需的包​

先决条件

依赖项

安装 Azure CLI

检查Azure CLI安装

检查Azure CLI的安装和登录状态

安装所需的包