跳到主要内容
Open In ColabOpen on GitHub

AzureMLChatOnlineEndpoint

Azure Machine Learning 是一个用于构建、训练和部署机器学习模型的平台。用户可以在模型目录中探索要部署的模型类型，其中提供了来自不同提供商的基础模型和通用模型。

通常，您需要部署模型才能使用其预测（推理）。在 Azure Machine Learning 中，联机终结点 (Online Endpoints) 用于部署这些模型并提供实时服务。它们基于 Endpoints（终结点）和 Deployments（部署）的概念，这使您能够将生产工作负载的接口与提供服务的实现解耦。

本 notebook 介绍了如何使用托管在 Azure Machine Learning Endpoint 上的聊天模型。

from langchain_community.chat_models.azureml_endpoint import AzureMLChatOnlineEndpoint

设置​

您必须在 Azure ML 上部署模型或部署到 Azure AI studio，并获取以下参数

  • endpoint_url：终结点提供的 REST 终结点 URL。
  • endpoint_api_type：将模型部署到专用终结点 (Dedicated endpoints)（托管基础结构）时，使用 endpoint_type='dedicated'。使用即用即付 (Pay-as-you-go) 产品/服务（模型即服务）部署模型时，使用 endpoint_type='serverless'。
  • endpoint_api_key：终结点提供的 API 密钥

内容格式化程序​

content_formatter 参数是一个处理程序类，用于转换 AzureML 终结点的请求和响应，使其与所需的架构匹配。由于模型目录中有各种各样的模型，每个模型处理数据的方式可能彼此不同，因此提供了 ContentFormatterBase 类，允许用户根据自己的喜好转换数据。提供以下内容格式化程序

  • CustomOpenAIChatContentFormatter：用于格式化遵循 OpenAI API 请求和响应规范的模型（如 LLaMa2-chat）的请求和响应数据。

注意：langchain.chat_models.azureml_endpoint.LlamaChatContentFormatter 正在弃用，并由 langchain.chat_models.azureml_endpoint.CustomOpenAIChatContentFormatter 取代。

您可以实现特定于您模型的自定义内容格式化程序，这些格式化程序派生自类 langchain_community.llms.azureml_endpoint.ContentFormatterBase。

示例​

以下部分包含有关如何使用此类的示例

示例：使用实时终结点的聊天补全​

from langchain_community.chat_models.azureml_endpoint import (
    AzureMLEndpointApiType,
    CustomOpenAIChatContentFormatter,
)
from langchain_core.messages import HumanMessage

chat = AzureMLChatOnlineEndpoint(
    endpoint_url="https://<your-endpoint>.<your_region>.inference.ml.azure.com/score",
    endpoint_api_type=AzureMLEndpointApiType.dedicated,
    endpoint_api_key="my-api-key",
    content_formatter=CustomOpenAIChatContentFormatter(),
)
response = chat.invoke(
    [HumanMessage(content="Will the Collatz conjecture ever be solved?")]
)
response
AIMessage(content='  The Collatz Conjecture is one of the most famous unsolved problems in mathematics, and it has been the subject of much study and research for many years. While it is impossible to predict with certainty whether the conjecture will ever be solved, there are several reasons why it is considered a challenging and important problem:\n\n1. Simple yet elusive: The Collatz Conjecture is a deceptively simple statement that has proven to be extraordinarily difficult to prove or disprove. Despite its simplicity, the conjecture has eluded some of the brightest minds in mathematics, and it remains one of the most famous open problems in the field.\n2. Wide-ranging implications: The Collatz Conjecture has far-reaching implications for many areas of mathematics, including number theory, algebra, and analysis. A solution to the conjecture could have significant impacts on these fields and potentially lead to new insights and discoveries.\n3. Computational evidence: While the conjecture remains unproven, extensive computational evidence supports its validity. In fact, no counterexample to the conjecture has been found for any starting value up to 2^64 (a number', additional_kwargs={}, example=False)

示例：使用即用即付部署（模型即服务）的聊天补全​

chat = AzureMLChatOnlineEndpoint(
    endpoint_url="https://<your-endpoint>.<your_region>.inference.ml.azure.com/v1/chat/completions",
    endpoint_api_type=AzureMLEndpointApiType.serverless,
    endpoint_api_key="my-api-key",
    content_formatter=CustomOpenAIChatContentFormatter,
)
response = chat.invoke(
    [HumanMessage(content="Will the Collatz conjecture ever be solved?")]
)
response

如果您需要向模型传递额外参数，请使用 model_kwargs 参数

chat = AzureMLChatOnlineEndpoint(
    endpoint_url="https://<your-endpoint>.<your_region>.inference.ml.azure.com/v1/chat/completions",
    endpoint_api_type=AzureMLEndpointApiType.serverless,
    endpoint_api_key="my-api-key",
    content_formatter=CustomOpenAIChatContentFormatter,
    model_kwargs={"temperature": 0.8},
)

参数也可以在调用期间传递

response = chat.invoke(
    [HumanMessage(content="Will the Collatz conjecture ever be solved?")],
    max_tokens=512,
)
response