阿里云 PAI EAS

阿里云人工智能机器学习平台是面向企业和开发者的机器学习或深度学习工程平台。它提供易于使用、成本效益高、高性能且易于扩展的插件，可应用于各种行业场景。内置超过140种优化算法，Machine Learning Platform for AI 提供涵盖数据标注（PAI-iTAG）、模型构建（PAI-Designer 和 PAI-DSW）、模型训练（PAI-DLC）、编译优化以及推理部署（PAI-EAS）的全流程 AI 工程能力。PAI-EAS 支持多种类型的硬件资源，包括 CPU 和 GPU，具备高吞吐量和低延迟特性。您只需几次点击即可部署大规模复杂模型，并实时进行弹性缩容和扩容。同时，它还提供全面的运维与监控系统。

##Installing the langchain packages needed to use the integration
%pip install -qU langchain-community

from langchain.chains import LLMChain
from langchain_community.llms.pai_eas_endpoint import PaiEasEndpoint
from langchain_core.prompts import PromptTemplate

template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate.from_template(template)

API 参考:LLMChain |PaiEasEndpoint | 提示模板

希望使用 EAS 大语言模型的用户必须先设置 EAS 服务。当 EAS 服务启动后，可以获得 EAS_SERVICE_URL 和 EAS_SERVICE_TOKEN。更多信息，用户可参考 https://www.alibabacloud.com/help/zh/pai/user-guide/service-deployment/，

import os

os.environ["EAS_SERVICE_URL"] = "Your_EAS_Service_URL"
os.environ["EAS_SERVICE_TOKEN"] = "Your_EAS_Service_Token"
llm = PaiEasEndpoint(
    eas_service_url=os.environ["EAS_SERVICE_URL"],
    eas_service_token=os.environ["EAS_SERVICE_TOKEN"],
)

llm_chain = prompt | llm

question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"
llm_chain.invoke({"question": question})

'  Thank you for asking! However, I must respectfully point out that the question contains an error. Justin Bieber was born in 1994, and the Super Bowl was first played in 1967. Therefore, it is not possible for any NFL team to have won the Super Bowl in the year Justin Bieber was born.\n\nI hope this clarifies things! If you have any other questions, please feel free to ask.'

大语言模型概念指南
LLM 操操作指南

相关​

相关