Skip to main content

High energy physics Artificial Intelligence platform, HAI.

Project description

Stars Open issue

简体中文 | English

高能AI框架HepAI

HepAI提供了一个AI开源框架,是高能AI平台的核心技术,应用此技术可以加速多学科场景的科学研究,简化模型迭代和流程,是开发AI算法和应用的共性基础。

HepAI平台本身是一个软件系统,承载AI算法模型,提供AI计算能力,打通数据通道,并开展AI培训。

HepAI框架集成了高能物理领域的经典和最先进(SOTA)的人工智能算法。用户可以通过统一接口访问相关的算法模型、数据集和计算资源,使AI的应用变得简单高效。

News
  • [2025.04.27] v1.1.34 支持原opendrsai智能体与多智能体协作框架,将from drsai 改为 from hepai.agents即可,具体见 https://code.ihep.ac.cn/hepai/drsai

  • [2024.12.22] v1.1.16 支持远程模型!点此查看详情

  • [2024.05.16] v1.1.9 HepAI Client支持GPT-4o系列模型。

  • [2024.03.26] v1.0.21 Make LLM request like OpenAI via HepAI object.

  • [2023.10.24] v1.0.18 接入dalle文生图模型,调用方法教程见此处

  • [2023.04.21] v1.0.7通过hepai使用GPT-3.5,hepai_api.md.

  • [2023.02.09] 基于ChatGPT的HaiChatGPT已上线,使用简单,无需梯子!详情查看:HaiChatGPT.

  • [2023.01.16] 支持华为NPU服务器,如有算法国产化需求,请查阅NPU文档

  • [2022.10.20] HAI v1.0.6-Beta 第一个测试版本发布,4个算法和3个数据集

  • [2022.08.23] HAI v1.0.0

  • 详细更新日志:update_log

教程

使用远程模型实现分布式模型、工具及智能体组件 60+深度学习论文代码的实现和解释 在HPC计算集群中使用HepAI的快速入门 使用PointNet在JUNO实验中重建和识别大气中微子

模型Zoo
数据集Zoo

快速开始

pip install hepai --upgrade
hepai -V  # 查看版本

1. 调用HepAI模型

    from hepai import HepAI
    
    client = HepAI(api_key="your_api_key")
    models = client.list_models()
    response = client.chat.completion.create(
        model="hepai/deepseek-r1:671b", 
        prompt="你好",
        )
    print(response.choices[0].text)

2. 使用算力资源

高能AI算力集群用户手册

X. 智能体

TODO xx

workers

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hepai-1.2.15.tar.gz (448.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hepai-1.2.15-py2.py3-none-any.whl (837.2 kB view details)

Uploaded Python 2Python 3

File details

Details for the file hepai-1.2.15.tar.gz.

File metadata

  • Download URL: hepai-1.2.15.tar.gz
  • Upload date:
  • Size: 448.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.11

File hashes

Hashes for hepai-1.2.15.tar.gz
Algorithm Hash digest
SHA256 591ff5eaca5c5d495e10dd9af40096365c4de6bc43115958322f8e64e6cf1aaa
MD5 14dd6fc7cdca15a09e4b3ad7302a9bc4
BLAKE2b-256 e136a281083f2865928c9013801382fd42e858d6d737fd035490c207a2f9c873

See more details on using hashes here.

File details

Details for the file hepai-1.2.15-py2.py3-none-any.whl.

File metadata

  • Download URL: hepai-1.2.15-py2.py3-none-any.whl
  • Upload date:
  • Size: 837.2 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.11

File hashes

Hashes for hepai-1.2.15-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 27c0bea2c4045cbc03faa5f24772015ba018595711d15ec7df482d5dcd449820
MD5 0ce867d66f3b2f87340f7ac364f8e56f
BLAKE2b-256 70131817c26f041611b888dd34e1b9c39da7c56d18a3bb777f733429acf2e7ec

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page