ChatGLM2使用api_key本地部署

晓shuo

已于 2024-05-13 20:34:41 修改

阅读量597

点赞数 7

文章标签：数据库大模型人工智能

于 2024-02-28 21:30:31 首次发布

本文链接：https://blog.csdn.net/python_plus/article/details/136356666

版权

本文介绍了如何在Python程序中安装并使用阿里云DashscopeAPI调用ChatGLM2-6B版本的AI助手，通过提供API_KEY并展示了一个示例请求及其输出结果。

摘要由CSDN通过智能技术生成

在这里插入图片描述

安装

按照以下网址的指示申请api_key然后替换程序中的your_api_key

https://help.aliyun.com/zh/dashscope/developer-reference/activate-dashscope-and-create-an-api-key?spm=a2c4g.11186623.0.0.459ac11aaiehfX

程序

from http import HTTPStatus

from dashscope import Generation
import dashscope

dashscope.api_key = your_api_key
def chatglmv2_call(prompt):
    rsp = Generation.call(model='chatglm-6b-v2',
                          prompt=prompt,
                          history=[])
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        glm_result = rsp.output['text']

    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))

    return glm_result
if __name__ == '__main__':
    prompt_TP = "Who are you?"

    glm_TP = chatglmv2_call(prompt=prompt_TP)
    print(glm_TP)

程序运行结果

{"status_code": 200, "request_id": "6faa94b1-6fb1-95cb-8fb5-4a7331bee0b2", "code": "", "message": "", "output": {"text": "I am an AI assistant named ChatGLM2-6B, which is developed based on the language model jointly trained by Tsinghua University KEG Lab and Zhipu AI Company in 2023. My job is to provide appropriate answers and support to users' questions and requests.", "finish_reason": "stop", "choices": null}, "usage": {"input_tokens": 20, "output_tokens": 63, "total_tokens": 83}}
I am an AI assistant named ChatGLM2-6B, which is developed based on the language model jointly trained by Tsinghua University KEG Lab and Zhipu AI Company in 2023. My job is to provide appropriate answers and support to users' questions and requests.