腾讯混元大模型集成LangChain

slient_love

已于 2024-07-10 17:05:52 修改

阅读量988

点赞数 4

CC 4.0 BY-SA版权

文章标签： langchain python

于 2024-07-10 16:53:09 首次发布

本文链接：https://blog.csdn.net/slient_love/article/details/140327834

腾讯混元大模型集成LangChain

获取API密钥

登录控制台–>访问管理–>API密钥管理–>新建密钥，获取到SecretId和SecretKey。访问链接：https://console.cloud.tencent.com/cam/capi

python SDK方式调用大模型

可参考腾讯官方API

import json
import types

from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.hunyuan.v20230901 import hunyuan_client, models

try:
    cred = credential.Credential("SecretId", "SecretKey")
    httpProfile = HttpProfile()
    httpProfile.endpoint = "hunyuan.tencentcloudapi.com"

    clientProfile = ClientProfile()
    clientProfile.httpProfile = httpProfile
    client = hunyuan_client.HunyuanClient(cred, "", clientProfile)

    # 实例化一个请求对象,每个接口都会对应一个request对象
    req = models.ChatCompletionsRequest()
    params = {
   
   
        "TopP": 1,
        "Temperature": 1,
        "Model": "hunyuan-pro",
        "Messages": [
            {
   
   
                "Role": "system",
                "Content": "将英文单词转换为包括中文翻译、英文释义和一个例句的完整解释。请检查所有信息是否准确，并在回答时保持简洁，不需要任何其他反馈。"
            },
            {
   
   
                "Role": "user",
                "Content": "nice"
            }
        ]
    }
    req.from_json_string(json.dumps(params))

    resp = client.ChatCompletions(req)
    if isinstance(resp, types.GeneratorType):  # 流式响应
        for event in resp:
            print(