使用Microsoft Autogen遇Completions.create()参数错误，如何解决？

1. 解决Completions.create() got an unexpected keyword argument 'request_timeout'错误 #

错误原因是request_timeout参数被放在了llm_config顶层，而Autogen要求该参数属于单个模型的配置项，需将其移至config_list的字典中。

修改后的核心代码片段：

config_list = [
    {
        'model': 'gpt-4',
        'api_key': '你的真实API密钥',
        'request_timeout': 600  # 将request_timeout移至此处
    }
]

llm_config={
    "seed": 42,
    "config_list": config_list,
    "temperature": 0
    # 移除顶层的request_timeout参数
}

2. 解决API密钥格式不符合OpenAI规范的警告 #

警告源于代码中使用了占位符'API_KEY'，需替换为真实有效的OpenAI API密钥：

• 密钥必须以sk-开头，格式为sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
• 确保密钥未过期、权限正常，可在OpenAI平台的API密钥管理页面获取

完整修改后的代码：

import autogen
from autogen import AssistantAgent, UserProxyAgent

config_list = [
    {
        'model': 'gpt-4',
        'api_key': 'sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx',  # 替换为你的真实API密钥
        'request_timeout': 600
    }
]

llm_config={
    "seed": 42,
    "config_list": config_list,
    "temperature": 0
}

assistant = autogen.AssistantAgent(
    name="assistant",
    llm_config=llm_config,
    system_message="Chief technical officer of a tech company"
)

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="ALWAYS",
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={"work_dir": "web"},
    llm_config=llm_config,
    system_message="""Reply TERMINATE if the task has been solved at full satisfaction.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet."""
)

task = """
Write python code to output numbers 1 to 100
"""

user_proxy.initiate_chat(
    assistant,
    message=task
)

内容的提问来源于stack exchange，提问作者esllmllama