You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Ask what version of pyautogen will support 'register_for_llm' later, because I'm using the local model chatGLM, needs openai<1, so I use pyautogen==0.1.14, but reports an error: AttributeError: 'AssistantAgent' object has no attribute 'register_for_llm'. Did you mean: 'register_reply'?
Steps to reproduce
import autogen
from typing import Literal
from pydantic import BaseModel, Field
from typing_extensions import Annotated
# 1、建立必要配置
config_list = [
{
"model": "chatglm2-6b",
"api_base": "http://localhost:8002/v1",
"api_type": "open_ai",
"api_key": "NULL",
}]
# 2、大模型请求配置
llm_config = {
"request_timeout": 600,
"seed": 45, # change the seed for different trials
"config_list": config_list,
"temperature": 0,
"max_tokens":8192,
}
# 3、新建一个助理智能体
assistant = autogen.AssistantAgent(
name="assistant",
llm_config=llm_config,
system_message="For currency exchange tasks, only use the functions you have been provided with. Reply TERMINATE when the task is done."
)
#创建名为 user_proxy 的用户代理实例,这里定义为进行干预
user_proxy = autogen.UserProxyAgent(
name="user_proxy",
human_input_mode="NEVER",
max_consecutive_auto_reply=10,
is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
code_execution_config={"work_dir":"_output", "use_docker":False},
llm_config=llm_config,
)
CurrencySymbol = Literal["USD", "EUR"]
def exchange_rate(base_currency: CurrencySymbol, quote_currency: CurrencySymbol) -> float:
if base_currency == quote_currency:
return 1.0
elif base_currency == "USD" and quote_currency == "EUR":
return 1 / 1.1
elif base_currency == "EUR" and quote_currency == "USD":
return 1.1
else:
raise ValueError(f"Unknown currencies {base_currency}, {quote_currency}")
@assistant.register_for_llm(description="Currency exchange calculator.")
@user_proxy.register_for_execution()
def currency_calculator(
base_amount: Annotated[float, "Amount of currency in base_currency"],
base_currency: Annotated[CurrencySymbol, "Base currency"] = "USD",
quote_currency: Annotated[CurrencySymbol, "Quote currency"] = "EUR",
) -> str:
quote_amount = exchange_rate(base_currency, quote_currency) * base_amount
return f"{quote_amount} {quote_currency}"
task1 = """How much is 123.45 USD in EUR?"""
user_proxy.initiate_chat(assistant,message=task1)
Screenshots and logs
Traceback (most recent call last):
File "/ldata/llms/autogen/ZY/test.py", line 59, in <module>
@assistant.register_for_llm(description="Currency exchange calculator.")
AttributeError: 'AssistantAgent' object has no attribute 'register_for_llm'. Did you mean: 'register_reply'?
Additional Information
No response
The text was updated successfully, but these errors were encountered:
Describe the issue
Ask what version of pyautogen will support 'register_for_llm' later, because I'm using the local model chatGLM, needs openai<1, so I use pyautogen==0.1.14, but reports an error: AttributeError: 'AssistantAgent' object has no attribute 'register_for_llm'. Did you mean: 'register_reply'?
Steps to reproduce
Screenshots and logs
Additional Information
No response
The text was updated successfully, but these errors were encountered: