Very new to Autogen. I have a model meta-llama-3.1-8b-instruct running on LMStudio at http://127.0.0.1:1234/v1. I am trying to run the example code provided here at Autogen Getting Started. The difference is , I have changed the config_list to work with LMStudio
import autogen
import os
import dotenv
from autogen import AssistantAgent, UserProxyAgent
config_list = [{
"api_type": "open_ai",
"api_base": "http://127.0.0.1:1234/v1",
"api_key": "NULL"
}]
llm_config = {
"request_timeout": 600,
"seed": 42,
"config_list": config_list,
"temperature": 0
}
assistant = AssistantAgent("assistant", llm_config=llm_config)
user_proxy = UserProxyAgent("user_proxy", code_execution_config=False)
# Start the chat
user_proxy.initiate_chat(
assistant,
message="Tell me a joke about an egg and chicken.",
)
However, I get the following error. Am I missing something obvious ?
TypeError: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given
I was just working on this also and managed to get it running with llama-3.2-1b running locally on LM Studio.
from autogen import AssistantAgent, UserProxyAgent
config_list = [{
"api_type": "open_ai",
"base_url": "http://localhost:1234/v1",
"api_key": "NULL"
}]
llm_config = {
"seed": 42,
"config_list": config_list,
"temperature": 0,
"model": "llama-3.2-1b-instruct"
}
assistant = AssistantAgent("assistant", llm_config=llm_config)
user_proxy = UserProxyAgent("user_proxy", code_execution_config=False)
# Start the chat
user_proxy.initiate_chat(
assistant,
message="Tell me a joke about an egg and chicken.",
)
Example output:
user_proxy (to assistant):
Tell me a joke about an egg and chicken.
--------------------------------------------------------------------------------
assistant (to user_proxy):
Here's one:
Why did the egg go to therapy after meeting the chicken?
Because it was cracking under the pressure!
I hope that cracked you up!
--------------------------------------------------------------------------------