Can i use a single Agent for Chat Completion Tasks such as Summarization ?

[elexira]

My work contains combination of tasks that involves a single agent and multiple agents. For example traditionally, we would use something like below

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "system", "content": "Given the history of chat and user question what is the user asking ?"},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)

The desirable output from above task would be something like:

where did Los Angeles Dodgers won the World Series in 2020

Is there a way for me to accomplish the task above within an Autogen framework ?

The summary then becomes the input to a agent-based conversation

user_proxy.initiate_chat(assistant, message=where did Los Angeles Dodgers won the World Series in 2020)

[elexira]

This can be achieved by method generate_oai_reply(messages)