How to Use the Chat Module

This module is built to let you run multiple chat sessions in parallel with an AI model (like gpt-3.5-turbo, deepseek-chat, qwen-plus). Each session belongs to one user, but a user can have multiple sessions at the same time.

Think of it like this:

  • You are the user.
  • Each session is like a separate conversation thread.
  • The module will handle running them all at once and can save the results for you.

1. Initialize the Chat

chat = Chat(MODEL, try_mode=True)
  • MODEL is the model name you want to use.
  • You can also set options like temperature or add a filter function if you want to change the output style.

2. Add a Prompt

chat.use_prompt("Use email format the answer following question? {question}")
  • This sets a system prompt for all sessions.
  • The {question} placeholder will be replaced by each question you send.
  • If the input is a string, but placeholder in the prompt. The placeholder would be ignored and input will be appended in the prompt.

3. Choose the Output Format

  • Save results to file as JSONL:
chat.save_to("Translation/translation2.jsonl", disable_return=True).to_json()

  • Writes all answers into a file.

  • Each line is one response in JSON format.

  • disable_return=True means it won’t return results to your program, only save them.

  • Print results in JSON format:

chat.to_json(indent=2)
  • Outputs JSON to the console.
  • indent=2 makes it pretty-printed.

4. Run the Chat

results = await chat.achat(questions)
  • questions is a list of sessions, and each session is a list of questions.
  • Example:
questions = [
    [{'question': "what is 氣?"}, "what is 阴阳五行"],  # session 1
    [{'question': "what is air"}]                      # session 2
]
  • This runs both sessions in parallel.
  • Each session gets its own history, so follow-up questions will make sense.

The work flow is like this

workflow

5. Example Workflows

from openai_chat import Chat
import asyncio
import logging 
import pprint


MODEL = "gpt-3.5-turbo"

TCM_PROMPT = "Use email format the answer following question? {question}"

async def output_to_file(questions: list[list]):
    chat = Chat(MODEL, try_mode=True) \
        .use_prompt(TCM_PROMPT) \
        .save_to('Translation/translation2.jsonl', disable_return=True) \
        .to_json()
    
    print(chat.info)
    await chat.achat(questions)

async def output_to_stdout(questions):
    def filter(character: str):
        return character.capitalize()
    
    chat = Chat(MODEL, filter=filter, temperature=0.7).to_json(indent=2).use_prompt(TCM_PROMPT)
    print(chat.info)

    results = await chat.achat(questions)
    pprint.pprint(results)

async def main():
    questions = [
        [{'question': "what is 氣?"}, "what is 阴阳五行"], 
        [{'question': "what is air"}]
    ]
    await output_to_file(questions)
    await output_to_stdout(questions)



if __name__ == "__main__":
    asyncio.run(main())

Save to File

await output_to_file(questions)
  • Runs all sessions and writes answers into translation2.jsonl.
await output_to_stdout(questions)
  • Runs all sessions and prints answers directly in your terminal.

6. Check Info

At any point, you can check the configuration:

print(chat.info)

It shows:

  • Which model you’re using.
  • Temperature setting.
  • Where results will be written.
  • Whether JSON formatting is enabled.

That’s it! In short:

  1. Create a Chat.
  2. Add a prompt.
  3. Decide on file or console output.
  4. Call achat(questions) with your sessions.