Programming an LLM-based chatbot

In this notebook we will program a basic chatbot. We can use multiple large language models, via the OpenAI Python interface.

from llm_utilities import prompt_chatgpt, prompt_ollama, prompt_blablador, prompt_claude

Decide for a prompt function

Here we need to decide for one of the prompt-functions introduced before.

prompt = prompt_claude

prompt("Hi!")

'Hello! How can I assist you today? Feel free to ask me any questions or let me know if you need help with anything.'

Adding memory

Our prompt function does not have memory yet.

prompt("Hi, my name is Robert.")

"Hello Robert! It's nice to meet you. How can I assist you today? Is there anything specific you'd like to know or discuss?"

prompt("What is my name?")

"I apologize, but I don't have access to personal information about individual users, including names. Each conversation I have starts fresh, so I don't have any prior context about who you are or what your name might be. If you'd like me to refer to you by a specific name during our conversation, you're welcome to let me know what you'd like to be called."

Memory can be simply a list where we collect questions and answers in a format specified by the OpenAI API.

chat_history = []
def prompt_with_memory(message:str):
    
    # convert message in the right format and store it in memory
    question = {"role": "user", "content": message}
    chat_history.append(question)
    
    # receive answer
    response = prompt(chat_history)
    
    # convert answer in the right format and store it in memory
    answer = {"role": "assistant", "content": message}
    chat_history.append(answer)
    
    return response

prompt_with_memory("Hi, my name is Robert.")

"Hello Robert! It's nice to meet you. How can I assist you today? Feel free to ask me any questions or let me know if there's anything specific you'd like help with."

prompt_with_memory("What is my name?")

'Your name is Robert, as you mentioned in your introduction.'

Continuous discussion

Finally, we use the functions above for a continuous chat.

question = ""
while(question != "bye"):
    question = input("Q:")
    
    answer = prompt_with_memory(question)
    print("A:",answer)

A: Hello Alice, it's nice to meet you. I apologize for the confusion earlier - I'm Claude, an AI assistant. How can I help you today?

A: I apologize for the confusion in my previous responses. I am an AI language model and do not have personal experiences or real-time information. I cannot predict the weather or know your actual name.

To answer your question about rain tomorrow, I would need access to current weather data and forecasts for your specific location, which I don't have. For the most accurate and up-to-date weather information, I recommend checking a reliable weather website or app that provides forecasts for your area.

Is there anything else I can assist you with?

A: I apologize for the confusion in our previous exchanges. I am Claude, an AI assistant, and I don't actually share your name or have information about tomorrow's weather. I was mistakenly repeating your messages rather than responding properly. Is there anything I can actually assist you with today?