How to make a llm remember previous runtime chats

tux_tina

I want my llm chatbot to remember previous conversations even after restarting the program. It is made with llama cpp python and langchain, it has conversation memory of the present chat but obviously doesn't have memory of the previous chat and that's what I need help in. import threading from operator import itemgetter from langchain.llms import LlamaCpp from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder from...

Originally asked by QUARKS on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

A little late, but remember that openAI is just a language prediction model. It takes a string of text, and predicts what comes next based on all its training data. Think about all the training data it's had on the internet. This includes screenplays, short novels, fanfictions, etc. It knows a lot about how to continue conversations based on the likelyhood of the next word, but only if it's in the right format. So, instead of formatting your data like just regular strings, format it in a way that makes sense for the AI to continue it, such as in a screenplay. In other words, iterate on a string like: import openai openai.api_key = "secret_key" model_engine = "text-davinci-003" conversation...

Full answer by luce: https://stackoverflow.stackexchange.com/a/79508444 (CC BY-SA 4.0).

Need it done for your business? UphillTech.