Memory

This notebook goes over how to use Memory with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object.

from langchain.prompts import (
    ChatPromptTemplate, 
    MessagesPlaceholder, 
    SystemMessagePromptTemplate, 
    HumanMessagePromptTemplate
)

prompt = ChatPromptTemplate.from_messages([
    SystemMessagePromptTemplate.from_template("The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know."),
    MessagesPlaceholder(variable_name="history"),
    HumanMessagePromptTemplate.from_template("{input}")
])

from langchain.chains import ConversationChain
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory

llm = ChatOpenAI(temperature=0)

We can now initialize the memory. Note that we set return_messages=True To denote that this should return a list of messages when appropriate

memory = ConversationBufferMemory(return_messages=True)

We can now use this in the rest of the chain.

conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)

conversation.predict(input="Hi there!")

'Hello! How can I assist you today?'

conversation.predict(input="I'm doing well! Just having a conversation with an AI.")

"That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?"

conversation.predict(input="Tell me about yourself.")

"Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?"