langchain/docs/examples/memory/adding_memory.ipynb

Adding Memory To an LLMChain

This notebook goes over how to use the Memory class with an LLMChain. For the purposes of this walkthrough, we will add the ConversationBufferMemory class, although this can be any memory class.

In [1]:

from langchain.chains.conversation.memory import ConversationBufferMemory
from langchain import OpenAI, LLMChain, PromptTemplate

The most important step is setting up the prompt correctly. In the below prompt, we have two input keys: one for the actual input, another for the input from the Memory class. Importantly, we make sure the keys in the PromptTemplate and the ConversationBufferMemory match up (chat_history).

In [2]:

template = """You are a chatbot having a conversation with a human.

{chat_history}
Human: {human_input}
Chatbot:"""

prompt = PromptTemplate(
    input_variables=["chat_history", "human_input"], 
    template=template
)
memory = ConversationBufferMemory(memory_key="chat_history")

In [3]:

llm_chain = LLMChain(
    llm=OpenAI(), 
    prompt=prompt, 
    verbose=True, 
    memory=memory,
)

In [4]:

llm_chain.predict(human_input="Hi there my friend")

Out [4]:

> Entering new chain...
Prompt after formatting:
You are a chatbot having a conversation with a human.


Human: Hi there my friend
Chatbot:

> Finished chain.

' Hi there!'

In [5]:

llm_chain.predict(human_input="Not to bad - how are you?")

Out [5]:

> Entering new chain...
Prompt after formatting:
You are a chatbot having a conversation with a human.


Human: Hi there my friend
AI:  Hi there!
Human: Not to bad - how are you?
Chatbot:

> Finished chain.

"\n\nI'm doing well, thanks for asking. How about you?"

In [ ]: