LangChain: Memory

Outline

ConversationBufferMemory
ConversationBufferWindowMemory
ConversationTokenBufferMemory
ConversationSummaryMemory

ConversationBufferMemory

## Get your OpenAI API
import openai
import os
from langchain.chat_models import AzureChatOpenAI
from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationChain
from langchain.memory import ConversationBufferMemory

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv())

# Set OpenAI API key
os.environ["OPENAI_API_TYPE"] = os.getenv("api_type")
os.environ["OPENAI_API_BASE"] = os.getenv("api_base")
os.environ["OPENAI_API_VERSION"] = os.getenv("api_version")
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")

llm = AzureChatOpenAI(deployment_name="chatgpt-gpt35-turbo",model_name="gpt-35-turbo",temperature=0.0)

memory = ConversationBufferMemory()
conversation = ConversationChain(
    llm=llm, 
    memory = memory,
    verbose=True
)

conversation.predict(input="Hi, my name is Andrew")

Error in on_chain_start callback: 'name'


Prompt after formatting:
[32;1m[1;3mThe 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.

Current conversation:

Human: Hi, my name is Andrew
AI:[0m

[1m> Finished chain.[0m





"Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?"

conversation.predict(input="What is 1+1?")

Error in on_chain_start callback: 'name'


Prompt after formatting:
[32;1m[1;3mThe 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.

Current conversation:
Human: Hi, my name is Andrew
AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?
Human: What is 1+1?
AI:[0m

[1m> Finished chain.[0m





'The answer to 1+1 is 2.'

conversation.predict(input="What is my name?")

Error in on_chain_start callback: 'name'


Prompt after formatting:
[32;1m[1;3mThe 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.

Current conversation:
Human: Hi, my name is Andrew
AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?
Human: What is 1+1?
AI: The answer to 1+1 is 2.
Human: What is my name?
AI:[0m

[1m> Finished chain.[0m





'Your name is Andrew, as you mentioned earlier.'

print(memory.buffer)

Human: Hi, my name is Andrew
AI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?
Human: What is 1+1?
AI: The answer to 1+1 is 2.
Human: What is my name?
AI: Your name is Andrew, as you mentioned earlier.

memory.load_memory_variables({})

{'history': "Human: Hi, my name is Andrew\nAI: Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?\nHuman: What is 1+1?\nAI: The answer to 1+1 is 2.\nHuman: What is my name?\nAI: Your name is Andrew, as you mentioned earlier."}

memory = ConversationBufferMemory()

memory.save_context({"input": "Hi"}, 
                    {"output": "What's up"})

print(memory.buffer)

Human: Hi
AI: What's up

memory.load_memory_variables({})

{'history': "Human: Hi\nAI: What's up"}

memory.save_context({"input": "Not much, just hanging"}, 
                    {"output": "Cool"})

memory.load_memory_variables({})

{'history': "Human: Hi\nAI: What's up\nHuman: Not much, just hanging\nAI: Cool"}

ConversationBufferWindowMemory

from langchain.memory import ConversationBufferWindowMemory

memory = ConversationBufferWindowMemory(k=1)

memory.save_context({"input": "Hi"},
                    {"output": "What's up"})
memory.save_context({"input": "Not much, just hanging"},
                    {"output": "Cool"})

memory.load_memory_variables({})

{'history': 'Human: Not much, just hanging\nAI: Cool'}

memory = ConversationBufferWindowMemory(k=1)
conversation = ConversationChain(
    llm=llm, 
    memory = memory,
    verbose=False
)

conversation.predict(input="Hi, my name is Andrew")

"Hello Andrew, it's nice to meet you. My name is AI. How can I assist you today?"

conversation.predict(input="What is 1+1?")

'The answer to 1+1 is 2.'

conversation.predict(input="What is my name?")

"I'm sorry, I don't have access to that information. Could you please tell me your name?"

ConversationTokenBufferMemory

#!pip install tiktoken

Below notebook will be helpfull to understand how to use tiktoken library to generate tokens for your application.

https://github.com/pinecone-io/examples/blob/master/generation/langchain/handbook/03-langchain-conversational-memory.ipynb

from langchain.memory import ConversationTokenBufferMemory
from langchain.llms import OpenAI
import tiktoken

llm = OpenAI(
    temperature=0, 
    model_name='text-davinci-003'  # can be used with llms like 'gpt-3.5-turbo'
)

memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=30)
memory.save_context({"input": "AI is what?!"},
                    {"output": "Amazing!"})
memory.save_context({"input": "Backpropagation is what?"},
                    {"output": "Beautiful!"})
memory.save_context({"input": "Chatbots are what?"}, 
                    {"output": "Charming!"})
# Ideally you should use ChatGPT, I am getting error ```Warning: model not found. Using cl100k_base encoding.```. So, I am using Instruct GPT.

memory.load_memory_variables({})

{'history': 'AI: Amazing!\nHuman: Backpropagation is what?\nAI: Beautiful!\nHuman: Chatbots are what?\nAI: Charming!'}

ConversationSummaryMemory

from langchain.memory import ConversationSummaryBufferMemory

# create a long string
schedule = "There is a meeting at 8am with your product team. \
You will need your powerpoint presentation prepared. \
9am-12pm have time to work on your LangChain \
project which will go quickly because Langchain is such a powerful tool. \
At Noon, lunch at the italian resturant with a customer who is driving \
from over an hour away to meet you to understand the latest in AI. \
Be sure to bring your laptop to show the latest LLM demo."

memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=4000)
memory.save_context({"input": "Hello"}, {"output": "What's up"})
memory.save_context({"input": "Not much, just hanging"},
                    {"output": "Cool"})
memory.save_context({"input": "What is on the schedule today?"}, 
                    {"output": f"{schedule}"})

memory.load_memory_variables({})

{'history': "Human: Hello\nAI: What's up\nHuman: Not much, just hanging\nAI: Cool\nHuman: What is on the schedule today?\nAI: There is a meeting at 8am with your product team. You will need your powerpoint presentation prepared. 9am-12pm have time to work on your LangChain project which will go quickly because Langchain is such a powerful tool. At Noon, lunch at the italian resturant with a customer who is driving from over an hour away to meet you to understand the latest in AI. Be sure to bring your laptop to show the latest LLM demo."}

llm_turbo = AzureChatOpenAI(deployment_name="chatgpt-gpt35-turbo",model_name="gpt-35-turbo",temperature=0.0)

conversation = ConversationChain(
    llm=llm_turbo, 
    memory = memory,
    verbose=True
)

conversation.predict(input="What would be a good demo to show?")

Error in on_chain_start callback: 'name'


Prompt after formatting:
[32;1m[1;3mThe 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.

Current conversation:
Human: Hello
AI: What's up
Human: Not much, just hanging
AI: Cool
Human: What is on the schedule today?
AI: There is a meeting at 8am with your product team. You will need your powerpoint presentation prepared. 9am-12pm have time to work on your LangChain project which will go quickly because Langchain is such a powerful tool. At Noon, lunch at the italian resturant with a customer who is driving from over an hour away to meet you to understand the latest in AI. Be sure to bring your laptop to show the latest LLM demo.
Human: What would be a good demo to show?
AI:[0m

[1m> Finished chain.[0m





"Based on the customer's interests, I would recommend showing the LLM's natural language processing capabilities and how it can be used to analyze large amounts of data quickly and accurately. You could also demonstrate how the LLM can be integrated with other AI tools to create a more comprehensive solution."

memory.load_memory_variables({})

{'history': "Human: Hello\nAI: What's up\nHuman: Not much, just hanging\nAI: Cool\nHuman: What is on the schedule today?\nAI: There is a meeting at 8am with your product team. You will need your powerpoint presentation prepared. 9am-12pm have time to work on your LangChain project which will go quickly because Langchain is such a powerful tool. At Noon, lunch at the italian resturant with a customer who is driving from over an hour away to meet you to understand the latest in AI. Be sure to bring your laptop to show the latest LLM demo.\nHuman: What would be a good demo to show?\nAI: Based on the customer's interests, I would recommend showing the LLM's natural language processing capabilities and how it can be used to analyze large amounts of data quickly and accurately. You could also demonstrate how the LLM can be integrated with other AI tools to create a more comprehensive solution."}