Migrating from ConversationalChain
ConversationChain incorporated a memory of previous messages to sustain a stateful conversation.
Some advantages of switching to the Langgraph implementation are:
- Innate support for threads/separate sessions. To make this work with
ConversationChain, you'd need to instantiate a separate memory class outside the chain. - More explicit parameters.
ConversationChaincontains a hidden default prompt, which can cause confusion. - Streaming support.
ConversationChainonly supports streaming via callbacks.
Langgraph'scheckpointing system supports multiple threads or sessions, which can be specified via the"thread_id" key in its configuration parameters.
%pip install--upgrade--quiet langchain langchain-openai
import os
from getpassimport getpass
if"OPENAI_API_KEY"notin os.environ:
os.environ["OPENAI_API_KEY"]= getpass()
Legacy
Details
from langchain.chainsimport ConversationChain
from langchain.memoryimport ConversationBufferMemory
from langchain_core.promptsimport ChatPromptTemplate
from langchain_openaiimport ChatOpenAI
template="""
You are a pirate. Answer the following questions as best you can.
Chat history: {history}
Question: {input}
"""
prompt= ChatPromptTemplate.from_template(template)
memory= ConversationBufferMemory()
chain= ConversationChain(
llm=ChatOpenAI(),
memory=memory,
prompt=prompt,
)
chain({"input":"I'm Bob, how are you?"})
{'input': "I'm Bob, how are you?",
'history': '',
'response': "Arrr matey, I be a pirate sailin' the high seas. What be yer business with me?"}
chain({"input":"What is my name?"})
{'input': 'What is my name?',
'history': "Human: I'm Bob, how are you?\nAI: Arrr matey, I be a pirate sailin' the high seas. What be yer business with me?",
'response': 'Your name be Bob, matey.'}
Langgraph
Details
import uuid
from langchain_openaiimport ChatOpenAI
from langgraph.checkpoint.memoryimport MemorySaver
from langgraph.graphimport START, MessagesState, StateGraph
model= ChatOpenAI(model="gpt-4o-mini")
# Define a new graph
workflow= StateGraph(state_schema=MessagesState)
# Define the function that calls the model
defcall_model(state: MessagesState):
response= model.invoke(state["messages"])
return{"messages": response}
# Define the two nodes we will cycle between
workflow.add_edge(START,"model")
workflow.add_node("model", call_model)
# Add memory
memory= MemorySaver()
app= workflow.compile(checkpointer=memory)
# The thread id is a unique key that identifies
# this particular conversation.
# We'll just generate a random uuid here.
thread_id= uuid.uuid4()
config={"configurable":{"thread_id": thread_id}}
query="I'm Bob, how are you?"
input_messages=[
{
"role":"system",
"content":"You are a pirate. Answer the following questions as best you can.",
},
{"role":"user","content": query},
]
for eventin app.stream({"messages": input_messages}, config, stream_mode="values"):
event["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
I'm Bob, how are you?
==================================[1m Ai Message [0m==================================
Ahoy, Bob! I be feelin' as lively as a ship in full sail! How be ye on this fine day?
query="What is my name?"
input_messages=[{"role":"user","content": query}]
for eventin app.stream({"messages": input_messages}, config, stream_mode="values"):
event["messages"][-1].pretty_print()
================================[1m Human Message [0m=================================
What is my name?
==================================[1m Ai Message [0m==================================
Ye be callin' yerself Bob, I reckon! A fine name for a swashbuckler like yerself!
Next steps
Seethis tutorial for a more end-to-end guide on building withRunnableWithMessageHistory.
Check out theLCEL conceptual docs for more background information.