Memory means carrying useful information from earlier turns or earlier workflow steps. In chat apps, memory may include recent messages. In business workflows, state may include selected documents, user role, tool results, approvals, or partial outputs.
The key is to store the right information in the right place. Do not blindly append the entire conversation forever. Summarize, trim, retrieve, and separate durable user profile data from temporary chat context.
LangChain is expanded here with a practical explanation, multiple examples, and beginner-focused checks so the idea is easier to learn from this page alone.
Read the concept first, then trace the example line by line. The important habit is to connect the rule to visible behavior instead of memorizing only the name.
Memory is not magic. It is state management for LLM applications, and it should be designed like any other stateful system.
Short-term memory keeps the current conversation coherent. Long-term memory stores durable facts or preferences. Workflow state tracks intermediate steps in a multi-step process.
Memory can leak sensitive information, increase token cost, and preserve incorrect assumptions. Treat memory as data with privacy, retention, and correction rules.
LangChain becomes much easier when you separate the concept from the tool syntax. First identify the problem being solved, then identify the data or resource being changed, and finally identify the proof that the change worked.
In LangChain, this topic should be studied through prompt inputs, model calls, parser behavior, retrieved context, tool boundaries, and validation. Those points explain not only how to use the feature, but also why it fails when the wrong assumption is made.
The previous audit note was: under 650 content words . This expanded section adds a fuller explanation, concrete examples, and practice guidance so the page can stand on its own for beginners.
A good way to learn this page is to read the normal path once, run or trace the example, then intentionally change one input to observe the different result. That one change teaches more than memorizing several definitions.
Start with a tiny project scenario. For example, imagine one user action, one request, one resource, one function call, or one batch of data. Keep the scenario small enough that every step can be explained without skipping details.
Next, describe the movement of information. Where does the input start? Which rule or component handles it? What result should appear? If the result is wrong, where would you inspect first?
Finally, compare two outcomes. The correct outcome proves that you understand the main rule. The incorrect outcome teaches the symptom, which is what you will recognize later during debugging or interviews.
This pattern keeps chat history outside the model and injects it only when invoking the chain.
from langchain_core.chat_history import InMemoryChatMessageHistory
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_openai import ChatOpenAI
store = {}
def get_history(session_id: str):
if session_id not in store:
store[session_id] = InMemoryChatMessageHistory()
return store[session_id]
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful programming mentor."),
MessagesPlaceholder(variable_name="history"),
("human", "{question}"),
])
chain = prompt | ChatOpenAI(model="gpt-4o-mini", temperature=0.2)
chat = RunnableWithMessageHistory(
chain,
get_history,
input_messages_key="question",
history_messages_key="history",
)
config = {"configurable": {"session_id": "user-123"}}
print(chat.invoke({"question": "What is RAG?"}, config=config).content)
print(chat.invoke({"question": "Give me one use case for it."}, config=config).content)from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
prompt = ChatPromptTemplate.from_template('Explain LangChain with one example and one warning.')
chain = prompt | (lambda message: message.text) | StrOutputParser()
# In a real app, replace the lambda with a chat model and keep the parser step explicit.def check_answer(answer: str) -> list[str]:
issues = []
if 'source' not in answer.lower():
issues.append('Add sources or retrieved context.')
if len(answer) < 120:
issues.append('Add a fuller explanation for LangChain.')
return issues
print(check_answer('Short answer without source'))Append every message forever.
Trim, summarize, or retrieve relevant memory.
Store user secrets in long-term memory.
Store only necessary, user-approved durable facts.
Learning LangChain only as a term.
Learn it through a working example, a boundary case, and a failure case.
Skipping verification.
Always check output, state, logs, metrics, query results, or compiler feedback.
Changing many things at once while debugging.
Change one setting, input, or line, then inspect the result.
No. Memory usually stores conversation or user state. RAG retrieves external knowledge from documents or databases.
Yes. Old, irrelevant, or incorrect memory can distract the model and produce poor answers.
Start with one tiny example, trace every step, then compare it with a broken version.
Verify the visible result: output, state, log entry, metric, query result, compiler feedback, or rendered behavior.
It often combines vocabulary with behavior. The confusion drops when you trace the input, rule, result, and failure path.
Explore 500+ free tutorials across 20+ languages and frameworks.