Przechowywanie długoterminowej pamięci między wątkami w LangGraph
Pamięć długoterminowa w różnych wątkach w LangGraph: przechowywanie nazw przestrzeni, operacje dodawania, pobierania i wyszukiwania, wyszukiwanie semantyczne w pamięci, usuwanie duplikatów przy zapisie oraz trwałość zapewniona przez Postgres.
Źródła: Long Term Memory in LangGraph| Part 16| class 24 of LangGraph | cswithshahil
Dlaczego krótkoterminowa pamięć wątków nie wystarcza
Historia rozmów z punktami kontrolnymi obejmuje tylko jeden wątek. Prawdziwi użytkownicy przechodzą między różnymi wątkami – w poniedziałek debugują LangChain, we wtorek planują podróż – więc informacje o nich są rozproszone. Pamięć długoterminowa (LTM) zapewnia trwałe przechowywanie: ekstraktor zapisuje dane osobowe po każdej rozmowie, a później przed udzieleniem odpowiedzi sprawdza tę bazę danych. Jeśli raz wybierzesz Python, a później poprosisz o sekwencję Fibonacciego, asystent może ponownie użyć tej preferencji bez konieczności ponownego informowania.
Bazy danych jako powierzchnia pamięci LangGraph
LangGraph modeluje LTM za pomocą baz danych. BaseStore definiuje operacje tworzenia, wyszukiwania, edycji i usuwania. Powszechne backendy to InMemoryStore do prototypów w pamięci RAM, oraz PostgresStore i RedisStore, gdy restart nie powinien usuwać danych z pamięci.
Operacje w samodzielnych bazach danych
Traktuj nazwy przestrzeni jak foldery. Są to tablice w Pythonie — ("users", "U1") lub bardziej złożone struktury typu ("users", "U1", "profile").
Twórz je za pomocą funkcji put(namespace, key, values). Aby pobrać jeden element, użyj funkcji get, gdy znasz klucz; aby wylistować zawartość nazwy przestrzeni, zastosuj funkcję search.
from langgraph.store.memory import InMemoryStore
# creating a store
store = InMemoryStore()
# creating a namespace
namespace = ("user", "u1")
Tworzenie wspomnień
# Adding memories
store.put(namespace, "1", {"data": "User likes pizza"})
store.put(namespace, "2", {"data": "User prefers dark mode"})
# another namespace
namespace2 = ("user", "u2")
# Add memories
store.put(namespace2, "1", {"data": "User likes pasta"})
store.put(namespace2, "2", {"data": "User prefers grid style navigation"})
Pobieranie jednego wspomnienia
# store.get(namespace, key)
store.get(namespace2, "2")
Item(namespace=['user', 'u2'], key='2', value={'data': 'User prefers grid style navigation'}, created_at='2026-01-06T15:05:16.376069+00:00', updated_at='2026-01-06T15:05:16.376070+00:00')
Pobieranie wszystkiego z nazwy przestrzeni
items = store.search(namespace2)
for item in items:
print(item.value)
{'data': 'User likes pasta'}
{'data': 'User prefers grid style navigation'}
Poyszukiwanie semantyczne wraz z rosnącą ilością danych
Wprowadzanie stu faktów z profilu do promptu przytłacza model. Zindeksuj magazyn za pomocą modelu embeddingowego (na przykład text-embedding-3-small), aby funkcja search mogła przyjąć query i limit, zwracając jedynie wektory bliskie aktualnemu pytaniu.
Semantic Search
from langchain_openai import OpenAIEmbeddings
from dotenv import load_dotenv
load_dotenv()
embedding_model = OpenAIEmbeddings(model='text-embedding-3-small')
store = InMemoryStore(index={'embed': embedding_model, 'dims':1536})
namespace = ('users', 'u1')
store.put(namespace, "1", {"data": "User prefers concise answers over long explanations"})
store.put(namespace, "2", {"data": "User likes examples in Python"})
store.put(namespace, "3", {"data": "User usually works late at night"})
store.put(namespace, "4", {"data": "User prefers dark mode in applications"})
store.put(namespace, "5", {"data": "User is learning machine learning"})
store.put(namespace, "6", {"data": "User dislikes overly theoretical explanations"})
store.put(namespace, "7", {"data": "User prefers step-by-step reasoning"})
store.put(namespace, "8", {"data": "User is based in India"})
store.put(namespace, "9", {"data": "User likes real-world analogies"})
store.put(namespace, "10", {"data": "User prefers bullet points over paragraphs"})
items = store.search(namespace, query="what is the user currently learning", limit=1)
for item in items:
print(item.value)
# output :{'data': 'User is learning machine learning'}
items = store.search(namespace, query="what are user's preferences", limit=3)
for item in items:
print(item.value)
# output :
# {'data': 'User prefers dark mode in applications'}
# {'data': 'User prefers bullet points over paragraphs'}
# {'data': 'User prefers concise answers over long explanations'}
Spersonalizacja tylko do odczytu w węźle czatu
Połącz magazyn z węzłem czatu LangGraph, który otrzymuje state, config (identyfikator użytkownika lub wątku) oraz store. Stwórz przestrzeń nazw na podstawie identyfikatora użytkownika, przeszukaj pamięci, połącz je z promptem systemowym i poinstruuj model, aby używał znanych nazw, projektów oraz tonu — plus kilku istotnych dodatkowych informacji.
Chatbot Reading Existing Memories
from dotenv import load_dotenv
load_dotenv()
from langchain_openai import ChatOpenAI
from langchain_core.runnables import RunnableConfig
from langchain_core.messages import SystemMessage
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) Create LTM store + seed memories (done BEFORE running the graph)
# ----------------------------
store = InMemoryStore()
user_id = "u1"
# Store user details as a single blob (simple for teaching)
# You can also split into multiple records; this keeps it easy.
user_details = ("user", user_id, "details")
store.put(user_details, "profile_1", {"data": "Name: Nitish"})
store.put(user_details, "profile_2", {"data": "Profession: Teaches AI on YouTube"})
store.put(user_details, "preference_1", {"data": "Prefers concise answers"})
store.put(user_details, "preference_2", {"data": "Likes examples in Python"})
store.put(user_details, "project_1", {"data": "Building MCP servers (Python-based project)"})
# ----------------------------
# 2) System prompt template (your prompt)
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible. For example, instead of "In TypeScript apps..."
say "Since your project is built with TypeScript..."
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Build graph: START -> chat -> END (read-only LTM)
# ----------------------------
llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
# Read-only: fetch user details memory (no writes)
user_details = ("user", user_id, "details")
items = store.search(user_details)
# Convert memory items into a string blob for {user_details_content}
# Keep it dead simple for teaching.
if items:
user_details_content = "\n".join(f"- {it.value.get('data', '')}" for it in items)
else:
user_details_content = "" # prompt says it may be empty
system_prompt = SYSTEM_PROMPT_TEMPLATE.format(
user_details_content=user_details_content
)
system_msg = SystemMessage(content=system_prompt)
response = llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
builder = StateGraph(MessagesState)
builder.add_node("chat", chat_node)
builder.add_edge(START, "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 4) Run it (provide user_id in config)
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
result = graph.invoke(
{"messages": [{"role": "user", "content": "Explain gen ai in simple terms."}]},
config,
)
print(result["messages"][-1].content)
# Sure, Nitish! Generative AI, or Gen AI, refers to a type of artificial intelligence that creates new content or data instead of just analyzing existing information. It can generate text, images, music, and more by learning patterns from large sets of data. For example, it can write a story, design an artwork, or compose a song based on the styles of various creators it has learned from.
#If you're considering using examples or applications of Gen AI for your YouTube teaching, there are plenty of interesting case studies you could explore, especially in creative fields.
#Here are a few questions to consider:
#1. Would you like to see specific examples of Gen AI in Python?
#2. Are you interested in exploring tools or libraries for building Gen AI projects?
#3. How would you like to incorporate Gen AI concepts into your teaching materials?
Zapisywanie nowych pamięci podczas rozmowy
Chatbot Creating New Memories
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) LLM that decides what to remember (structured output)
# ----------------------------
extractor_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryDecision(BaseModel):
should_write: bool = Field(description="Whether to store any memories")
memories: List[str] = Field(default_factory=list, description="Atomic user memories to store")
memory_extractor = extractor_llm.with_structured_output(MemoryDecision)
# ----------------------------
# 3) Graph: START -> remember -> END
# (Creates memories, but does NOT use them to answer)
# ----------------------------
def remember_only_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
namespace = ("user", user_id, "details")
# take latest user message
last_msg = state["messages"][-1].content
# LLM decides what to store
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(
content=(
"Extract LONG-TERM memories from the user's message.\n"
"Only store stable, user-specific info (identity, preferences, ongoing projects).\n"
"Do NOT store transient info.\n"
"Return should_write=false if nothing is worth storing.\n"
"Each memory should be a short atomic sentence."
)
),
{"role": "user", "content": last_msg},
]
)
# Write to store (LTM)
if decision.should_write:
for mem in decision.memories:
store.put(namespace, str(uuid.uuid4()), {"data": mem})
# IMPORTANT: we are NOT using memory, not even responding with the LLM.
# We just return a fixed acknowledgement.
return {"messages": [{"role": "assistant", "content": "Noted."}]}
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_only_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 4) Demo
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
res = graph.invoke({"messages": [{"role": "user", "content": "Hi my name is nitish"}]},config)
print("Assistant:", res["messages"][-1].content)
#output : Assistant: Noted.
res = graph.invoke({"messages": [{"role": "user", "content": "I teach AI on youtube"}]},config)
print("Assistant:", res["messages"][-1].content)
#output :Assistant: Noted.
res = graph.invoke({"messages": [{"role": "user", "content": "My favorite programming language is Python"}]},config)
print("Assistant:", res["messages"][-1].content)
# output :Assistant: Noted.
items = store.search(("user", "u1", "details"))
for item in items:
print(item.value['data'])
#output:
# User's name is Nitish.
# User teaches AI on YouTube.
# User's favorite programming language is Python.
#User's name is Nitish.
# User teaches AI on YouTube.
# User's favorite programming language is Python.
Automaticzne zapisy wymagają węzła pamięci umieszczonego przed rozmową. Specjalny model ekstraktora zwraca ustrukturyzowany wynik MemoryDecision: określa, czy dokonać zapisu i jakie elementy. Bez usuwania duplikatów powtarzanie frazy „moje imię to…” tworzy klony. Aktualizuj elementy za pomocą flagi is_new w odniesieniu do istniejących informacji pamięciowych i przechowuj tylko te nowe.
Chatbot Creating New Memories(without Duplication)
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) LLMs
# - memory_llm: extracts candidate memories + tells if each is NEW (no duplicate_of needed)
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory as a short sentence")
is_new: bool = Field(description="True if this memory is NEW and should be stored. False if duplicate/already known.")
class MemoryDecision(BaseModel):
should_write: bool = Field(description="Whether to store any memories")
memories: List[MemoryItem] = Field(default_factory=list, description="Atomic user memories to store")
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return an empty list.
"""
def chat_creates_memory_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
namespace = ("user", user_id, "details")
# A) Load existing memories
existing_items = store.search(namespace)
existing_texts = [it.value.get("data", "") for it in existing_items if it.value.get("data")]
user_details_content = "\n".join(f"- {t}" for t in existing_texts) if existing_texts else "(empty)"
# B) Latest user message
last_text = state["messages"][-1]
# C) LLM extracts memories + marks new vs duplicate
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=user_details_content)),
{"role": "user", "content": f"USER MESSAGE:\n{last_text}"},
]
)
# D) Store ONLY new memories
if decision.should_write:
for mem in decision.memories:
if mem.is_new:
store.put(namespace, str(uuid.uuid4()), {"data": mem.text})
return {"messages": [{"role": "assistant", "content": "Noted."}]}
# ----------------------------
# 4) Build graph: START -> chat -> END
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("chat", chat_creates_memory_node)
builder.add_edge(START, "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
config = {"configurable": {"user_id": "u1"}}
r1 = graph.invoke({"messages": [{"role": "user", "content": "My name is Nitish"}]}, config)
print("Assistant:", r1["messages"][-1].content)
# output: Assistant: Noted.
# Likely duplicate of the first memory -> is_new should be false -> saved=0
r2 = graph.invoke({"messages": [{"role": "user", "content": "I like Python for programming."}]}, config)
print("\nAssistant:", r2["messages"][-1].content)
# output:Assistant: Noted.
for it in store.search(("user", "u1", "details")):
print(it.value['data'])
# output:The user's name is Nitish.
# output:Nitish likes Python for programming.
Zintegrowany graf i trwałość danych produkcyjnych
Ostateczna sekwencja działań: start → pamięć (ekstrakcja i zapis) → rozmowa (czytanie i odpowiadanie) → koniec. Agent uczy się w trakcie rozmowy i natychmiast wykorzystuje nowe fakty.
Merged Workflow
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store (START EMPTY)
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) System prompt
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible.
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Memory extraction LLM
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory")
is_new: bool = Field(description="True if new, false if duplicate")
class MemoryDecision(BaseModel):
should_write: bool
memories: List[MemoryItem] = Field(default_factory=list)
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return should_write=false and an empty list.
"""
# ----------------------------
# 4) Node 1: remember
# ----------------------------
def remember_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
# existing memory
items = store.search(ns)
existing = "\n".join(it.value["data"] for it in items) if items else "(empty)"
# last user message
last_msg = state["messages"][-1].content
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=existing)),
{"role": "user", "content": last_msg},
]
)
if decision.should_write:
for mem in decision.memories:
if mem.is_new:
store.put(ns, str(uuid.uuid4()), {"data": mem.text})
return {} # no message change
# ----------------------------
# 5) Node 2: chat
# ----------------------------
chat_llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
items = store.search(ns)
user_details = "\n".join(it.value["data"] for it in items) if items else ""
system_msg = SystemMessage(
content=SYSTEM_PROMPT_TEMPLATE.format(
user_details_content=user_details or "(empty)"
)
)
response = chat_llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
# ----------------------------
# 6) Graph
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_node)
builder.add_node("chat", chat_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 7) Demo
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
result = graph.invoke({"messages": [{"role": "user", "content": "Hi, my name is Nitish"}]}, config)
result['messages'][-1].content
# output:'Hi Nitish! It’s great to meet you. How can I assist you today?'
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
result = graph.invoke({"messages": [{"role": "user", "content": "I teach AI on YouTube"}]}, config)
print(result['messages'][-1].content)
# output:That's great, Nitish! Teaching AI on YouTube must be really fulfilling. What topics do you cover in your videos? Are there any specific projects or concepts you find your audience is particularly interested in?
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:User's name is Nitish.
# output:Nitish teaches AI on YouTube.
result = graph.invoke({"messages": [{"role": "user", "content": "Explain GenAI simply"}]}, config)
print(result['messages'][-1].content)
# output:Sure, Nitish! Generative AI, often referred to as GenAI, is a type of artificial intelligence that can create new content based on the data it's trained on. This includes generating text, images, music, and even video.
# output:Here's a simple breakdown:
# output:1. **Learning from Examples:** GenAI is trained on vast amounts of data, learning the patterns, styles, and structures of the content it sees.
# output:2. **Creating Content:** Once trained, it can generate new content that resembles what it learned. For example, it can write a story in a specific style, create artwork, or compose music.
# output:3. **Applications:** It's used in various fields, from helping writers brainstorm ideas to producing artwork and even customer service chatbots that can engage with users in a conversational manner.
# output:If you're planning to teach this topic on your YouTube channel, emphasizing practical examples and real-world applications could be very engaging for your audience!
Do you want to explore specific applications of GenAI, tools for using it, or perhaps the ethics involved?
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:User's name is Nitish.
# output:Nitish teaches AI on YouTube.
InMemoryStore przestaje funkcjonować po zakończeniu procesu. Uruchom Postgres (zwykle przez Docker), zainstaluj pakietów do zarządzania punktami kontrolnymi i przechowywaniem danych w Postgresie, a następnie zastąp ten mechanizm implementacją opartą na połączeniach. Po pełnym restartowaniu zapytania do bazy danych powinny nadal zwracać zapisane informacje profilu.
services:
postgres:
image: postgres:16
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: postgres
ports:
- "5442:5432"
! pip install -U "psycopg[binary,pool]" langgraph langgraph-checkpoint-postgres
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.postgres import PostgresStore
from langgraph.store.base import BaseStore
# ----------------------------
# 2) System prompt
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible.
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Memory extraction LLM
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory")
is_new: bool = Field(description="True if new, false if duplicate")
class MemoryDecision(BaseModel):
should_write: bool
memories: List[MemoryItem] = Field(default_factory=list)
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return should_write=false and an empty list.
"""
# ----------------------------
# 3) Nodes
# ----------------------------
def remember_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
# existing memory (all items under namespace)
items = store.search(ns)
existing = "\n".join(it.value.get("data", "") for it in items) if items else "(empty)"
# latest user message
last_text = state["messages"][-1].content
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=existing)),
{"role": "user", "content": last_text},
]
)
if decision.should_write:
for mem in decision.memories:
if mem.is_new and mem.text.strip():
store.put(ns, str(uuid.uuid4()), {"data": mem.text.strip()})
return {}
chat_llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
items = store.search(ns)
user_details = "\n".join(it.value.get("data", "") for it in items) if items else ""
system_msg = SystemMessage(
content=SYSTEM_PROMPT_TEMPLATE.format(user_details_content=user_details or "(empty)")
)
response = chat_llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
# ----------------------------
# 4) Build graph
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_node)
builder.add_node("chat", chat_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", "chat")
builder.add_edge("chat", END)
<langgraph.graph.state.StateGraph at 0x110ce4a90>
# ----------------------------
# 5) Use PostgresStore (PERSISTENT LTM)
# ----------------------------
DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"
with PostgresStore.from_conn_string(DB_URI) as store:
# IMPORTANT: run ONCE the first time you use this database
store.setup()
graph = builder.compile(store=store)
config = {"configurable": {"user_id": "u1"}}
graph.invoke({"messages": [{"role": "user", "content": "Hi, my name is Nitish"}]}, config)
graph.invoke({"messages": [{"role": "user", "content": "I teach AI on YouTube"}]}, config)
out = graph.invoke({"messages": [{"role": "user", "content": "Explain GenAI simply"}]}, config)
print(out["messages"][-1].content)
print("\n--- Stored Memories (from Postgres) ---")
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:Sure, Nitish! Generative AI, or GenAI, refers to a type of artificial intelligence that can create new content, like images, text, music, or even code, on its own. It learns from a large dataset and uses patterns it recognizes to generate something that resembles what it has seen before.
# output:For example, if you input a topic or a few words into a generative AI model, it can produce a coherent piece of writing or generate a unique piece of art. Popular examples include models like GPT-3 for text and DALL-E for images.
# output:The key point is that GenAI is designed to take what it has learned and create new, original outputs based on that learning. If you’re discussing this concept in your YouTube teachings, it might be interesting for your audience to see how GenAI can assist in creative processes or even in automating certain tasks.
# output:Would you like to dive deeper into a specific application of GenAI, or perhaps explore its implications for teaching AI?
# output:--- Stored Memories (from Postgres) ---
# output:Nitish teaches AI on YouTube.
# output:User's name is Nitish.
Check Persistence
from langgraph.store.postgres import PostgresStore
DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"
with PostgresStore.from_conn_string(DB_URI) as store:
ns = ("user", "u1", "details")
items = store.search(ns)
for it in items:
print(it.value["data"])
# output: Nitish teaches AI on YouTube.
# output: User's name is Nitish.
Praktyczne pułapki przy łączeniu LTM
Przestrzenie nazw wydają się proste, dopóki dwa elementy nie dzielą się ("users", user_id) i nie nadpisują swoich kluczy. Lepiej używać par składających się z elementu specyficznego dla funkcji, takich jak ("users", user_id, "prefs") zamiast ("users", user_id, "facts"), oraz udokumentować, kto może edytować każdy z nich. Klucze powinny być stabilnymi identyfikatorami, a nie zdaniami tekstowymi; zdania należy umieszczać w wartościach.
Jakość wyszukiwania semantycznego zależy od wyboru metod embeddingu oraz sposobu sformułowania informacji. Przechowywanie frazy „lubię Python” a późniejsze wyszukiwanie „ulubiony język programowania” działa tylko wtedy, gdy przestrzeń embeddingu grupuje te frazy. Okresowe ponowne użycie metod embeddingu po aktualizacjach modelu to nużące zadania, które zapobiegają niezauważalnym regresjom w wynikach wyszukiwania.
Zapisy ścieżek wymagają ograniczeń szybkości. Ekstraktor, który uruchamia się przy każdej wypowiedzi użytkownika, może zalać Postgres niemal identycznymi danymi nawet po sprawdzeniach `is_new`, szczególnie gdy model wybiera ostrożniejsze rozwiązania. Ogranicz liczba zapisów na jeden ruch, grupuj podsumowania na koniec sesji i monitoruj wzrost ilości danych przechowywanych dla każdego użytkownika. W środowisku produkcyjnym łącz długoterminowe przechowywanie z krótkoterminowym punktem kontrolnym, aby dialog lokalny dla poszczególnych wątków oraz pamięć profilu międzywątkowa pozostały koncepcyjnie oddzielone, nawet jeśli korzystają z tej samej infrastruktury.
Higiena ścieżek odczytu
Pod względem odczytu, gdy personalizacja będzie działać w demonstracjach, nigdy nie umieszczaj całego przestrzeni nazw w komendzie systemowej. Ogranicz liczbę pobranych wspomnień, wskazuj klucze przestrzeni nazw, które przyczyniły się do tego, i umożliwiaj operatorowi wyłączenie LTM dla poszczególnych użytkowników, gdy przywoływanie informacji wydaje się błędne. Funkcja personalizacji, której nie można wyłączyć, staje się koszmarem dla działu wsparcia. Ponadto oddziel w przechowaniu „fakty profilowe” od „streszczeń rozmów”, aby błędna rotacja streszczeń nie mogła usunąć trwałych preferencji użytkownika. Przy migracji z InMemoryStore do Postgres ćwicz tworzenie kopii zapasowych i przywracanie tabel pamięci w taki sam sposób, jak ćwiczysz przywracanie punktów kontrolnych – utrata LTM to dla użytkownika widoczna amnezja, a nie zwykły problem infrastruktury.
Nauczanie wydobywacza, co oznacza „ważne”
Zapytania, które mówią „zapisz wszystko, co przydatne”, tworzą śmieci. Lepiej używać zamkniętej listy kontrolnej: tożsamość, trwałe preferencje, aktywne projekty, surowe ograniczenia oraz wyraźnie zadeklarowane przypomnienia. Wszystko inne pozostaje w wskaźniku stanu wątku. Pokaż ekstraktorowi kilka par dialogów z zakłóceniami w porównaniu z minimalnym plikiem JSON pamięci, jakiego chcesz, i uruchamiaj ponownie te przykłady w CI, gdy zmieniają się zapytania. Jakość długoterminowej pamięci jest produktem zapytania i schematu – traktuj ją jak taki.
Operatorzy powinni również ćwiczyć naprawę „błędnej pamięci”: usuwanie według klucza, ponowne wydobycie informacji z poprawionej wypowiedzi oraz potwierdzenie, że węzeł czatu nie odwołuje się już do przestarzałych faktów. Bez takich ćwiczeń długoterminowa pamięć staje się jedynie szufladą do zapisywania danych, bez możliwości edycji.
Literatura pokrewna
- Config, State, Store, Prompt: Inżynieria kontekstu w LangGraph — Oddzielna, niezmienialna konfiguracja w czasie wykonywania, zmienny stan roboczy, długoterminowe przechowywanie oraz przygotowane prompty, dzięki czemu agenci są tańsze, bezpieczniejsze i łatwiejsze do debugowania.
- HR Policy RAG w formacie produkcyjnym z LangChain i LangGraph — Proces pobierania danych, MMR, przepisywanie z uwzględnieniem historii, odpowiedzi oparte na faktach, zasady bezpieczeństwa, ocena, cytaty oraz orkiestracja grafu dla asystenta ds. polityk HR.