Graf memori

Graph RAG dengan LangChain dan Neo4j

Adam Cowley

Manager, Developer Education at Neo4j

Memori dalam aplikasi RAG

Memori jangka pendek

Singkat, dibatasi cakupan
Riwayat percakapan

Memori jangka panjang

Memori semantik: fakta tentang dunia
Berguna untuk hiper-personalisasi

Memori jangka pendek

Memori jangka pendek ke jangka panjang

Riwayat pesan chat Neo4j

from langchain_neo4j import Neo4jChatMessageHistory


history = Neo4jChatMessageHistory(

    url=NEO4J_URI,

    username=NEO4J_USERNAME,

    password=NEO4J_PASSWORD,

    session_id="session_id_1",

)


# Add a human message
history.add_user_message("hi!")


# Add an AI message
history.add_ai_message("what's up?")

Masalah menyimpan semuanya

Riwayat pesan chat Neo4j

from langchain_neo4j import Neo4jChatMessageHistory

history = Neo4jChatMessageHistory(
    url=NEO4J_URI,
    username=NEO4J_USERNAME,
    password=NEO4J_PASSWORD,
    session_id="session_id_1",

    window=10 # defaults to 3 messages

)


# Get history
print(history.messages)

[HumanMessage(content='hi!', ...), AIMessage(content='whats up?', ...)]

Meringkas percakapan

from pydantic import BaseModel, Field

class ConversationFact(BaseModel):
    """
    A class that holds the facts from a conversation in a format of object, subject, predicate.
    """

    object: str = Field(description="The object of the fact. For example, 'Adam' ")

    subject: str = Field(description="The subject of the fact. For example, 'Ice cream'")

    relationship: str = Field(description="The relationship between object and subject. Eg: 'LOVES'")


class ConversationFacts(BaseModel):
    """
    A class that holds a list of ConversationFact objects.
    """
    facts: list[ConversationFact] = Field(description="A list of ConversationFact objects.")

Meringkas percakapan

llm_with_output = (
    init_chat_model("gpt-4o-mini", model_provider="openai", api_key="...")
        .with_structured_output(ConversationFacts)
)

Meringkas percakapan

prompt = ChatPromptTemplate.from_messages(

    SystemMessagePromptTemplate.from_template("Extract the facts from the conversation."),

    MessagesPlaceholder(variable_name="history"),

)


chain = prompt | llm_with_output


chain.invoke({

    "history": history.messages,

})

ConversationFacts(facts=[
    ConversationFact(object='child', subject='Bluey', relationship='LOVES')
])

Ayo berlatih!

Graph RAG dengan LangChain dan Neo4j