Menyimpan dan menanya dokumen

Retrieval Augmented Generation (RAG) dengan LangChain

Meri Nova

Machine Learning Engineer

Menginisialisasi basis data Neo4j

from langchain_community.graphs import Neo4jGraph

graph = Neo4jGraph(url="bolt://localhost:7687", username="neo4j", password="...")

import os

url = os.environ["NEO4J_URI"]
user = os.environ["NEO4J_USERNAME"]
password = os.environ["NEO4J_PASSWORD"]

graph = Neo4jGraph(url=url, username=user, password=password)

¹ https://neo4j.com/download/

Menyimpan dokumen grafik

from langchain_experimental.graph_transformers import LLMGraphTransformer

llm = ChatOpenAI(api_key="...", temperature=0, model="gpt-4o-mini")
llm_transformer = LLMGraphTransformer(llm=llm)

graph_documents = llm_transformer.convert_to_graph_documents(documents)

Menyimpan dokumen grafik

graph.add_graph_documents(
  graph_documents,

  include_source=True,

  baseEntityLabel=True

)

include_source=True: tautkan node ke dokumen sumber dengan edge MENTIONS
baseEntityLabel=True: tambahkan label __Entity__ ke setiap node

Dokumen grafik direpresentasikan sebagai node dan edge.

Versi diperbesar dari gambar sebelumnya yang menampilkan node tentang model OpenAI.

Skema basis data

print(graph.get_schema)

Node properties:
Concept {id: STRING}
Architecture {id: STRING}
Organization {id: STRING}
Event {id: STRING}
Paper {id: STRING}

The relationships:
(:Concept)-[:DEVELOPED_BY]->(:Person)
(:Architecture)-[:BASED_ON]->(:Concept)
(:Organization)-[:PROPOSED]->(:Concept)
(:Document)-[:MENTIONS]->(:Event)
(:Paper)-[:BASED_ON]->(:Concept)

Menanya Neo4j - Bahasa Kueri Cypher

Sebuah node bernama James dengan relasi bernama friends yang menunjuk ke node person misteri.

Menanya Neo4j - Bahasa Kueri Cypher

Menanya grafik LLM

results = graph.query("""
MATCH (gpt4:Model {id: "Gpt-4"})-[:DEVELOPED_BY]->(org:Organization)
RETURN org
""")


print(results)

[{'org': {'id': 'Openai'}}]

Ayo berlatih!

Retrieval Augmented Generation (RAG) dengan LangChain