Extracting a schema from text

Overview

The GraphRAG for Python package (neo4j-graphrag) allows you to access Neo4j Generative AI functions.

During this course you will use the neo4j_graphrag package to build a knowledge graph and retrievers to extract information from the graph using LLMs.

In this lesson you will review how a graph schema can be extracted from text using an LLM.

Using the SchemaFromTextExtractor

Open workshop-genai/extract_schema.py

python

extract_entities.py

import os
from dotenv import load_dotenv
load_dotenv()

from neo4j_graphrag.experimental.components.schema import SchemaFromTextExtractor
from neo4j_graphrag.llm import OpenAILLM
import asyncio

schema_extractor = SchemaFromTextExtractor(
    llm = OpenAILLM(
        model_name="gpt-5-nano",
    ),
    use_structured_output=True,
)

text = """
Neo4j is a graph database management system (GDBMS) developed by Neo4j Inc.
"""

# Extract the schema from the text
extracted_schema = asyncio.run(schema_extractor.run(text=text))

print(extracted_schema)

The code uses the SchemaFromTextExtractor class to extract a schema from a given text input.

The extractor:

Creates a prompt instructing the LLM to:
1. Identify entities and relationships in any given text
2. Format the output as JSON
Passes the prompt and text to the LLM for processing
Parses the JSON response to create a schema object

Output

Given the text, "Neo4j is a graph database management system (GDBMS) developed by Neo4j Inc.", a simplified version of the extracted schema would be:

text

Extracted Schema

node_types=(
    NodeType(label='GraphDatabase),
    NodeType(label='Company')
)
relationship_types=(
    RelationshipType(label='DEVELOPED_BY'),
)
patterns=(
    ('GraphDatabaseManagementSystem', 'DEVELOPED_BY', 'Company')
)

Execute

Run the program and observe the output. You will see a more detailed schema based on the text provided.

This schema can be used to store the data held within the text.

mermaid

Extracted Schema

graph LR
    A(("Neo4j<br/>(GraphDatabase)"))
    B(("Neo4j<br/>(Company)"))
    
    A -->|DEVELOPED_BY| B

Experiment

Experiment with different text inputs to see how the schema extraction varies based on the content provided, for example:

Python is a programming language created by Guido van Rossum.
The Eiffel Tower is a wrought-iron lattice tower on the Champ de Mars in Paris, France.
Large Language Models (LLMs) are a type of artificial intelligence model designed to generate human-like text.

When you have experimented with the schema extraction, you can continue.

Lesson Summary

In this lesson, you:

Learned how to extract a graph schema from unstructured text using an LLM.
Explored how different text inputs can lead to different schema extractions.

In the next lesson, you will create a knowledge graph construction pipeline using the SimpleKGPipeline class.

Neo4j and Generative AI Workshop

Generative AI

Knowledge Graph Construction

Retrieval

Agents