Knowledge Graphs for LLM Applications

What is a Knowledge Graph? A knowledge graph represents information as entities (nodes) and relationships (edges), enabling structured reasoning and fact storage.

Structure

[Entity: Eiffel Tower]
    |
    |-- Type: Landmark
    |-- Location: Paris
    |-- Height: 330m
    |-- Built: 1889
    |
    +-- (located_in) --> [Entity: France]
    |
    +-- (designed_by) --> [Entity: Gustave Eiffel]

Knowledge Graph + LLM Approaches

RAG with Knowledge Graph

def kg_rag(query: str) -> str:
    # Extract entities from query
    entities = extract_entities(query)

    # Query knowledge graph for related facts
    facts = []
    for entity in entities:
        facts.extend(kg.get_triplets(entity, hops=2))

    # Format as context
    context = format_triplets(facts)

    return llm.generate(f"""
Context from knowledge base:
{context}

Question: {query}
Answer:
    """)

Graph-Guided Retrieval Use KG structure to improve retrieval:

def graph_guided_retrieval(query: str) -> list:
    # Get relevant entities
    entities = kg.search_entities(query)

    # Expand via graph relations
    expanded = set()
    for entity in entities:
        expanded.add(entity)
        expanded.update(kg.get_neighbors(entity))

    # Retrieve documents for all entities
    docs = []
    for entity in expanded:
        docs.extend(doc_store.search(entity.name))

    return docs

Building Knowledge Graphs

From Text (LLM Extraction)

def extract_triplets(text: str) -> list:
    result = llm.generate(f"""
Extract entity relationships from this text as triplets:
(subject, relation, object)

Text: {text}

Triplets:
    """)
    return parse_triplets(result)

Schema Example

entities = ["Person", "Organization", "Location", "Product"]
relations = ["works_at", "located_in", "founded_by", "produces"]

Graph Databases

Use Cases

Knowledge graphs complement vector search by providing structured, explainable facts.