Neo4j Document Import Skill

pip install neo4j-graphrag              # includes SimpleKGPipeline
pip install neo4j-graphrag[openai]      # + OpenAI LLM/embedder
pip install neo4j-graphrag[anthropic]   # + Anthropic Claude
pip install neo4j-graphrag[google]      # + Vertex AI / Gemini
# spaCy entity resolver (Python <= 3.13 only — unsupported on 3.14+):
pip install neo4j-graphrag[nlp]

# Option A — Simple string lists (LLM infers descriptions)
entities = ["Person", "Organization", "Location", "Product", "Event"]
relations = ["WORKS_AT", "LOCATED_IN", "KNOWS", "MENTIONS", "PART_OF"]
patterns = [
    ("Person", "WORKS_AT", "Organization"),
    ("Organization", "LOCATED_IN", "Location"),
    ("Person", "KNOWS", "Person"),
    ("Article", "MENTIONS", "Organization"),
]

# Option B — Rich schema (better extraction quality)
from neo4j_graphrag.experimental.components.schema import (
    SchemaBuilder, SchemaEntity, SchemaRelation
)
schema = SchemaBuilder().create_schema_from_dict({
    "entities": {
        "Person": {"description": "A human individual", "properties": {"name": "str", "role": "str"}},
        "Organization": {"description": "A company or institution", "properties": {"name": "str", "industry": "str"}},
    },
    "relations": {
        "WORKS_AT": {"description": "Employment relationship"},
    },
    "patterns": [("Person", "WORKS_AT", "Organization")],
})

# Option C — Auto-extract schema from text (no constraints)
schema = "EXTRACTED"   # LLM infers types; noisier output
schema = "FREE"        # No schema guidance; most noise

import asyncio
from neo4j import GraphDatabase
from neo4j_graphrag.experimental.pipeline.kg_builder import SimpleKGPipeline
from neo4j_graphrag.llm import OpenAILLM
from neo4j_graphrag.embeddings import OpenAIEmbeddings

driver = GraphDatabase.driver(
    "neo4j+s://xxxx.databases.neo4j.io",
    auth=("neo4j", "password")
)

llm = OpenAILLM(
    model_name="gpt-4o",
    model_params={"temperature": 0, "response_format": {"type": "json_object"}},
)
embedder = OpenAIEmbeddings()   # OPENAI_API_KEY from env

pipeline = SimpleKGPipeline(
    llm=llm,
    driver=driver,
    embedder=embedder,
    entities=entities,          # from Step 1
    relations=relations,
    patterns=patterns,
    from_file=True,             # False → pass text= instead of file_path=
    on_error="IGNORE",          # RAISE to surface extraction failures
    perform_entity_resolution=True,
    neo4j_database="neo4j",     # omit to use default
)

# From PDF or Markdown file:
result = asyncio.run(pipeline.run_async(
    file_path="report.pdf",
    document_metadata={"source": "Q4 report", "year": 2025},
))

# From raw text:
result = asyncio.run(pipeline.run_async(
    text=document_text,
))

# Batch — process multiple files:
async def ingest_all(paths):
    for p in paths:
        await pipeline.run_async(file_path=str(p))

asyncio.run(ingest_all(list(pdf_dir.glob("*.pdf"))))

from neo4j_graphrag.experimental.components.text_splitters.fixed_size_splitter import FixedSizeSplitter

splitter = FixedSizeSplitter(
    chunk_size=512,       # tokens; 300–512 typical for GPT-4o
    chunk_overlap=50,     # ~10% of chunk_size; preserves boundary context
    approximate=True,     # respect sentence/word boundaries when possible
)

pipeline = SimpleKGPipeline(
    ...,
    text_splitter=splitter,
)

from neo4j_graphrag.experimental.components.resolver import (
    SinglePropertyExactMatchResolver,   # identical name → merge
    FuzzyMatchResolver,                  # Levenshtein similarity; needs rapidfuzz
    SpaCySemanticMatchResolver,          # cosine similarity; needs neo4j-graphrag[nlp]
)

# Exact match (fastest; good baseline)
resolver = SinglePropertyExactMatchResolver(driver)
asyncio.run(resolver.run())

# Fuzzy match (handles typos / alternate spellings)
from neo4j_graphrag.experimental.components.resolver import FuzzyMatchResolver
resolver = FuzzyMatchResolver(driver, threshold=0.9)
asyncio.run(resolver.run())

# Scope resolution to specific labels only:
resolver = SinglePropertyExactMatchResolver(
    driver,
    filter_query="WHERE n:Organization OR n:Person",
)
asyncio.run(resolver.run())

(:Document {id, fileName, status, ...metadata})
    -[:HAS_CHUNK]->
(:Chunk {id, text, index, embedding, ...})
    -[:NEXT_CHUNK]->          ← linked list for ordered traversal
(:Chunk {...})

(:Chunk)-[:FROM_DOCUMENT]->(:Document)   ← back-pointer

(:Chunk)-[:MENTIONS]->(:Person {name, ...})
(:Chunk)-[:MENTIONS]->(:Organization {name, ...})
(:Person)-[:WORKS_AT]->(:Organization)

CYPHER 25
MATCH (d:Document)-[:HAS_CHUNK]->(c:Chunk)
RETURN d.fileName, count(c) AS chunks LIMIT 10;

MATCH (c:Chunk)-[:MENTIONS]->(e)
RETURN labels(e)[0] AS type, count(*) AS cnt ORDER BY cnt DESC LIMIT 20;

git clone https://github.com/neo4j-labs/llm-graph-builder
cd llm-graph-builder
# Set OPENAI_API_KEY (or other provider keys) in .env
docker-compose up
# Opens at http://localhost:8080

CYPHER 25
CALL apoc.load.json("https://example.com/articles.json") YIELD value
UNWIND value.articles AS article
CALL (article) {
  MERGE (d:Document {id: article.id})
  SET d.title = article.title, d.url = article.url, d.publishedAt = article.publishedAt
  FOREACH (tag IN article.tags |
    MERGE (t:Tag {name: tag})
    MERGE (d)-[:HAS_TAG]->(t)
  )
} IN TRANSACTIONS OF 1000 ROWS

from langchain_community.graphs import Neo4jGraph
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings
from neo4j import GraphDatabase

graph = Neo4jGraph(
    url="neo4j+s://xxxx.databases.neo4j.io",
    username="neo4j",
    password="password",
)

loader = PyPDFLoader("report.pdf")
docs = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=64)
chunks = splitter.split_documents(docs)

embedder = OpenAIEmbeddings()
driver = GraphDatabase.driver(url, auth=("neo4j", "password"))

for i, chunk in enumerate(chunks):
    emb = embedder.embed_query(chunk.page_content)
    driver.execute_query(
        """
        MERGE (doc:Document {id: $doc_id})
        SET doc.source = $source
        CREATE (c:Chunk {id: $chunk_id, text: $text, embedding: $emb, index: $idx})
        CREATE (doc)-[:HAS_CHUNK]->(c)
        """,
        doc_id=chunk.metadata.get("source", "unknown"),
        source=chunk.metadata.get("source"),
        chunk_id=f"chunk-{i}",
        text=chunk.page_content,
        emb=emb,
        idx=i,
    )

CYPHER 25
// Prevent duplicate documents
CREATE CONSTRAINT doc_id_unique IF NOT EXISTS
  FOR (d:Document) REQUIRE d.id IS UNIQUE;

// Prevent duplicate chunks
CREATE CONSTRAINT chunk_id_unique IF NOT EXISTS
  FOR (c:Chunk) REQUIRE c.id IS UNIQUE;

// Entity deduplication
CREATE CONSTRAINT person_name_unique IF NOT EXISTS
  FOR (p:Person) REQUIRE p.name IS UNIQUE;
CREATE CONSTRAINT org_name_unique IF NOT EXISTS
  FOR (o:Organization) REQUIRE o.name IS UNIQUE;

// Vector index for chunk embeddings (adjust dims for your model)
CREATE VECTOR INDEX chunk_embeddings IF NOT EXISTS
  FOR (c:Chunk) ON c.embedding
  OPTIONS {indexConfig: {`vector.dimensions`: 1536, `vector.similarity_function`: 'cosine'}};

// Poll until index ONLINE:
// SHOW INDEXES YIELD name, state WHERE state <> 'ONLINE'

SHOW INDEXES YIELD name, state WHERE state <> 'ONLINE';

from neo4j_graphrag.experimental.components.schema import (
    GraphSchema, NodeType, RelationshipType, PropertyType
)
schema = GraphSchema(
    node_types=[
        NodeType(label="Person", properties=[PropertyType(name="name", type="STRING")]),
        NodeType(label="Organization", properties=[PropertyType(name="name", type="STRING")]),
    ],
    relationship_types=[RelationshipType(label="WORKS_AT")],
    patterns=[("Person", "WORKS_AT", "Organization")],
)
pipeline = SimpleKGPipeline(llm=llm, driver=driver, embedder=embedder, schema=schema)

from neo4j_graphrag.experimental.components.types import LexicalGraphConfig
# All fields have sensible defaults — only override what differs from your graph's conventions
config = LexicalGraphConfig(
    document_node_label="Article",             # default: "Document"
    chunk_node_label="Passage",                # default: "Chunk"
    node_to_chunk_relationship_type="HAS_ENTITY",  # default: "MENTIONS"
    chunk_text_property="content",             # default: "text"
)
pipeline = SimpleKGPipeline(..., lexical_graph_config=config)

from neo4j_graphrag.experimental.components.data_loader import DataLoader
from neo4j_graphrag.experimental.components.types import DocumentInfo, LoadedDocument

class WebPageLoader(DataLoader):
    async def run(self, filepath, metadata=None):
        import httpx
        text = httpx.get(filepath).text   # strip HTML in real impl
        return LoadedDocument(text=text,
            document_info=DocumentInfo(path=filepath, metadata=metadata))

pipeline = SimpleKGPipeline(..., file_loader=WebPageLoader(), from_file=True)