skills.rest
eklyukin
eklyukinCOMMUNITY
Explore all skills by this author →
GitHub

neo4j-document-import-skill

Ingest unstructured documents into Neo4j as a knowledge graph with LLM entity extraction.

Updated Jul 24, 2026
Search Tags:#knowledge graph#llm#chunking#document ingestion#neo4j#entity extraction#graphrag
One-click install
npx skills add https://github.com/eklyukin/my-ai-config --skill neo4j-document-import-skill-eklyukin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: neo4j-document-import-skill
Source: https://github.com/eklyukin/my-ai-config/tree/main/skills/neo4j-document-import-skill
Command: npx skills add https://github.com/eklyukin/my-ai-config --skill neo4j-document-import-skill-eklyukin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires neo4j-graphrag, neo4j, and includes references (resource) components.

What problem does it solve? Turning PDFs, Markdown, HTML, and JSON into a queryable Neo4j knowledge graph requires coordinating chunking, LLM entity extraction, embeddings, and entity resolution, which is error-prone without a proven pipeline. ## Core Features & Use Cases - SimpleKGPipeline Setup: Configure neo4j-graphrag's SimpleKGPipeline with GraphSchema definitions, multiple LLM providers (OpenAI, Anthropic, Vertex AI, Ollama, Bedrock), and embedders to build Document→Chunk→Entity graph structures. - Chunking and Entity Resolution: Apply FixedSizeSplitter tuning guidance and run SinglePropertyExactMatchResolver, FuzzyMatchResolver, or SpaCySemanticMatchResolver to merge duplicate entities after ingestion. - Alternative Ingestion Paths: Use the no-code LLM Graph Builder web UI, apoc.load.json for semi-structured JSON, or LangChain/LlamaIndex document loaders connected to Neo4j. - Use Case: Ingest a folder of quarterly PDF reports into Neo4j, extract Person and Organization entities with GPT-4.1, resolve duplicates, and verify the resulting graph with Cypher queries. ## Quick Start Ask the agent to ingest a PDF file into Neo4j using SimpleKGPipeline with a defined entity schema and then verify the Document and Chunk node counts.

Frequently Asked Questions about neo4j-document-import-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I import PDF documents into Neo4j as a knowledge graph?▼

Use SimpleKGPipeline from the neo4j-graphrag Python package with from_file=True and a file_path pointing to the PDF. The pipeline chunks the document, extracts entities with your configured LLM, and creates Document, Chunk, and entity nodes automatically.

What is the difference between SimpleKGPipeline and LLM Graph Builder?▼

SimpleKGPipeline is a programmatic Python API in neo4j-graphrag for scripted ingestion pipelines. LLM Graph Builder is a no-code web UI for drag-and-drop ingestion, better suited for non-developers or rapid prototyping.

Which LLM providers does neo4j-graphrag support for entity extraction?▼

neo4j-graphrag supports OpenAI, Anthropic Claude, Vertex AI Gemini, Amazon Bedrock, Ollama for local models, and MistralAI. Each installs via an extras package such as neo4j-graphrag[openai] or neo4j-graphrag[anthropic].

Why does SimpleKGPipeline extract zero entities from my documents?▼

Zero entities usually means the chunk_size exceeds the LLM context window, causing extraction failure. Reduce chunk_size to 512 tokens or below for GPT-4o, and define an explicit GraphSchema with entity types and patterns.

How do I merge duplicate entities after Neo4j document ingestion?▼

Run an entity resolver after bulk ingestion completes. Use SinglePropertyExactMatchResolver for exact name matches, FuzzyMatchResolver for typos with a 0.9 threshold, or SpaCySemanticMatchResolver for semantic synonyms on Python 3.13 or earlier.

When should I not use this document import approach for Neo4j?▼

Do not use it for structured CSV or relational data, which belongs in a dedicated CSV import workflow. It also does not cover GraphRAG retrieval after ingestion or vector index search configuration, which are separate skills.

Related Skills

Explore More Software Engineering Skills→
reason-machinesreason-machines
5

terraform-data-engineering-iac

Provision AWS S3, EC2, and IAM resources for data pipelines using Terraform.

Official
Intermediate
sharpninjasharpninja

GraphRAG Knowledge Graph

Ingest raw text into a GraphRAG knowledge graph and run graph-aware queries.

Community
Advanced
neo4j-contribneo4j-contrib
101

neo4j-document-import-skill

Ingest PDFs and text into Neo4j knowledge graphs via SimpleKGPipeline.

Official
Advanced
acmelemeacmeleme

gh-auth-isolation

Detect GitHub identities and switch gh config contexts per operation.

Official
Advanced