GraphRAG for Python

This package contains the official Neo4j GraphRAG features for Python.

The purpose of this package is to provide a first party package to developers, where Neo4j can guarantee long term commitment and maintenance as well as being fast to ship new features and high performing patterns and methods.

⚠️ This package is a renamed continuation of neo4j-genai. The package neo4j-genai is deprecated and will no longer be maintained. We encourage all users to migrate to this new package to continue receiving updates and support.

Neo4j versions supported:

  • Neo4j >=5.18.1

  • Neo4j Aura >=5.18.0

Python versions supported:

  • Python 3.12

  • Python 3.11

  • Python 3.10

  • Python 3.9

Topics

Usage

Installation

This package requires Python (>=3.9).

To install the latest stable version, use:

pip install neo4j-graphrag

Note

It is always recommended to install python packages for user space in a virtual environment.

Optional Dependencies

Extra dependencies can be installed with:

pip install "neo4j-graphrag[openai]"
# or
pip install "neo4j-graphrag[openai, experimental]"

List of extra dependencies:

  • LLM providers (at least one is required for RAG and KG Builder Pipeline):
    • ollama: LLMs from Ollama

    • openai: LLMs from OpenAI (including AzureOpenAI)

    • google: LLMs from Vertex AI

    • cohere: LLMs from Cohere

    • anthropic: LLMs from Anthropic

    • mistralai: LLMs from MistralAI

  • sentence-transformers : to use embeddings from the sentence-transformers Python package

  • Vector database (to use External Retrievers):
    • weaviate: store vectors in Weaviate

    • pinecone: store vectors in Pinecone

    • qdrant: store vectors in Qdrant

  • experimental: experimental features such as the Knowledge Graph creation pipelines.
    • Warning: this requires pygraphviz. Installation instructions can be found here.

Examples

Creating a vector index

When creating a vector index, make sure you match the number of dimensions in the index with the number of dimensions the embeddings have.

See the API documentation for more details.

from neo4j import GraphDatabase
from neo4j_graphrag.indexes import create_vector_index

URI = "neo4j://localhost:7687"
AUTH = ("neo4j", "password")

INDEX_NAME = "vector-index-name"

# Connect to Neo4j database
driver = GraphDatabase.driver(URI, auth=AUTH)

# Creating the index
create_vector_index(
    driver,
    INDEX_NAME,
    label="Document",
    embedding_property="vectorProperty",
    dimensions=1536,
    similarity_fn="euclidean",
)

Note

Assumed Neo4j is running

Populating the Neo4j Vector Index

Note that the below example is not the only way you can upsert data into your Neo4j database. For example, you could also leverage the Neo4j Python driver.

from neo4j import GraphDatabase
from neo4j_graphrag.indexes import upsert_vector

URI = "neo4j://localhost:7687"
AUTH = ("neo4j", "password")

# Connect to Neo4j database
driver = GraphDatabase.driver(URI, auth=AUTH)

# Upsert the vector
vector = ...
upsert_vector(
    driver,
    node_id=1,
    embedding_property="vectorProperty",
    vector=vector,
)

Note

Assumed Neo4j is running with a defined vector index

Limitations

The query over the vector index is an approximate nearest neighbor search and may not give exact results. See this reference for more details.

Development

Install dependencies

poetry install --all-extras

Getting started

Issues

If you have a bug to report or feature to request, first search to see if an issue already exists. If a related issue doesn’t exist, please raise a new issue using the relevant issue form.

If you’re a Neo4j Enterprise customer, you can also reach out to Customer Support.

If you don’t have a bug to report or feature request, but you need a hand with the library; community support is available via Neo4j Online Community and/or Discord.

Make changes

  1. Fork the repository.

  2. Install Python and Poetry.

  3. Create a working branch from main and start with your changes!

Pull request

When you’re finished with your changes, create a pull request, also known as a PR.

  • Ensure that you have signed the CLA.

  • Ensure that the base of your PR is set to main.

  • Don’t forget to link your PR to an issue if you are solving one.

  • Enable the checkbox to allow maintainer edits so that maintainers can make any necessary tweaks and update your branch for merge.

  • Reviewers may ask for changes to be made before a PR can be merged, either using suggested changes or normal pull request comments. You can apply suggested changes directly through the UI, and any other changes can be made in your fork and committed to the PR branch.

  • As you update your PR and apply changes, mark each conversation as resolved.

Run tests

Open a new virtual environment and then run the tests.

poetry shell
pytest

Unit tests

This should run out of the box once the dependencies are installed.

poetry run pytest tests/unit

E2E tests

To run e2e tests you’d need to have some services running locally:

  • neo4j

  • weaviate

  • weaviate-text2vec-transformers

The easiest way to get it up and running is via Docker compose:

docker compose -f tests/e2e/docker-compose.yml up

Note

If you suspect something in the databases are cached, run docker compose -f tests/e2e/docker-compose.yml down to remove them completely

Once the services are running, execute the following command to run the e2e tests.

poetry run pytest tests/e2e

Further information