# Prerequisites

To begin, you’ll need to set up and familiarize yourself with Memgraph, the foundation of your GraphRAG system.

## Getting started with Memgraph 

To begin your GraphRAG journey, you’ll need Memgraph MAGE set up and ready to go. If
you’re new to Memgraph, follow the [getting started guide](https://memgraph.com/docs/getting-started) for detailed
installation and setup instructions.

## Requirements for GraphRAG 

GraphRAG systems involve combining graph databases with LLMs. Here’s what you’ll
need to set up for success:

- A running Memgraph MAGE instance
- Knowledge graph stored in Memgraph - identify your structured or unstructured
  data to convert into a knowledge graph and follow Memgraph's [data
  modeling](https://memgraph.com/docs/data-modeling) docs to design your graph. 
- LLM API - use the large language model of your choice.

> **Note**
>
> Building a GraphRAG system involves multiple building blocks, and selecting the
> right ones isn’t straightforward.
>
> Before you begin, carefully consider what information the LLM needs that it
> wouldn’t have without the knowledge graph. Identify the key context to provide,
> and prioritize the most relevant data for inference.
>
> Remember, creating an ideal system rarely happens on the first try—iteration and
> evaluation are essential.

### Hardware requirements 

Since Memgraph is an in-memory graph database, the hardware requirements depend
on the size of your dataset and the complexity of your queries.

1. **Memory**: Sufficient RAM is essential for storing and processing your
   dataset in memory. To estimate your needs, refer to
   our [RAM calculation guide](https://memgraph.com/docs/help-center/faq#how-much-ram-do-i-need-for-my-graph).
2. **Storage**: While Memgraph operates in memory, storage is required for
   backups, snapshots, and write-ahead logs (WAL) to ensure data durability.
   Learn more about best practices in
   our [storage FAQ](https://memgraph.com/docs/help-center/faq#what-are-the-minimum-and-recommended-requirements-to-run-a-on-premise-instance).

## Next steps

Once your environment is ready:

1. Proceed
   to [Knowledge graph creation](https://memgraph.com/docs/ai-ecosystem/graph-rag/knowledge-graph-creation) to
   model and import your data into Memgraph.
2. Explore [GraphRAG Pipelines](https://memgraph.com/docs/ai-ecosystem/graph-rag/atomic-pipelines) to
   understand how to retrieve and manage knowledge effectively.
3. Review [Examples and demos](https://memgraph.com/docs/ai-ecosystem/graph-rag/examples-and-demos) for
   inspiration on building your own GraphRAG system.