> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/microsoft/graphrag/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration overview

> Learn how to configure GraphRAG for your indexing and query needs

The GraphRAG system is highly configurable, allowing you to customize everything from language models to storage mechanisms. This section provides a comprehensive guide to configuring GraphRAG for your specific use case.

## Configuration modes

GraphRAG supports a default configuration mode that is designed to work out-of-the-box with minimal setup. You can configure GraphRAG through:

<CardGroup cols={2}>
  <Card title="Init command" icon="terminal" href="/configuration/initialization">
    Get started quickly with the `graphrag init` command
  </Card>

  <Card title="Settings file" icon="file-code" href="/configuration/settings">
    Customize behavior through `settings.yaml` configuration
  </Card>
</CardGroup>

## Quick start

The simplest way to get started is by running the initialization command:

```bash theme={null}
graphrag init --root ./my-project
```

This creates:

* `settings.yaml` - Main configuration file
* `.env` - Environment variables for API keys
* `prompts/` - Default LLM prompts

## Configuration structure

GraphRAG configuration is organized into several key areas:

<AccordionGroup>
  <Accordion title="Language models">
    Configure completion and embedding models, including provider settings, authentication, retry logic, and rate limiting.

    [View LLM configuration details](/configuration/llm-models)
  </Accordion>

  <Accordion title="Input and processing">
    Set up document ingestion, text chunking, and preprocessing options for your data pipeline.

    Includes support for CSV, TXT, and JSON formats with configurable chunking strategies.
  </Accordion>

  <Accordion title="Storage and caching">
    Configure storage backends for inputs, outputs, and caching to optimize performance and cost.

    [View storage configuration details](/configuration/storage)
  </Accordion>

  <Accordion title="Graph extraction">
    Tune entity extraction, relationship detection, and graph construction parameters.

    Choose between LLM-based and NLP-based extraction methods.
  </Accordion>

  <Accordion title="Community detection">
    Configure hierarchical clustering and community report generation.

    Uses Leiden algorithm for graph partitioning with customizable parameters.
  </Accordion>

  <Accordion title="Query methods">
    Set up local, global, drift, and basic search with custom prompts and context limits.

    Each search method has dedicated configuration options.
  </Accordion>
</AccordionGroup>

## Environment variables

GraphRAG supports environment variable substitution in configuration files using `${VAR_NAME}` syntax:

```yaml theme={null}
completion_models:
  default_completion_model:
    api_key: ${GRAPHRAG_API_KEY}
```

```bash .env theme={null}
GRAPHRAG_API_KEY=your-api-key-here
```

<Note>
  Environment variables are automatically loaded from `.env` files in your project root.
</Note>

## Configuration defaults

GraphRAG includes sensible defaults for most settings. You only need to configure:

<Steps>
  <Step title="API credentials">
    Set your language model API keys and endpoints
  </Step>

  <Step title="Input location">
    Specify where your source documents are located
  </Step>

  <Step title="Optional customization">
    Tune advanced settings based on your requirements
  </Step>
</Steps>

For a complete list of default values, see the [defaults.py file](https://github.com/microsoft/graphrag/blob/main/graphrag/config/defaults.py) in the source code.

## Next steps

<CardGroup cols={2}>
  <Card title="Initialize your project" icon="rocket" href="/configuration/initialization">
    Run `graphrag init` to create your configuration
  </Card>

  <Card title="Configure LLM models" icon="brain" href="/configuration/llm-models">
    Set up your language models and embeddings
  </Card>

  <Card title="Settings reference" icon="book" href="/configuration/settings">
    Explore all available configuration options
  </Card>

  <Card title="Storage setup" icon="database" href="/configuration/storage">
    Configure input, output, and cache storage
  </Card>
</CardGroup>