> ## 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.

# Initialization

> Initialize GraphRAG projects with the init command

The `graphrag init` command is the easiest way to get started with GraphRAG. It creates a complete project structure with configuration files, environment variables, and default prompts.

## Usage

```bash theme={null}
graphrag init [--root PATH] [--force, --no-force]
```

### Options

<ParamField path="--root" type="string" default="current directory">
  The project root directory to initialize GraphRAG at
</ParamField>

<ParamField path="--force" type="boolean" default="false">
  Overwrite existing configuration and prompt files if they exist
</ParamField>

## Example

Initialize a new GraphRAG project in a specific directory:

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

This creates a complete project structure:

```
ragtest/
├── settings.yaml      # Main configuration file
├── .env              # Environment variables
└── prompts/          # LLM prompt templates
    ├── extract_graph.txt
    ├── summarize_descriptions.txt
    ├── community_report_graph.txt
    └── ...
```

## Generated files

### settings.yaml

The main configuration file containing all GraphRAG settings:

```yaml settings.yaml theme={null}
### LLM settings ###
completion_models:
  default_completion_model:
    model_provider: openai
    model: gpt-4.1
    auth_method: api_key
    api_key: ${GRAPHRAG_API_KEY}
    retry:
      type: exponential_backoff

embedding_models:
  default_embedding_model:
    model_provider: openai
    model: text-embedding-3-large
    auth_method: api_key
    api_key: ${GRAPHRAG_API_KEY}
    retry:
      type: exponential_backoff

### Document processing settings ###
input:
  type: text  # [csv, text, json, jsonl]

chunking:
  type: tokens
  size: 1200
  overlap: 100
  encoding_model: o200k_base

### Storage settings ###
input_storage:
  type: file  # [file, blob, cosmosdb]
  base_dir: "input"

output_storage:
  type: file  # [file, blob, cosmosdb]
  base_dir: "output"

cache:
  type: json  # [json, memory, none]
  storage:
    type: file  # [file, blob, cosmosdb]
    base_dir: "cache"

vector_store:
  type: lancedb
  db_uri: output/lancedb

### Workflow settings ###
extract_graph:
  completion_model_id: default_completion_model
  prompt: "prompts/extract_graph.txt"
  entity_types: [organization, person, geo, event]
  max_gleanings: 1
```

<Tip>
  See the [settings reference](/configuration/settings) for complete documentation of all available options.
</Tip>

### .env

Environment variables file for storing sensitive credentials:

```bash .env theme={null}
GRAPHRAG_API_KEY=<API_KEY>
```

<Warning>
  Never commit your `.env` file to version control. Add it to `.gitignore` to keep your API keys secure.
</Warning>

### prompts/

The prompts directory contains default LLM prompt templates that you can customize:

<CardGroup cols={2}>
  <Card title="extract_graph.txt" icon="diagram-project">
    Prompt for extracting entities and relationships from text
  </Card>

  <Card title="summarize_descriptions.txt" icon="compress">
    Prompt for summarizing entity descriptions
  </Card>

  <Card title="community_report_graph.txt" icon="users">
    Prompt for generating graph-based community reports
  </Card>

  <Card title="community_report_text.txt" icon="file-lines">
    Prompt for generating text-based community reports
  </Card>
</CardGroup>

Additional prompt files include:

* `extract_claims.txt` - Claim extraction (disabled by default)
* `local_search_system_prompt.txt` - Local search queries
* `global_search_map_system_prompt.txt` - Global search mapping
* `global_search_reduce_system_prompt.txt` - Global search reduction
* `drift_search_system_prompt.txt` - DRIFT search queries
* `basic_search_system_prompt.txt` - Basic search queries

## Customizing prompts

You can modify the generated prompts to better suit your domain:

<Steps>
  <Step title="Edit prompt files">
    Open and modify the prompt files in the `prompts/` directory
  </Step>

  <Step title="Test with your data">
    Run indexing to see how the modified prompts perform
  </Step>

  <Step title="Iterate and refine">
    Adjust prompts based on extraction quality and results
  </Step>
</Steps>

<Info>
  For data-adapted prompts, run the [Auto Prompt Tuning](/prompt-tuning/overview) command after initialization.
</Info>

## Using the --force flag

By default, `init` will not overwrite existing files. Use `--force` to regenerate:

```bash theme={null}
graphrag init --root ./ragtest --force
```

<Warning>
  The `--force` flag will overwrite:

  * `settings.yaml`
  * `.env` (your API keys will be lost)
  * All files in `prompts/`

  Back up any customizations before using `--force`.
</Warning>

## Next steps

After initialization, you're ready to:

<CardGroup cols={2}>
  <Card title="Configure API keys" icon="key">
    Edit `.env` to add your language model API credentials
  </Card>

  <Card title="Add source documents" icon="folder">
    Place your documents in the `input/` directory
  </Card>

  <Card title="Tune prompts" icon="wand-magic-sparkles" href="/prompt-tuning/overview">
    Run auto prompt tuning to adapt prompts to your data
  </Card>

  <Card title="Start indexing" icon="play" href="/indexing/overview">
    Run `graphrag index` to process your documents
  </Card>
</CardGroup>