> ## 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.

# Indexing overview

> Learn about the GraphRAG indexing pipeline and how it transforms unstructured text into a structured knowledge graph

The GraphRAG indexing package is a data pipeline and transformation suite that extracts meaningful, structured data from unstructured text using LLMs.

## What is indexing?

Indexing pipelines are configurable workflows composed of standard and custom steps, prompt templates, and input/output adapters. The standard pipeline is designed to:

* Extract entities, relationships and claims from raw text
* Perform community detection on entities
* Generate community summaries and reports at multiple levels of granularity
* Embed text into a vector space

The outputs of the pipeline are stored as Parquet tables by default, and embeddings are written to your configured vector store.

## Getting started

<Steps>
  <Step title="Install requirements">
    See the [requirements](/installation) section for details on setting up a development environment.
  </Step>

  <Step title="Configure GraphRAG">
    To configure GraphRAG, see the [configuration](/configuration/overview) documentation.
  </Step>

  <Step title="Run the indexing pipeline">
    After you have a config file, you can run the pipeline using the CLI or Python API.
  </Step>
</Steps>

## Usage

<CodeGroup>
  ```bash CLI theme={null}
  uv run poe index --root <data_root>
  ```

  ```python Python API theme={null}
  from graphrag.api.index import build_index
  from graphrag.config.models.graph_rag_config import GraphRagConfig

  # Load your configuration
  config = GraphRagConfig.from_yaml("settings.yaml")

  # Run the indexing pipeline
  results = await build_index(
      config=config,
      method="standard",  # or "fast"
      verbose=True
  )
  ```
</CodeGroup>

<Note>
  The Python API is available in `graphrag/api/index.py` and provides the recommended method to call the indexer directly from Python code.
</Note>

## Key features

<CardGroup cols={2}>
  <Card title="LLM caching" icon="database">
    Built-in cache layer around LLM interactions for resilience and efficiency
  </Card>

  <Card title="Flexible workflows" icon="diagram-project">
    Customizable pipeline with standard and custom workflow steps
  </Card>

  <Card title="Parquet outputs" icon="table">
    Structured data outputs in Parquet format for efficient storage and querying
  </Card>

  <Card title="Vector embeddings" icon="vector-square">
    Automatic text embedding to configured vector stores
  </Card>
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Architecture" icon="sitemap" href="/indexing/architecture">
    Understand the underlying concepts and execution model
  </Card>

  <Card title="Data flow" icon="arrow-right-arrow-left" href="/indexing/dataflow">
    Learn how data flows through the indexing pipeline
  </Card>

  <Card title="Methods" icon="flask" href="/indexing/methods">
    Compare Standard and FastGraphRAG indexing methods
  </Card>

  <Card title="Configuration" icon="gear" href="/configuration/overview">
    Configure the indexing engine for your use case
  </Card>
</CardGroup>