> ## 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.

# graphrag prompt-tune

> Generate custom prompts tuned to your domain and data

The `prompt-tune` command automatically generates domain-specific prompts by analyzing your input documents. This creates prompts that are better suited to your specific use case than the default generic prompts.

## Usage

```bash theme={null}
graphrag prompt-tune [OPTIONS]
```

## Options

<ParamField path="--root" type="string" default="current directory">
  The project root directory.

  **Aliases**: `-r`
</ParamField>

<ParamField path="--domain" type="string">
  The domain your input data is related to. For example: "space science", "microbiology", "environmental news", "legal documents".

  If not specified, the domain will be automatically inferred from the input data.
</ParamField>

<ParamField path="--output" type="string" default="prompts">
  The directory to save generated prompts to, relative to the project root directory.

  **Aliases**: `-o`
</ParamField>

<ParamField path="--selection-method" type="string" default="random">
  The text chunk selection method for prompt generation.

  Available methods:

  * `random` - Randomly select chunks (fastest)
  * `top` - Select top chunks by order
  * `auto` - Automatically select diverse chunks using embeddings (best quality)
</ParamField>

<ParamField path="--limit" type="integer" default="15">
  The number of documents to load when `--selection-method` is `random` or `top`.
</ParamField>

<ParamField path="--n-subset-max" type="integer" default="300">
  The number of text chunks to embed when `--selection-method=auto`. Higher values provide more diversity but take longer.
</ParamField>

<ParamField path="--k" type="integer" default="15">
  The maximum number of documents to select from each centroid when `--selection-method=auto`.
</ParamField>

<ParamField path="--max-tokens" type="integer" default="2000">
  The maximum token count for prompt generation examples.
</ParamField>

<ParamField path="--min-examples-required" type="integer" default="2">
  The minimum number of examples to generate/include in the entity extraction prompt.
</ParamField>

<ParamField path="--chunk-size" type="integer" default="1200">
  The size of each example text chunk in tokens. Overrides `chunking.size` in the configuration file.
</ParamField>

<ParamField path="--overlap" type="integer" default="100">
  The overlap size for chunking documents in tokens. Overrides `chunking.overlap` in the configuration file.
</ParamField>

<ParamField path="--language" type="string">
  The primary language used for inputs and outputs in GraphRAG prompts.

  Examples: "English", "Spanish", "French", "Japanese"

  If not specified, defaults to English.
</ParamField>

<ParamField path="--discover-entity-types" type="boolean" default="true">
  Discover and extract unspecified entity types from the data.

  Use `--no-discover-entity-types` to disable and only use predefined entity types.
</ParamField>

<ParamField path="--verbose" type="boolean" default="false">
  Run the prompt tuning pipeline with verbose logging.

  **Aliases**: `-v`
</ParamField>

## Examples

### Basic prompt tuning

Generate prompts with automatic domain inference:

```bash theme={null}
graphrag prompt-tune
```

### Specify domain

```bash theme={null}
graphrag prompt-tune --domain "medical research"
```

### Use auto selection for better quality

```bash theme={null}
graphrag prompt-tune --selection-method auto
```

The `auto` selection method uses embeddings to select diverse, representative samples from your documents.

### Customize output directory

```bash theme={null}
graphrag prompt-tune --output custom_prompts
```

### Multilingual prompt generation

```bash theme={null}
graphrag prompt-tune --language "Spanish" --domain "noticias políticas"
```

### Increase sample diversity

```bash theme={null}
graphrag prompt-tune \
  --selection-method auto \
  --n-subset-max 500 \
  --k 20
```

### Use predefined entity types only

```bash theme={null}
graphrag prompt-tune --no-discover-entity-types
```

### Custom chunking parameters

```bash theme={null}
graphrag prompt-tune \
  --chunk-size 800 \
  --overlap 200
```

### Verbose output

```bash theme={null}
graphrag prompt-tune --verbose
```

## Generated prompts

The prompt-tune command generates three customized prompt files:

### extract\_graph.txt

Prompt for extracting entities and relationships from text. This is customized with:

* Domain-specific entity types discovered from your data
* Example extractions from your actual documents
* Domain context and terminology

### summarize\_descriptions.txt

Prompt for summarizing entity descriptions. Customized with:

* Domain-specific summarization guidelines
* Examples from your data

### community\_report.txt

Prompt for generating community reports. Customized with:

* Domain-appropriate report structure
* Relevant analysis dimensions for your domain

## How it works

1. **Sample selection**: Selects representative text chunks from your documents using the specified selection method
2. **Domain analysis**: Analyzes the samples to understand domain characteristics and terminology
3. **Entity discovery**: Identifies domain-specific entity types present in your data
4. **Example generation**: Creates few-shot examples by extracting entities from sample chunks
5. **Prompt creation**: Generates prompts incorporating discovered entity types and examples

## Selection methods

### Random selection

* Fastest method
* Randomly samples chunks from documents
* Good for homogeneous datasets
* Use `--limit` to control sample size

### Top selection

* Selects first N chunks in order
* Fast and deterministic
* Good when early content is representative

### Auto selection (recommended)

* Uses embeddings to find diverse, representative samples
* Creates embeddings for up to `--n-subset-max` chunks
* Clusters chunks and selects up to `--k` from each cluster
* Best quality but slower due to embedding generation
* Recommended for heterogeneous datasets

## Best practices

1. **Use auto selection**: For best results, use `--selection-method auto` with adequate sample size
2. **Specify domain**: Providing a domain helps generate more focused prompts
3. **Diverse samples**: Ensure your input documents are representative of your full dataset
4. **Review outputs**: Always review generated prompts before using them for indexing
5. **Iterate**: Try different selection methods and parameters to find what works best

## Customizing generated prompts

After generation, you can manually edit the prompts in the output directory:

1. Review the generated entity types and examples
2. Add or remove entity types as needed
3. Adjust the prompt instructions for your specific needs
4. Test with a small index before running on full dataset

## Using tuned prompts

After generating prompts:

1. Review the prompts in the `prompts/` directory (or your custom output directory)
2. Copy them to your project's `prompts/` directory if using a custom output location
3. Run indexing - it will automatically use the new prompts:
   ```bash theme={null}
   graphrag index
   ```

## Performance considerations

* **Auto selection**: Slower due to embedding generation but produces better quality
* **Sample size**: Larger `--n-subset-max` values take longer but capture more diversity
* **Token limits**: Higher `--max-tokens` allows for more examples but increases API costs

## Error handling

Common issues:

* **No input documents**: Ensure documents exist in your `input/` directory
* **API errors**: Check that your API key is configured in `.env`
* **Insufficient samples**: Increase `--limit` or `--n-subset-max` if you get too few examples
* **Language mismatch**: Ensure `--language` matches your document language

## Next steps

* [Review and customize generated prompts](/examples/custom-prompts)
* [Run indexing with tuned prompts](/cli/index)
* [Understand entity types](/concepts/knowledge-graphs)
* [Configure prompt settings](/prompt-tuning/overview)