> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# From Directory • AI Agent SDK

> from_directory: Create CorpusStats from directory scan.

# from\_directory

<div className="flex items-center gap-2">
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**CorpusStats**](../classes/CorpusStats) class in the [**indexing**](../modules/indexing) module.

Create CorpusStats from directory scan.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def from_directory(path: str, extensions: Optional[List[str]]) -> 'CorpusStats'
```

## Parameters

<ParamField query="path" type="str" required={true}>
  Directory path to scan
</ParamField>

<ParamField query="extensions" type="Optional" required={false}>
  Optional list of extensions to include
</ParamField>

### Returns

<ResponseField name="Returns" type="'CorpusStats'">
  CorpusStats with file count and token estimate
</ResponseField>

## Uses

* `os.walk`
* `splitext`
* `getsize`
* `cls`
* `isoformat`
* `datetime.now`

## Used By

* [`Knowledge.index`](../functions/Knowledge-index)

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/knowledge/indexing.py#L71">
  `praisonaiagents/knowledge/indexing.py` at line 71
</Card>