> ## 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.

# Corpus Stats • AI Agent SDK

> CorpusStats: Statistics about an indexed corpus.

# CorpusStats

> Defined in the [**indexing**](https://praison.ai/docs/sdk/reference/praisonaiagents/modules/indexing.md) module.

AI Agent

Statistics about an indexed corpus.

Used for strategy selection and monitoring.

Attributes:
file\_count: Number of files in corpus
chunk\_count: Number of chunks created
total\_tokens: Estimated total tokens
indexed\_at: Timestamp of last indexing
path: Path to corpus root
strategy\_recommendation: Recommended retrieval strategy

## Properties

**file\_count** `int`

No description available.

**chunk\_count** `int`

No description available.

**total\_tokens** `int`

No description available.

**indexed\_at** `Optional[str]`

No description available.

**path** `Optional[str]`

No description available.

## Methods

> [card] [from\_directory()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/CorpusStats-from_directory.md)
>
> Create CorpusStats from directory scan.

> [card] [strategy\_recommendation()](https://praison.ai/docs/sdk/reference/praisonaiagents/functions/CorpusStats-strategy_recommendation.md)
>
> Recommend retrieval strategy based on corpus size.

> [accordion] Internal & Generic Methods
>
> * **from\_dict**: Create from dictionary.
> * **to\_dict**: Convert to dictionary.

## Source

> [card] [View on GitHub](https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/knowledge/indexing.py#L37)
>
> `praisonaiagents/knowledge/indexing.py` at line 37


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.