> ## 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.

# Suggest Similar • AI Agent SDK

> suggest_similar: Find the most similar string from candidates using Levenshtein distance.

# suggest\_similar

<div className="flex items-center gap-2">
  <Badge color="teal">Function</Badge>
</div>

> This function is defined in the [**parse\_utils**](../modules/parse_utils) module.

Find the most similar string from candidates using Levenshtein distance.

This function is ONLY called on error paths, never on happy paths.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def suggest_similar(value: str, candidates: Iterable[str], max_distance: int) -> Optional[str]
```

## Parameters

<ParamField query="value" type="str" required={true}>
  The invalid value
</ParamField>

<ParamField query="candidates" type="Iterable" required={true}>
  Valid options to compare against
</ParamField>

<ParamField query="max_distance" type="int" required={false} default="2">
  Maximum edit distance to consider a match
</ParamField>

### Returns

<ResponseField name="Returns" type="Optional[str]">
  Most similar candidate if within max\_distance, None otherwise
</ResponseField>

## Used By

* [`make_preset_error`](../functions/make_preset_error)

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/config/parse_utils.py#L142">
  `praisonaiagents/config/parse_utils.py` at line 142
</Card>