> ## 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.

# embedding • AI Agents Framework

> embedding: Get embedding vector for text.

# embedding

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

> This function is defined in the [**llm**](../modules/llm) module.

Get embedding vector for text.

.. deprecated::
Use `from praisonai import embed` or `from praisonai.capabilities import embed` instead.
This function returns raw vectors; the new embed() returns EmbeddingResult with metadata.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def embedding(text: Any, model: Any) -> Any
```

## Parameters

<ParamField query="text" type="Any" required={true}>
  Text string or list of strings to embed
</ParamField>

<ParamField query="model" type="Any" required={false} default="'text-embedding-3-small'">
  Embedding model name (default: text-embedding-3-small) \*\*kwargs: Additional arguments passed to litellm.embedding()
</ParamField>

### Returns

<ResponseField name="Returns" type="Any">
  List\[float] for single text, or List\[List\[float]] for multiple texts
</ResponseField>

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai.llm import embedding

    # Single text
    emb = embedding("Hello world")

    # Multiple texts
    embs = embedding(["Hello", "World"])

    # Different model
    emb = embedding("Hello", model="text-embedding-3-large")
```

## Uses

* `warnings.warn`
* `ImportError`
* `litellm.embedding`

## Notes

Requires litellm. Install with: pip install praisonai\[llm]

## Used By

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

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai/praisonai/llm/__init__.py#L70">
  `praisonai/llm/__init__.py` at line 70
</Card>