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

# all-mpnet-base-v2

> Compute L2-normalized sentence embeddings for a batch of short strings

Compute L2-normalized sentence embeddings for a batch of short strings.

## Parameters

<ParamField body="text" type="List[str]" required>
  List of 1..128 UTF-8 strings — short object descriptions.
</ParamField>

<ParamField body="timeout" type="float | None">
  Optional timeout in seconds for the HTTP request.
</ParamField>

## Returns

Dict\[str, Any]: Dict with `features` of shape `(len(text), 768)`, `float32` and
L2-normalized per row (cosine similarity == dot product);
`model_revision` of the backing checkpoint; and `normalized=True`.

## Example

```python theme={null}
from grid_cortex_client import CortexClient, ModelType
client = CortexClient()
out = client.run(
    ModelType.ALL_MPNET_BASE_V2,
    text=["red cup on table", "red mug on table", "blue bowl"],
)
sims = out["features"] @ out["features"].T
sims[0, 1] > sims[0, 2]   # cup/mug > cup/bowl
```


## Related topics

- [owlv2](/models/cortex/owlv2.md)
- [Galaxea R1 Pro Mobile Manipulator](/python-api/r1pro/galaxear1pro.md)
- [GRIDType](/python-api/grid-types/gridtype.md)
- [Robot](/python-api/robot-interface/robot.md)
- [EndEffector](/python-api/robot-interface/endeffector.md)


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