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

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Embeddings

> Gets the embeddings for the input data `X`.

<Info>
  Looking for usage documentation? Check out [Embeddings](/capabilities/embeddings).
</Info>

<div className="python-reference-heading">
  <h2 id="get-embeddings">
    `TabPFNRegressor.get_embeddings`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/regressor.py#L2200" aria-label="View source for TabPFNRegressor.get_embeddings"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Gets the embeddings for the input data `X`.

```python theme={null}
TabPFNRegressor.get_embeddings(
    X: XType,
    data_source: Literal["train", "test"] = "test",
) -> np.ndarray
```

<Accordion title="Type aliases">
  ```python theme={null}
  XType = Any
  ```
</Accordion>

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="get-embeddings--x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type"><a href="https://github.com/PriorLabs/TabPFN/blob/c70b6ef0488858d32244c52222abfc0c5be207d6/src/tabpfn/constants.py#L25">X<wbr />Type</a></code> | Required | The input data. |
  | <span id="get-embeddings--data-source" /><code className="python-reference-parameter">data\_<wbr />source</code> | <code className="python-reference-type">Literal\["train", "test"]</code> | `"test"` | Select the transformer output to return. Use `"train"` to obtain embeddings from the training tokens and `"test"` for the test tokens. When `n_estimators > 1` the returned array has shape `(n_estimators, n_samples, embedding_dim)`. `"train"` is not available with `fit_mode="fit_with_cache"`; see `tabpfn.base.get_embeddings`. |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type"><a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a></code> | [`np.ndarray`](https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html)     The computed embeddings for each fitted estimator. |
</div>


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