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

# Load datasets

> How to load Adaptive datasets in your recipes

You can import datasets previously [uploaded to Adaptive](/v0.13/core/datasets) directly within your recipes.
Datasets stored on Adaptive can be loaded by specifying a parameter of type `Dataset` from `adaptive_harmony.parameters` in your recipe's `InputConfig` [class](/v0.13/harmony/config).

You can then load it in your recipe as a list of [`StringThread`](/v0.13/harmony/string-thread) objects by calling `await dataset.load(ctx)`.

## Load a dataset

First, define your dataset in your recipe's input config:

```python theme={null}
from adaptive_harmony.runtime import InputConfig
from adaptive_harmony.parameters import Dataset

class MyConfig(InputConfig):
    dataset: Dataset
```

To load a dataset from Adaptive, you can use the `load` method on the dataset:

```python theme={null}
async def my_recipe(config: MyConfig, ctx: RecipeContext):
    dataset = await config.dataset.load(ctx)
```

If your dataset contains completions (assistant responses), `with_weight_last_assistant_turn()` is applied automatically: only the final assistant turn contributes to the training loss. See [Turn weights](/v0.13/harmony/string-thread#turn-weights) for more details and how to override this behavior.

<Info>
  This utility can also load local files structured in the Adaptive-supported [format](/v0.13/core/datasets), which you can leverage if you are testing a recipe [locally](/v0.13/harmony/harmony-client). Load a local dataset with `Dataset(dataset_key="local-file", local_file_path="your_file.jsonl")`.
</Info>

## Loading from Hugging Face

You can also load datasets directly from Hugging Face in your recipe. `adaptive_harmony` exposes helper methods to convert arbitrary datasets into a list of `StringThread` objects by allowing you to specify the column in the original dataset that contains chat messages.

```python theme={null}
from adaptive_harmony.core.dataset import load_from_hf, convert_sample_dict

def load_hf_dataset():
    # Helper function to convert HF dataset to Adaptive StringThread
    convert_sample_fn = convert_sample_dict(
        turns_key="messages",
        role_key="role",
        content_key="content"
    )

    # Load the dataset
    dataset = load_from_hf(
        "HuggingFaceH4/ultrachat_200k",
        "train_sft",
        convert_sample_fn
    )

    return dataset
```