# Mixins & serialization methods

## Mixins & serialization methods

### Mixins

The `huggingface_hub` library offers a range of mixins that can be used as a parent class for your objects, in order to provide simple uploading and downloading functions. Check out our [integration guide](https://huggingface.co/docs/huggingface_hub/guides/integrations) to learn how to integrate any ML framework with the Hub.

#### Generic

#### class huggingface\_hub.ModelHubMixin

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L23)

( )

A generic mixin to integrate ANY machine learning framework with the Hub.

To integrate your framework, your model class must inherit from this class. Custom logic for saving/loading models have to be overwritten in `_from_pretrained` and `_save_pretrained`. [PyTorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) is a good example of mixin integration with the Hub. Check out our [integration guide](https://huggingface.co/docs/huggingface_hub/guides/integrations) for more instructions.

**\_save\_pretrained**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L76)

( save\_directory: Path )

Parameters

* **save\_directory** (`str` or `Path`) — Path to directory in which the model weights and configuration will be saved.

Overwrite this method in subclass to define how to save your model. Check out our [integration guide](https://huggingface.co/docs/huggingface_hub/guides/integrations) for instructions.

**\_from\_pretrained**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L171)

( model\_id: strrevision: typing.Optional\[str]cache\_dir: typing.Union\[str, pathlib.Path, NoneType]force\_download: boolproxies: typing.Optional\[typing.Dict]resume\_download: boollocal\_files\_only: booltoken: typing.Union\[str, bool, NoneType]\*\*model\_kwargs )

Parameters

* **model\_id** (`str`) — ID of the model to load from the Huggingface Hub (e.g. `bigscience/bloom`).
* **revision** (`str`, *optional*) — Revision of the model on the Hub. Can be a branch name, a git tag or any commit id. Defaults to the latest commit on `main` branch.
* **force\_download** (`bool`, *optional*, defaults to `False`) — Whether to force (re-)downloading the model weights and configuration files from the Hub, overriding the existing cache.
* **resume\_download** (`bool`, *optional*, defaults to `False`) — Whether to delete incompletely received files. Will attempt to resume the download if such a file exists.
* **proxies** (`Dict[str, str]`, *optional*) — A dictionary of proxy servers to use by protocol or endpoint (e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`).
* **token** (`str` or `bool`, *optional*) — The token to use as HTTP bearer authorization for remote files. By default, it will use the token cached when running `huggingface-cli login`.
* **cache\_dir** (`str`, `Path`, *optional*) — Path to the folder where cached files are stored.
* **local\_files\_only** (`bool`, *optional*, defaults to `False`) — If `True`, avoid downloading the file and return the path to the local cached file if it exists. model\_kwargs — Additional keyword arguments passed along to the [\_from\_pretrained()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/mixins#huggingface_hub.ModelHubMixin._from_pretrained) method.

Overwrite this method in subclass to define how to load your model from pretrained.

Use [hf\_hub\_download()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/file_download#huggingface_hub.hf_hub_download) or [snapshot\_download()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/file_download#huggingface_hub.snapshot_download) to download files from the Hub before loading them. Most args taken as input can be directly passed to those 2 methods. If needed, you can add more arguments to this method using “model\_kwargs”. For example `PyTorchModelHubMixin._from_pretrained()` takes as input a `map_location` parameter to set on which device the model should be loaded.

Check out our [integration guide](https://huggingface.co/docs/huggingface_hub/guides/integrations) for more instructions.

**from\_pretrained**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L87)

( pretrained\_model\_name\_or\_path: typing.Union\[str, pathlib.Path]force\_download: bool = Falseresume\_download: bool = Falseproxies: typing.Optional\[typing.Dict] = Nonetoken: typing.Union\[str, bool, NoneType] = Nonecache\_dir: typing.Union\[str, pathlib.Path, NoneType] = Nonelocal\_files\_only: bool = Falserevision: typing.Optional\[str] = None\*\*model\_kwargs )

Parameters

* **pretrained\_model\_name\_or\_path** (`str`, `Path`) —
  * Either the `model_id` (string) of a model hosted on the Hub, e.g. `bigscience/bloom`.
  * Or a path to a `directory` containing model weights saved using [save\_pretrained](https://huggingface.co/docs/transformers/v4.34.0/en/main_classes/model#transformers.PreTrainedModel.save_pretrained), e.g., `../path/to/my_model_directory/`.
* **revision** (`str`, *optional*) — Revision of the model on the Hub. Can be a branch name, a git tag or any commit id. Defaults to the latest commit on `main` branch.
* **force\_download** (`bool`, *optional*, defaults to `False`) — Whether to force (re-)downloading the model weights and configuration files from the Hub, overriding the existing cache.
* **resume\_download** (`bool`, *optional*, defaults to `False`) — Whether to delete incompletely received files. Will attempt to resume the download if such a file exists.
* **proxies** (`Dict[str, str]`, *optional*) — A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`. The proxies are used on every request.
* **token** (`str` or `bool`, *optional*) — The token to use as HTTP bearer authorization for remote files. By default, it will use the token cached when running `huggingface-cli login`.
* **cache\_dir** (`str`, `Path`, *optional*) — Path to the folder where cached files are stored.
* **local\_files\_only** (`bool`, *optional*, defaults to `False`) — If `True`, avoid downloading the file and return the path to the local cached file if it exists.
* **model\_kwargs** (`Dict`, *optional*) — Additional kwargs to pass to the model during initialization.

Download a model from the Huggingface Hub and instantiate it.

**push\_to\_hub**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L220)

( repo\_id: strconfig: typing.Optional\[dict] = Nonecommit\_message: str = 'Push model using huggingface\_hub.'private: bool = Falseapi\_endpoint: typing.Optional\[str] = Nonetoken: typing.Optional\[str] = Nonebranch: typing.Optional\[str] = Nonecreate\_pr: typing.Optional\[bool] = Noneallow\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Noneignore\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Nonedelete\_patterns: typing.Union\[typing.List\[str], str, NoneType] = None )

Parameters

* **repo\_id** (`str`) — ID of the repository to push to (example: `"username/my-model"`).
* **config** (`dict`, *optional*) — Configuration object to be saved alongside the model weights.
* **commit\_message** (`str`, *optional*) — Message to commit while pushing.
* **private** (`bool`, *optional*, defaults to `False`) — Whether the repository created should be private.
* **api\_endpoint** (`str`, *optional*) — The API endpoint to use when pushing the model to the hub.
* **token** (`str`, *optional*) — The token to use as HTTP bearer authorization for remote files. By default, it will use the token cached when running `huggingface-cli login`.
* **branch** (`str`, *optional*) — The git branch on which to push the model. This defaults to `"main"`.
* **create\_pr** (`boolean`, *optional*) — Whether or not to create a Pull Request from `branch` with that commit. Defaults to `False`.
* **allow\_patterns** (`List[str]` or `str`, *optional*) — If provided, only files matching at least one pattern are pushed.
* **ignore\_patterns** (`List[str]` or `str`, *optional*) — If provided, files matching any of the patterns are not pushed.
* **delete\_patterns** (`List[str]` or `str`, *optional*) — If provided, remote files matching any of the patterns will be deleted from the repo.

Upload model checkpoint to the Hub.

Use `allow_patterns` and `ignore_patterns` to precisely filter which files should be pushed to the hub. Use `delete_patterns` to delete existing remote files in the same commit. See [upload\_folder()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/hf_api#huggingface_hub.HfApi.upload_folder) reference for more details.

**save\_pretrained**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L32)

( save\_directory: typing.Union\[str, pathlib.Path]config: typing.Optional\[dict] = Nonerepo\_id: typing.Optional\[str] = Nonepush\_to\_hub: bool = False\*\*kwargs )

Parameters

* **save\_directory** (`str` or `Path`) — Path to directory in which the model weights and configuration will be saved.
* **config** (`dict`, *optional*) — Model configuration specified as a key/value dictionary.
* **push\_to\_hub** (`bool`, *optional*, defaults to `False`) — Whether or not to push your model to the Huggingface Hub after saving it.
* **repo\_id** (`str`, *optional*) — ID of your repository on the Hub. Used only if `push_to_hub=True`. Will default to the folder name if not provided. kwargs — Additional key word arguments passed along to the [\_from\_pretrained()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/mixins#huggingface_hub.ModelHubMixin._from_pretrained) method.

Save weights in local directory.

#### PyTorch

#### class huggingface\_hub.PyTorchModelHubMixin

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/hub_mixin.py#L292)

( )

Implementation of [ModelHubMixin](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/mixins#huggingface_hub.ModelHubMixin) to provide model Hub upload/download capabilities to PyTorch models. The model is set in evaluation mode by default using `model.eval()` (dropout modules are deactivated). To train the model, you should first set it back in training mode with `model.train()`.

Example:

Copied

```
>>> import torch
>>> import torch.nn as nn
>>> from huggingface_hub import PyTorchModelHubMixin


>>> class MyModel(nn.Module, PyTorchModelHubMixin):
...     def __init__(self):
...         super().__init__()
...         self.param = nn.Parameter(torch.rand(3, 4))
...         self.linear = nn.Linear(4, 5)

...     def forward(self, x):
...         return self.linear(x + self.param)
>>> model = MyModel()

# Save model weights to local directory
>>> model.save_pretrained("my-awesome-model")

# Push model weights to the Hub
>>> model.push_to_hub("my-awesome-model")

# Download and initialize weights from the Hub
>>> model = MyModel.from_pretrained("username/my-awesome-model")
```

#### Keras

#### class huggingface\_hub.KerasModelHubMixin

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/keras_mixin.py#L398)

( )

Implementation of [ModelHubMixin](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/mixins#huggingface_hub.ModelHubMixin) to provide model Hub upload/download capabilities to Keras models.

Copied

```
>>> import tensorflow as tf
>>> from huggingface_hub import KerasModelHubMixin


>>> class MyModel(tf.keras.Model, KerasModelHubMixin):
...     def __init__(self, **kwargs):
...         super().__init__()
...         self.config = kwargs.pop("config", None)
...         self.dummy_inputs = ...
...         self.layer = ...

...     def call(self, *args):
...         return ...


>>> # Initialize and compile the model as you normally would
>>> model = MyModel()
>>> model.compile(...)
>>> # Build the graph by training it or passing dummy inputs
>>> _ = model(model.dummy_inputs)
>>> # Save model weights to local directory
>>> model.save_pretrained("my-awesome-model")
>>> # Push model weights to the Hub
>>> model.push_to_hub("my-awesome-model")
>>> # Download and initialize weights from the Hub
>>> model = MyModel.from_pretrained("username/super-cool-model")
```

**huggingface\_hub.from\_pretrained\_keras**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/keras_mixin.py#L217)

( \*args\*\*kwargs )

Parameters

* **pretrained\_model\_name\_or\_path** (`str` or `os.PathLike`) — Can be either:
  * A string, the `model id` of a pretrained model hosted inside a model repo on huggingface.co. Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a user or organization name, like `dbmdz/bert-base-german-cased`.
  * You can add `revision` by appending `@` at the end of model\_id simply like this: `dbmdz/bert-base-german-cased@main` Revision is the specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git.
  * A path to a `directory` containing model weights saved using [save\_pretrained](https://huggingface.co/docs/transformers/v4.34.0/en/main_classes/model#transformers.PreTrainedModel.save_pretrained), e.g., `./my_model_directory/`.
  * `None` if you are both providing the configuration and state dictionary (resp. with keyword arguments `config` and `state_dict`).
* **force\_download** (`bool`, *optional*, defaults to `False`) — Whether to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist.
* **resume\_download** (`bool`, *optional*, defaults to `False`) — Whether to delete incompletely received files. Will attempt to resume the download if such a file exists.
* **proxies** (`Dict[str, str]`, *optional*) — A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
* **token** (`str` or `bool`, *optional*) — The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated when running `transformers-cli login` (stored in `~/.huggingface`).
* **cache\_dir** (`Union[str, os.PathLike]`, *optional*) — Path to a directory in which a downloaded pretrained model configuration should be cached if the standard cache should not be used.
* **local\_files\_only(`bool`,** *optional*, defaults to `False`) — Whether to only look at local files (i.e., do not try to download the model).
* **model\_kwargs** (`Dict`, *optional*) — model\_kwargs will be passed to the model during initialization

Instantiate a pretrained Keras model from a pre-trained model from the Hub. The model is expected to be in `SavedModel` format.

Passing `token=True` is required when you want to use a private model.

**huggingface\_hub.push\_to\_hub\_keras**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/keras_mixin.py#L276)

( modelrepo\_id: strconfig: typing.Optional\[dict] = Nonecommit\_message: str = 'Push Keras model using huggingface\_hub.'private: bool = Falseapi\_endpoint: typing.Optional\[str] = Nonetoken: typing.Optional\[str] = Nonebranch: typing.Optional\[str] = Nonecreate\_pr: typing.Optional\[bool] = Noneallow\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Noneignore\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Nonedelete\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Nonelog\_dir: typing.Optional\[str] = Noneinclude\_optimizer: bool = Falsetags: typing.Union\[list, str, NoneType] = Noneplot\_model: bool = True\*\*model\_save\_kwargs )

Parameters

* **model** (`Keras.Model`) — The [Keras model](https://huggingface.co/docs/huggingface_hub/package_reference/%60https://www.tensorflow.org/api_docs/python/tf/keras/Model%60) you’d like to push to the Hub. The model must be compiled and built.
* **repo\_id** (`str`) — ID of the repository to push to (example: `"username/my-model"`).
* **commit\_message** (`str`, *optional*, defaults to “Add Keras model”) — Message to commit while pushing.
* **private** (`bool`, *optional*, defaults to `False`) — Whether the repository created should be private.
* **api\_endpoint** (`str`, *optional*) — The API endpoint to use when pushing the model to the hub.
* **token** (`str`, *optional*) — The token to use as HTTP bearer authorization for remote files. If not set, will use the token set when logging in with `huggingface-cli login` (stored in `~/.huggingface`).
* **branch** (`str`, *optional*) — The git branch on which to push the model. This defaults to the default branch as specified in your repository, which defaults to `"main"`.
* **create\_pr** (`boolean`, *optional*) — Whether or not to create a Pull Request from `branch` with that commit. Defaults to `False`.
* **config** (`dict`, *optional*) — Configuration object to be saved alongside the model weights.
* **allow\_patterns** (`List[str]` or `str`, *optional*) — If provided, only files matching at least one pattern are pushed.
* **ignore\_patterns** (`List[str]` or `str`, *optional*) — If provided, files matching any of the patterns are not pushed.
* **delete\_patterns** (`List[str]` or `str`, *optional*) — If provided, remote files matching any of the patterns will be deleted from the repo.
* **log\_dir** (`str`, *optional*) — TensorBoard logging directory to be pushed. The Hub automatically hosts and displays a TensorBoard instance if log files are included in the repository.
* **include\_optimizer** (`bool`, *optional*, defaults to `False`) — Whether or not to include optimizer during serialization.
* **tags** (Union\[`list`, `str`], *optional*) — List of tags that are related to model or string of a single tag. See example tags [here](https://github.com/huggingface/hub-docs/blame/main/modelcard.md).
* **plot\_model** (`bool`, *optional*, defaults to `True`) — Setting this to `True` will plot the model and put it in the model card. Requires graphviz and pydot to be installed.
* **model\_save\_kwargs(`dict`,** *optional*) — model\_save\_kwargs will be passed to [`tf.keras.models.save_model()`](https://www.tensorflow.org/api_docs/python/tf/keras/models/save_model).

Upload model checkpoint to the Hub.

Use `allow_patterns` and `ignore_patterns` to precisely filter which files should be pushed to the hub. Use `delete_patterns` to delete existing remote files in the same commit. See [upload\_folder()](https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/en/package_reference/hf_api#huggingface_hub.HfApi.upload_folder) reference for more details.

**huggingface\_hub.save\_pretrained\_keras**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/keras_mixin.py#L132)

( modelsave\_directory: typing.Union\[str, pathlib.Path]config: typing.Union\[typing.Dict\[str, typing.Any], NoneType] = Noneinclude\_optimizer: bool = Falseplot\_model: bool = Truetags: typing.Union\[list, str, NoneType] = None\*\*model\_save\_kwargs )

Parameters

* **model** (`Keras.Model`) — The [Keras model](https://www.tensorflow.org/api_docs/python/tf/keras/Model) you’d like to save. The model must be compiled and built.
* **save\_directory** (`str` or `Path`) — Specify directory in which you want to save the Keras model.
* **config** (`dict`, *optional*) — Configuration object to be saved alongside the model weights.
* **include\_optimizer(`bool`,** *optional*, defaults to `False`) — Whether or not to include optimizer in serialization.
* **plot\_model** (`bool`, *optional*, defaults to `True`) — Setting this to `True` will plot the model and put it in the model card. Requires graphviz and pydot to be installed.
* **tags** (Union\[`str`,`list`], *optional*) — List of tags that are related to model or string of a single tag. See example tags [here](https://github.com/huggingface/hub-docs/blame/main/modelcard.md).
* **model\_save\_kwargs(`dict`,** *optional*) — model\_save\_kwargs will be passed to [`tf.keras.models.save_model()`](https://www.tensorflow.org/api_docs/python/tf/keras/models/save_model).

Saves a Keras model to save\_directory in SavedModel format. Use this if you’re using the Functional or Sequential APIs.

#### Fastai

**huggingface\_hub.from\_pretrained\_fastai**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/fastai_utils.py#L298)

( repo\_id: strrevision: typing.Optional\[str] = None )

Parameters

* **repo\_id** (`str`) — The location where the pickled fastai.Learner is. It can be either of the two:
  * Hosted on the Hugging Face Hub. E.g.: ‘espejelomar/fatai-pet-breeds-classification’ or ‘distilgpt2’. You can add a `revision` by appending `@` at the end of `repo_id`. E.g.: `dbmdz/bert-base-german-cased@main`. Revision is the specific model version to use. Since we use a git-based system for storing models and other artifacts on the Hugging Face Hub, it can be a branch name, a tag name, or a commit id.
  * Hosted locally. `repo_id` would be a directory containing the pickle and a pyproject.toml indicating the fastai and fastcore versions used to build the `fastai.Learner`. E.g.: `./my_model_directory/`.
* **revision** (`str`, *optional*) — Revision at which the repo’s files are downloaded. See documentation of `snapshot_download`.

Load pretrained fastai model from the Hub or from a local directory.

**huggingface\_hub.push\_to\_hub\_fastai**

[\<source>](https://github.com/huggingface/huggingface_hub/blob/v0.18.0.rc0/src/huggingface_hub/fastai_utils.py#L343)

( learnerrepo\_id: strcommit\_message: str = 'Push FastAI model using huggingface\_hub.'private: bool = Falsetoken: typing.Optional\[str] = Noneconfig: typing.Optional\[dict] = Nonebranch: typing.Optional\[str] = Nonecreate\_pr: typing.Optional\[bool] = Noneallow\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Noneignore\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Nonedelete\_patterns: typing.Union\[typing.List\[str], str, NoneType] = Noneapi\_endpoint: typing.Optional\[str] = None )

Parameters

* **learner** (*Learner*) — The \*fastai.Learner’ you’d like to push to the Hub.
* **repo\_id** (*str*) — The repository id for your model in Hub in the format of “namespace/repo\_name”. The namespace can be your individual account or an organization to which you have write access (for example, ‘stanfordnlp/stanza-de’).
* **commit\_message** (*str\`,* optional\*) — Message to commit while pushing. Will default to `"add model"`.
* **private** (*bool*, *optional*, defaults to *False*) — Whether or not the repository created should be private.
* **token** (*str*, *optional*) — The Hugging Face account token to use as HTTP bearer authorization for remote files. If `None`, the token will be asked by a prompt.
* **config** (*dict*, *optional*) — Configuration object to be saved alongside the model weights.
* **branch** (*str*, *optional*) — The git branch on which to push the model. This defaults to the default branch as specified in your repository, which defaults to *“main”*.
* **create\_pr** (*boolean*, *optional*) — Whether or not to create a Pull Request from *branch* with that commit. Defaults to *False*.
* **api\_endpoint** (*str*, *optional*) — The API endpoint to use when pushing the model to the hub.
* **allow\_patterns** (*List\[str]* or *str*, *optional*) — If provided, only files matching at least one pattern are pushed.
* **ignore\_patterns** (*List\[str]* or *str*, *optional*) — If provided, files matching any of the patterns are not pushed.
* **delete\_patterns** (*List\[str]* or *str*, *optional*) — If provided, remote files matching any of the patterns will be deleted from the repo.

Upload learner checkpoint files to the Hub.

Use *allow\_patterns* and *ignore\_patterns* to precisely filter which files should be pushed to the hub. Use *delete\_patterns* to delete existing remote files in the same commit. See \[*upload\_folder*] reference for more details.

Raises the following error:

* [*ValueError*](https://docs.python.org/3/library/exceptions.html#ValueError) if the user is not log on to the Hugging Face Hub.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/hub-python-library/reference/mixins-and-serialization-methods.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.