huggingface-hub 0.29.3__py3-none-any.whl → 0.30.0__py3-none-any.whl

huggingface_hub/hub_mixin.py

@@ -58,7 +58,8 @@ DEFAULT_MODEL_CARD = """
 ---
 
 This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: {{ repo_url | default("[More Information Needed]", true) }}
+- Code: {{ repo_url | default("[More Information Needed]", true) }}
+- Paper: {{ paper_url | default("[More Information Needed]", true) }}
 - Docs: {{ docs_url | default("[More Information Needed]", true) }}
 """
 
@@ -67,8 +68,9 @@ This model has been pushed to the Hub using the [PytorchModelHubMixin](https://h
 class MixinInfo:
     model_card_template: str
     model_card_data: ModelCardData
-    repo_url: Optional[str] = None
     docs_url: Optional[str] = None
+    paper_url: Optional[str] = None
+    repo_url: Optional[str] = None
 
 
 class ModelHubMixin:
@@ -88,6 +90,8 @@ class ModelHubMixin:
     Args:
         repo_url (`str`, *optional*):
             URL of the library repository. Used to generate model card.
+        paper_url (`str`, *optional*):
+            URL of the library paper. Used to generate model card.
         docs_url (`str`, *optional*):
             URL of the library documentation. Used to generate model card.
         model_card_template (`str`, *optional*):
@@ -110,7 +114,7 @@ class ModelHubMixin:
         pipeline_tag (`str`, *optional*):
             Tag of the pipeline. Used to generate model card. E.g. "text-classification".
         tags (`List[str]`, *optional*):
-            Tags to be added to the model card. Used to generate model card. E.g. ["x-custom-tag", "arxiv:2304.12244"]
+            Tags to be added to the model card. Used to generate model card. E.g. ["computer-vision"]
         coders (`Dict[Type, Tuple[Callable, Callable]]`, *optional*):
             Dictionary of custom types and their encoders/decoders. Used to encode/decode arguments that are not
             jsonable by default. E.g dataclasses, argparse.Namespace, OmegaConf, etc.
@@ -124,8 +128,9 @@ class ModelHubMixin:
     >>> class MyCustomModel(
     ...         ModelHubMixin,
     ...         library_name="my-library",
-    ...         tags=["x-custom-tag", "arxiv:2304.12244"],
+    ...         tags=["computer-vision"],
     ...         repo_url="https://github.com/huggingface/my-cool-library",
+    ...         paper_url="https://arxiv.org/abs/2304.12244",
     ...         docs_url="https://huggingface.co/docs/my-cool-library",
     ...         # ^ optional metadata to generate model card
     ...     ):
@@ -194,6 +199,7 @@ class ModelHubMixin:
         *,
         # Generic info for model card
         repo_url: Optional[str] = None,
+        paper_url: Optional[str] = None,
         docs_url: Optional[str] = None,
         # Model card template
         model_card_template: str = DEFAULT_MODEL_CARD,
@@ -234,6 +240,7 @@ class ModelHubMixin:
 
             # Inherit other info
             info.docs_url = cls._hub_mixin_info.docs_url
+            info.paper_url = cls._hub_mixin_info.paper_url
             info.repo_url = cls._hub_mixin_info.repo_url
         cls._hub_mixin_info = info
 
@@ -242,6 +249,8 @@ class ModelHubMixin:
             info.model_card_template = model_card_template
         if repo_url is not None:
             info.repo_url = repo_url
+        if paper_url is not None:
+            info.paper_url = paper_url
         if docs_url is not None:
             info.docs_url = docs_url
         if language is not None:
@@ -334,6 +343,8 @@ class ModelHubMixin:
     @classmethod
     def _is_jsonable(cls, value: Any) -> bool:
         """Check if a value is JSON serializable."""
+        if is_dataclass(value):
+            return True
         if isinstance(value, cls._hub_mixin_jsonable_custom_types):
             return True
         return is_jsonable(value)
@@ -341,6 +352,8 @@ class ModelHubMixin:
     @classmethod
     def _encode_arg(cls, arg: Any) -> Any:
         """Encode an argument into a JSON serializable format."""
+        if is_dataclass(arg):
+            return asdict(arg)
         for type_, (encoder, _) in cls._hub_mixin_coders.items():
             if isinstance(arg, type_):
                 if arg is None:
@@ -692,6 +705,7 @@ class ModelHubMixin:
             card_data=self._hub_mixin_info.model_card_data,
             template_str=self._hub_mixin_info.model_card_template,
             repo_url=self._hub_mixin_info.repo_url,
+            paper_url=self._hub_mixin_info.paper_url,
             docs_url=self._hub_mixin_info.docs_url,
             **kwargs,
         )
@@ -718,6 +732,7 @@ class PyTorchModelHubMixin(ModelHubMixin):
     ...         PyTorchModelHubMixin,
     ...         library_name="keras-nlp",
     ...         repo_url="https://github.com/keras-team/keras-nlp",
+    ...         paper_url="https://arxiv.org/abs/2304.12244",
     ...         docs_url="https://keras.io/keras_nlp/",
     ...         # ^ optional metadata to generate model card
     ...     ):

huggingface_hub/inference/_client.py

@@ -102,7 +102,8 @@ from huggingface_hub.inference._generated.types import (
 )
 from huggingface_hub.inference._providers import PROVIDER_T, HFInferenceTask, get_provider_helper
 from huggingface_hub.utils import build_hf_headers, get_session, hf_raise_for_status
-from huggingface_hub.utils._deprecation import _deprecate_arguments, _deprecate_method
+from huggingface_hub.utils._auth import get_token
+from huggingface_hub.utils._deprecation import _deprecate_method
 
 
 if TYPE_CHECKING:
@@ -132,12 +133,11 @@ class InferenceClient:
             path will be appended to the base URL (see the [TGI Messages API](https://huggingface.co/docs/text-generation-inference/en/messages_api)
             documentation for details). When passing a URL as `model`, the client will not append any suffix path to it.
         provider (`str`, *optional*):
-            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"fireworks-ai"`, `"hf-inference"`, `"hyperbolic"`, `"nebius"`, `"novita"`, `"replicate"`, "sambanova"` or `"together"`.
+            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"fireworks-ai"`, `"hf-inference"`, `"hyperbolic"`, `"nebius"`, `"novita"`, `"openai"`, `"replicate"`, "sambanova"` or `"together"`.
             defaults to hf-inference (Hugging Face Serverless Inference API).
             If model is a URL or `base_url` is passed, then `provider` is not used.
-        token (`str` or `bool`, *optional*):
+        token (`str`, *optional*):
             Hugging Face token. Will default to the locally saved token if not provided.
-            Pass `token=False` if you don't want to send your token to the server.
             Note: for better compatibility with OpenAI's client, `token` has been aliased as `api_key`. Those 2
             arguments are mutually exclusive and have the exact same behavior.
         timeout (`float`, `optional`):
@@ -146,6 +146,9 @@ class InferenceClient:
         headers (`Dict[str, str]`, `optional`):
             Additional headers to send to the server. By default only the authorization and user-agent headers are sent.
             Values in this dictionary will override the default values.
+        bill_to (`str`, `optional`):
+            The billing account to use for the requests. By default the requests are billed on the user's account.
+            Requests can only be billed to an organization the user is a member of, and which has subscribed to Enterprise Hub.
         cookies (`Dict[str, str]`, `optional`):
             Additional cookies to send to the server.
         proxies (`Any`, `optional`):
@@ -168,6 +171,7 @@ class InferenceClient:
         headers: Optional[Dict[str, str]] = None,
         cookies: Optional[Dict[str, str]] = None,
         proxies: Optional[Any] = None,
+        bill_to: Optional[str] = None,
         # OpenAI compatibility
         base_url: Optional[str] = None,
         api_key: Optional[str] = None,
@@ -185,10 +189,43 @@ class InferenceClient:
                 " `api_key` is an alias for `token` to make the API compatible with OpenAI's client."
                 " It has the exact same behavior as `token`."
             )
+        token = token if token is not None else api_key
+        if isinstance(token, bool):
+            # Legacy behavior: previously is was possible to pass `token=False` to disable authentication. This is not
+            # supported anymore as authentication is required. Better to explicitly raise here rather than risking
+            # sending the locally saved token without the user knowing about it.
+            if token is False:
+                raise ValueError(
+                    "Cannot use `token=False` to disable authentication as authentication is required to run Inference."
+                )
+            warnings.warn(
+                "Using `token=True` to automatically use the locally saved token is deprecated and will be removed in a future release. "
+                "Please use `token=None` instead (default).",
+                DeprecationWarning,
+            )
+            token = get_token()
 
         self.model: Optional[str] = base_url or model
-        self.token: Optional[str] = token if token is not None else api_key
-        self.headers = headers if headers is not None else {}
+        self.token: Optional[str] = token
+
+        self.headers = {**headers} if headers is not None else {}
+        if bill_to is not None:
+            if (
+                constants.HUGGINGFACE_HEADER_X_BILL_TO in self.headers
+                and self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO] != bill_to
+            ):
+                warnings.warn(
+                    f"Overriding existing '{self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO]}' value in headers with '{bill_to}'.",
+                    UserWarning,
+                )
+            self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO] = bill_to
+
+            if token is not None and not token.startswith("hf_"):
+                warnings.warn(
+                    "You've provided an external provider's API key, so requests will be billed directly by the provider. "
+                    "The `bill_to` parameter is only applicable for Hugging Face billing and will be ignored.",
+                    UserWarning,
+                )
 
         # Configure provider
         self.provider = provider if provider is not None else "hf-inference"
@@ -300,33 +337,32 @@ class InferenceClient:
         if request_parameters.task in TASKS_EXPECTING_IMAGES and "Accept" not in request_parameters.headers:
             request_parameters.headers["Accept"] = "image/png"
 
-        while True:
-            with _open_as_binary(request_parameters.data) as data_as_binary:
-                try:
-                    response = get_session().post(
-                        request_parameters.url,
-                        json=request_parameters.json,
-                        data=data_as_binary,
-                        headers=request_parameters.headers,
-                        cookies=self.cookies,
-                        timeout=self.timeout,
-                        stream=stream,
-                        proxies=self.proxies,
-                    )
-                except TimeoutError as error:
-                    # Convert any `TimeoutError` to a `InferenceTimeoutError`
-                    raise InferenceTimeoutError(f"Inference call timed out: {request_parameters.url}") from error  # type: ignore
-
+        with _open_as_binary(request_parameters.data) as data_as_binary:
             try:
-                hf_raise_for_status(response)
-                return response.iter_lines() if stream else response.content
-            except HTTPError as error:
-                if error.response.status_code == 422 and request_parameters.task != "unknown":
-                    msg = str(error.args[0])
-                    if len(error.response.text) > 0:
-                        msg += f"\n{error.response.text}\n"
-                    error.args = (msg,) + error.args[1:]
-                raise
+                response = get_session().post(
+                    request_parameters.url,
+                    json=request_parameters.json,
+                    data=data_as_binary,
+                    headers=request_parameters.headers,
+                    cookies=self.cookies,
+                    timeout=self.timeout,
+                    stream=stream,
+                    proxies=self.proxies,
+                )
+            except TimeoutError as error:
+                # Convert any `TimeoutError` to a `InferenceTimeoutError`
+                raise InferenceTimeoutError(f"Inference call timed out: {request_parameters.url}") from error  # type: ignore
+
+        try:
+            hf_raise_for_status(response)
+            return response.iter_lines() if stream else response.content
+        except HTTPError as error:
+            if error.response.status_code == 422 and request_parameters.task != "unknown":
+                msg = str(error.args[0])
+                if len(error.response.text) > 0:
+                    msg += f"\n{error.response.text}\n"
+                error.args = (msg,) + error.args[1:]
+            raise
 
     def audio_classification(
         self,
@@ -910,7 +946,7 @@ class InferenceClient:
         ...     messages=messages,
         ...     response_format=response_format,
         ...     max_tokens=500,
-        )
+        ... )
         >>> response.choices[0].message.content
         '{\n\n"activity": "bike ride",\n"animals": ["puppy", "cat", "raccoon"],\n"animals_seen": 3,\n"location": "park"}'
         ```
@@ -1272,7 +1308,7 @@ class InferenceClient:
         [ImageSegmentationOutputElement(score=0.989008, label='LABEL_184', mask=<PIL.PngImagePlugin.PngImageFile image mode=L size=400x300 at 0x7FDD2B129CC0>), ...]
         ```
         """
-        provider_helper = get_provider_helper(self.provider, task="audio-classification")
+        provider_helper = get_provider_helper(self.provider, task="image-segmentation")
         request_parameters = provider_helper.prepare_request(
             inputs=image,
             parameters={
@@ -2602,7 +2638,7 @@ class InferenceClient:
             api_key=self.token,
         )
         response = self._inner_post(request_parameters)
-        response = provider_helper.get_response(response)
+        response = provider_helper.get_response(response, request_parameters)
         return response
 
     def text_to_speech(
@@ -3033,22 +3069,14 @@ class InferenceClient:
         response = self._inner_post(request_parameters)
         return VisualQuestionAnsweringOutputElement.parse_obj_as_list(response)
 
-    @_deprecate_arguments(
-        version="0.30.0",
-        deprecated_args=["labels"],
-        custom_message="`labels`has been renamed to `candidate_labels` and will be removed in huggingface_hub>=0.30.0.",
-    )
     def zero_shot_classification(
         self,
         text: str,
-        # temporarily keeping it optional for backward compatibility.
-        candidate_labels: List[str] = None,  # type: ignore
+        candidate_labels: List[str],
         *,
         multi_label: Optional[bool] = False,
         hypothesis_template: Optional[str] = None,
         model: Optional[str] = None,
-        # deprecated argument
-        labels: List[str] = None,  # type: ignore
     ) -> List[ZeroShotClassificationOutputElement]:
         """
         Provide as input a text and a set of candidate labels to classify the input text.
@@ -3127,16 +3155,6 @@ class InferenceClient:
         ]
         ```
         """
-        # handle deprecation
-        if labels is not None:
-            if candidate_labels is not None:
-                raise ValueError(
-                    "Cannot specify both `labels` and `candidate_labels`. Use `candidate_labels` instead."
-                )
-            candidate_labels = labels
-        elif candidate_labels is None:
-            raise ValueError("Must specify `candidate_labels`")
-
         provider_helper = get_provider_helper(self.provider, task="zero-shot-classification")
         request_parameters = provider_helper.prepare_request(
             inputs=text,
@@ -3156,16 +3174,10 @@ class InferenceClient:
             for label, score in zip(output["labels"], output["scores"])
         ]
 
-    @_deprecate_arguments(
-        version="0.30.0",
-        deprecated_args=["labels"],
-        custom_message="`labels`has been renamed to `candidate_labels` and will be removed in huggingface_hub>=0.30.0.",
-    )
     def zero_shot_image_classification(
         self,
         image: ContentT,
-        # temporarily keeping it optional for backward compatibility.
-        candidate_labels: List[str] = None,  # type: ignore
+        candidate_labels: List[str],
         *,
         model: Optional[str] = None,
         hypothesis_template: Optional[str] = None,
@@ -3210,15 +3222,6 @@ class InferenceClient:
         [ZeroShotImageClassificationOutputElement(label='dog', score=0.956),...]
         ```
         """
-        # handle deprecation
-        if labels is not None:
-            if candidate_labels is not None:
-                raise ValueError(
-                    "Cannot specify both `labels` and `candidate_labels`. Use `candidate_labels` instead."
-                )
-            candidate_labels = labels
-        elif candidate_labels is None:
-            raise ValueError("Must specify `candidate_labels`")
         # Raise ValueError if input is less than 2 labels
         if len(candidate_labels) < 2:
             raise ValueError("You must specify at least 2 classes to compare.")

huggingface_hub/inference/_generated/_async_client.py

@@ -87,7 +87,8 @@ from huggingface_hub.inference._generated.types import (
 )
 from huggingface_hub.inference._providers import PROVIDER_T, HFInferenceTask, get_provider_helper
 from huggingface_hub.utils import build_hf_headers, get_session, hf_raise_for_status
-from huggingface_hub.utils._deprecation import _deprecate_arguments, _deprecate_method
+from huggingface_hub.utils._auth import get_token
+from huggingface_hub.utils._deprecation import _deprecate_method
 
 from .._common import _async_yield_from, _import_aiohttp
 
@@ -120,12 +121,11 @@ class AsyncInferenceClient:
             path will be appended to the base URL (see the [TGI Messages API](https://huggingface.co/docs/text-generation-inference/en/messages_api)
             documentation for details). When passing a URL as `model`, the client will not append any suffix path to it.
         provider (`str`, *optional*):
-            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"fireworks-ai"`, `"hf-inference"`, `"hyperbolic"`, `"nebius"`, `"novita"`, `"replicate"`, "sambanova"` or `"together"`.
+            Name of the provider to use for inference. Can be `"black-forest-labs"`, `"cerebras"`, `"cohere"`, `"fal-ai"`, `"fireworks-ai"`, `"hf-inference"`, `"hyperbolic"`, `"nebius"`, `"novita"`, `"openai"`, `"replicate"`, "sambanova"` or `"together"`.
             defaults to hf-inference (Hugging Face Serverless Inference API).
             If model is a URL or `base_url` is passed, then `provider` is not used.
-        token (`str` or `bool`, *optional*):
+        token (`str`, *optional*):
             Hugging Face token. Will default to the locally saved token if not provided.
-            Pass `token=False` if you don't want to send your token to the server.
             Note: for better compatibility with OpenAI's client, `token` has been aliased as `api_key`. Those 2
             arguments are mutually exclusive and have the exact same behavior.
         timeout (`float`, `optional`):
@@ -134,6 +134,9 @@ class AsyncInferenceClient:
         headers (`Dict[str, str]`, `optional`):
             Additional headers to send to the server. By default only the authorization and user-agent headers are sent.
             Values in this dictionary will override the default values.
+        bill_to (`str`, `optional`):
+            The billing account to use for the requests. By default the requests are billed on the user's account.
+            Requests can only be billed to an organization the user is a member of, and which has subscribed to Enterprise Hub.
         cookies (`Dict[str, str]`, `optional`):
             Additional cookies to send to the server.
         trust_env ('bool', 'optional'):
@@ -159,6 +162,7 @@ class AsyncInferenceClient:
         cookies: Optional[Dict[str, str]] = None,
         trust_env: bool = False,
         proxies: Optional[Any] = None,
+        bill_to: Optional[str] = None,
         # OpenAI compatibility
         base_url: Optional[str] = None,
         api_key: Optional[str] = None,
@@ -176,10 +180,43 @@ class AsyncInferenceClient:
                 " `api_key` is an alias for `token` to make the API compatible with OpenAI's client."
                 " It has the exact same behavior as `token`."
             )
+        token = token if token is not None else api_key
+        if isinstance(token, bool):
+            # Legacy behavior: previously is was possible to pass `token=False` to disable authentication. This is not
+            # supported anymore as authentication is required. Better to explicitly raise here rather than risking
+            # sending the locally saved token without the user knowing about it.
+            if token is False:
+                raise ValueError(
+                    "Cannot use `token=False` to disable authentication as authentication is required to run Inference."
+                )
+            warnings.warn(
+                "Using `token=True` to automatically use the locally saved token is deprecated and will be removed in a future release. "
+                "Please use `token=None` instead (default).",
+                DeprecationWarning,
+            )
+            token = get_token()
 
         self.model: Optional[str] = base_url or model
-        self.token: Optional[str] = token if token is not None else api_key
-        self.headers = headers if headers is not None else {}
+        self.token: Optional[str] = token
+
+        self.headers = {**headers} if headers is not None else {}
+        if bill_to is not None:
+            if (
+                constants.HUGGINGFACE_HEADER_X_BILL_TO in self.headers
+                and self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO] != bill_to
+            ):
+                warnings.warn(
+                    f"Overriding existing '{self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO]}' value in headers with '{bill_to}'.",
+                    UserWarning,
+                )
+            self.headers[constants.HUGGINGFACE_HEADER_X_BILL_TO] = bill_to
+
+            if token is not None and not token.startswith("hf_"):
+                warnings.warn(
+                    "You've provided an external provider's API key, so requests will be billed directly by the provider. "
+                    "The `bill_to` parameter is only applicable for Hugging Face billing and will be ignored.",
+                    UserWarning,
+                )
 
         # Configure provider
         self.provider = provider if provider is not None else "hf-inference"
@@ -298,40 +335,39 @@ class AsyncInferenceClient:
         if request_parameters.task in TASKS_EXPECTING_IMAGES and "Accept" not in request_parameters.headers:
             request_parameters.headers["Accept"] = "image/png"
 
-        while True:
-            with _open_as_binary(request_parameters.data) as data_as_binary:
-                # Do not use context manager as we don't want to close the connection immediately when returning
-                # a stream
-                session = self._get_client_session(headers=request_parameters.headers)
-
-                try:
-                    response = await session.post(
-                        request_parameters.url, json=request_parameters.json, data=data_as_binary, proxy=self.proxies
-                    )
-                    response_error_payload = None
-                    if response.status != 200:
-                        try:
-                            response_error_payload = await response.json()  # get payload before connection closed
-                        except Exception:
-                            pass
-                    response.raise_for_status()
-                    if stream:
-                        return _async_yield_from(session, response)
-                    else:
-                        content = await response.read()
-                        await session.close()
-                        return content
-                except asyncio.TimeoutError as error:
-                    await session.close()
-                    # Convert any `TimeoutError` to a `InferenceTimeoutError`
-                    raise InferenceTimeoutError(f"Inference call timed out: {request_parameters.url}") from error  # type: ignore
-                except aiohttp.ClientResponseError as error:
-                    error.response_error_payload = response_error_payload
-                    await session.close()
-                    raise error
-                except Exception:
+        with _open_as_binary(request_parameters.data) as data_as_binary:
+            # Do not use context manager as we don't want to close the connection immediately when returning
+            # a stream
+            session = self._get_client_session(headers=request_parameters.headers)
+
+            try:
+                response = await session.post(
+                    request_parameters.url, json=request_parameters.json, data=data_as_binary, proxy=self.proxies
+                )
+                response_error_payload = None
+                if response.status != 200:
+                    try:
+                        response_error_payload = await response.json()  # get payload before connection closed
+                    except Exception:
+                        pass
+                response.raise_for_status()
+                if stream:
+                    return _async_yield_from(session, response)
+                else:
+                    content = await response.read()
                     await session.close()
-                    raise
+                    return content
+            except asyncio.TimeoutError as error:
+                await session.close()
+                # Convert any `TimeoutError` to a `InferenceTimeoutError`
+                raise InferenceTimeoutError(f"Inference call timed out: {request_parameters.url}") from error  # type: ignore
+            except aiohttp.ClientResponseError as error:
+                error.response_error_payload = response_error_payload
+                await session.close()
+                raise error
+            except Exception:
+                await session.close()
+                raise
 
     async def __aenter__(self):
         return self
@@ -950,7 +986,7 @@ class AsyncInferenceClient:
         ...     messages=messages,
         ...     response_format=response_format,
         ...     max_tokens=500,
-        )
+        ... )
         >>> response.choices[0].message.content
         '{\n\n"activity": "bike ride",\n"animals": ["puppy", "cat", "raccoon"],\n"animals_seen": 3,\n"location": "park"}'
         ```
@@ -1317,7 +1353,7 @@ class AsyncInferenceClient:
         [ImageSegmentationOutputElement(score=0.989008, label='LABEL_184', mask=<PIL.PngImagePlugin.PngImageFile image mode=L size=400x300 at 0x7FDD2B129CC0>), ...]
         ```
         """
-        provider_helper = get_provider_helper(self.provider, task="audio-classification")
+        provider_helper = get_provider_helper(self.provider, task="image-segmentation")
         request_parameters = provider_helper.prepare_request(
             inputs=image,
             parameters={
@@ -2659,7 +2695,7 @@ class AsyncInferenceClient:
             api_key=self.token,
         )
         response = await self._inner_post(request_parameters)
-        response = provider_helper.get_response(response)
+        response = provider_helper.get_response(response, request_parameters)
         return response
 
     async def text_to_speech(
@@ -3094,22 +3130,14 @@ class AsyncInferenceClient:
         response = await self._inner_post(request_parameters)
         return VisualQuestionAnsweringOutputElement.parse_obj_as_list(response)
 
-    @_deprecate_arguments(
-        version="0.30.0",
-        deprecated_args=["labels"],
-        custom_message="`labels`has been renamed to `candidate_labels` and will be removed in huggingface_hub>=0.30.0.",
-    )
     async def zero_shot_classification(
         self,
         text: str,
-        # temporarily keeping it optional for backward compatibility.
-        candidate_labels: List[str] = None,  # type: ignore
+        candidate_labels: List[str],
         *,
         multi_label: Optional[bool] = False,
         hypothesis_template: Optional[str] = None,
         model: Optional[str] = None,
-        # deprecated argument
-        labels: List[str] = None,  # type: ignore
     ) -> List[ZeroShotClassificationOutputElement]:
         """
         Provide as input a text and a set of candidate labels to classify the input text.
@@ -3190,16 +3218,6 @@ class AsyncInferenceClient:
         ]
         ```
         """
-        # handle deprecation
-        if labels is not None:
-            if candidate_labels is not None:
-                raise ValueError(
-                    "Cannot specify both `labels` and `candidate_labels`. Use `candidate_labels` instead."
-                )
-            candidate_labels = labels
-        elif candidate_labels is None:
-            raise ValueError("Must specify `candidate_labels`")
-
         provider_helper = get_provider_helper(self.provider, task="zero-shot-classification")
         request_parameters = provider_helper.prepare_request(
             inputs=text,
@@ -3219,16 +3237,10 @@ class AsyncInferenceClient:
             for label, score in zip(output["labels"], output["scores"])
         ]
 
-    @_deprecate_arguments(
-        version="0.30.0",
-        deprecated_args=["labels"],
-        custom_message="`labels`has been renamed to `candidate_labels` and will be removed in huggingface_hub>=0.30.0.",
-    )
     async def zero_shot_image_classification(
         self,
         image: ContentT,
-        # temporarily keeping it optional for backward compatibility.
-        candidate_labels: List[str] = None,  # type: ignore
+        candidate_labels: List[str],
         *,
         model: Optional[str] = None,
         hypothesis_template: Optional[str] = None,
@@ -3274,15 +3286,6 @@ class AsyncInferenceClient:
         [ZeroShotImageClassificationOutputElement(label='dog', score=0.956),...]
         ```
         """
-        # handle deprecation
-        if labels is not None:
-            if candidate_labels is not None:
-                raise ValueError(
-                    "Cannot specify both `labels` and `candidate_labels`. Use `candidate_labels` instead."
-                )
-            candidate_labels = labels
-        elif candidate_labels is None:
-            raise ValueError("Must specify `candidate_labels`")
         # Raise ValueError if input is less than 2 labels
         if len(candidate_labels) < 2:
             raise ValueError("You must specify at least 2 classes to compare.")

huggingface_hub/inference/_generated/types/__init__.py

@@ -30,6 +30,7 @@ from .chat_completion import (
     ChatCompletionInputMessageChunkType,
     ChatCompletionInputStreamOptions,
     ChatCompletionInputTool,
+    ChatCompletionInputToolCall,
     ChatCompletionInputToolChoiceClass,
     ChatCompletionInputToolChoiceEnum,
     ChatCompletionInputURL,