huggingface-hub 0.26.2__py3-none-any.whl → 0.27.0rc0__py3-none-any.whl

huggingface_hub/inference/_generated/_async_client.py

@@ -56,17 +56,24 @@ from huggingface_hub.inference._generated.types import (
     AutomaticSpeechRecognitionOutput,
     ChatCompletionInputGrammarType,
     ChatCompletionInputStreamOptions,
-    ChatCompletionInputToolType,
+    ChatCompletionInputTool,
+    ChatCompletionInputToolChoiceClass,
+    ChatCompletionInputToolChoiceEnum,
     ChatCompletionOutput,
     ChatCompletionStreamOutput,
     DocumentQuestionAnsweringOutputElement,
     FillMaskOutputElement,
     ImageClassificationOutputElement,
+    ImageClassificationOutputTransform,
     ImageSegmentationOutputElement,
+    ImageSegmentationSubtask,
+    ImageToImageTargetSize,
     ImageToTextOutput,
     ObjectDetectionOutputElement,
+    Padding,
     QuestionAnsweringOutputElement,
     SummarizationOutput,
+    SummarizationTruncationStrategy,
     TableQuestionAnsweringOutputElement,
     TextClassificationOutputElement,
     TextClassificationOutputTransform,
@@ -75,9 +82,10 @@ from huggingface_hub.inference._generated.types import (
     TextGenerationStreamOutput,
     TextToImageTargetSize,
     TextToSpeechEarlyStoppingEnum,
+    TokenClassificationAggregationStrategy,
     TokenClassificationOutputElement,
-    ToolElement,
     TranslationOutput,
+    TranslationTruncationStrategy,
     VisualQuestionAnsweringOutputElement,
     ZeroShotClassificationOutputElement,
     ZeroShotImageClassificationOutputElement,
@@ -170,7 +178,9 @@ class AsyncInferenceClient:
 
         self.model: Optional[str] = model
         self.token: Union[str, bool, None] = token if token is not None else api_key
-        self.headers = CaseInsensitiveDict(build_hf_headers(token=self.token))  # 'authorization' + 'user-agent'
+        self.headers: CaseInsensitiveDict[str] = CaseInsensitiveDict(
+            build_hf_headers(token=self.token)  # 'authorization' + 'user-agent'
+        )
         if headers is not None:
             self.headers.update(headers)
         self.cookies = cookies
@@ -317,7 +327,7 @@ class AsyncInferenceClient:
                         logger.info(f"Waiting for model to be loaded on the server: {error}")
                         if "X-wait-for-model" not in headers and url.startswith(INFERENCE_ENDPOINT):
                             headers["X-wait-for-model"] = "1"
-                        time.sleep(1)
+                        await asyncio.sleep(1)
                         if timeout is not None:
                             timeout = max(self.timeout - (time.time() - t0), 1)  # type: ignore
                         continue
@@ -374,7 +384,7 @@ class AsyncInferenceClient:
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"AudioClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[AudioClassificationOutputElement]`: List of [`AudioClassificationOutputElement`] items containing the predicted labels and their confidence.
@@ -502,9 +512,9 @@ class AsyncInferenceClient:
         stop: Optional[List[str]] = None,
         stream_options: Optional[ChatCompletionInputStreamOptions] = None,
         temperature: Optional[float] = None,
-        tool_choice: Optional[Union[ChatCompletionInputToolType, str]] = None,
+        tool_choice: Optional[Union[ChatCompletionInputToolChoiceClass, "ChatCompletionInputToolChoiceEnum"]] = None,
         tool_prompt: Optional[str] = None,
-        tools: Optional[List[ToolElement]] = None,
+        tools: Optional[List[ChatCompletionInputTool]] = None,
         top_logprobs: Optional[int] = None,
         top_p: Optional[float] = None,
     ) -> ChatCompletionOutput: ...
@@ -527,9 +537,9 @@ class AsyncInferenceClient:
         stop: Optional[List[str]] = None,
         stream_options: Optional[ChatCompletionInputStreamOptions] = None,
         temperature: Optional[float] = None,
-        tool_choice: Optional[Union[ChatCompletionInputToolType, str]] = None,
+        tool_choice: Optional[Union[ChatCompletionInputToolChoiceClass, "ChatCompletionInputToolChoiceEnum"]] = None,
         tool_prompt: Optional[str] = None,
-        tools: Optional[List[ToolElement]] = None,
+        tools: Optional[List[ChatCompletionInputTool]] = None,
         top_logprobs: Optional[int] = None,
         top_p: Optional[float] = None,
     ) -> AsyncIterable[ChatCompletionStreamOutput]: ...
@@ -552,9 +562,9 @@ class AsyncInferenceClient:
         stop: Optional[List[str]] = None,
         stream_options: Optional[ChatCompletionInputStreamOptions] = None,
         temperature: Optional[float] = None,
-        tool_choice: Optional[Union[ChatCompletionInputToolType, str]] = None,
+        tool_choice: Optional[Union[ChatCompletionInputToolChoiceClass, "ChatCompletionInputToolChoiceEnum"]] = None,
         tool_prompt: Optional[str] = None,
-        tools: Optional[List[ToolElement]] = None,
+        tools: Optional[List[ChatCompletionInputTool]] = None,
         top_logprobs: Optional[int] = None,
         top_p: Optional[float] = None,
     ) -> Union[ChatCompletionOutput, AsyncIterable[ChatCompletionStreamOutput]]: ...
@@ -577,9 +587,9 @@ class AsyncInferenceClient:
         stop: Optional[List[str]] = None,
         stream_options: Optional[ChatCompletionInputStreamOptions] = None,
         temperature: Optional[float] = None,
-        tool_choice: Optional[Union[ChatCompletionInputToolType, str]] = None,
+        tool_choice: Optional[Union[ChatCompletionInputToolChoiceClass, "ChatCompletionInputToolChoiceEnum"]] = None,
         tool_prompt: Optional[str] = None,
-        tools: Optional[List[ToolElement]] = None,
+        tools: Optional[List[ChatCompletionInputTool]] = None,
         top_logprobs: Optional[int] = None,
         top_p: Optional[float] = None,
     ) -> Union[ChatCompletionOutput, AsyncIterable[ChatCompletionStreamOutput]]:
@@ -618,7 +628,7 @@ class AsyncInferenceClient:
                 Whether to return log probabilities of the output tokens or not. If true, returns the log
                 probabilities of each output token returned in the content of message.
             max_tokens (`int`, *optional*):
-                Maximum number of tokens allowed in the response. Defaults to 20.
+                Maximum number of tokens allowed in the response. Defaults to 100.
             n (`int`, *optional*):
                 UNUSED.
             presence_penalty (`float`, *optional*):
@@ -645,11 +655,11 @@ class AsyncInferenceClient:
             top_p (`float`, *optional*):
                 Fraction of the most likely next words to sample from.
                 Must be between 0 and 1. Defaults to 1.0.
-            tool_choice ([`ChatCompletionInputToolType`] or `str`, *optional*):
+            tool_choice ([`ChatCompletionInputToolChoiceClass`] or [`ChatCompletionInputToolChoiceEnum`], *optional*):
                 The tool to use for the completion. Defaults to "auto".
             tool_prompt (`str`, *optional*):
                 A prompt to be appended before the tools.
-            tools (List of [`ToolElement`], *optional*):
+            tools (List of [`ChatCompletionInputTool`], *optional*):
                 A list of tools the model may call. Currently, only functions are supported as a tool. Use this to
                 provide a list of functions the model may generate JSON inputs for.
 
@@ -981,28 +991,25 @@ class AsyncInferenceClient:
                 a deployed Inference Endpoint. If not provided, the default recommended document question answering model will be used.
                 Defaults to None.
             doc_stride (`int`, *optional*):
-                If the words in the document are too long to fit with the question for the model, it will
-                be split in several chunks with some overlap. This argument controls the size of that
-                overlap.
+                If the words in the document are too long to fit with the question for the model, it will be split in
+                several chunks with some overlap. This argument controls the size of that overlap.
             handle_impossible_answer (`bool`, *optional*):
-                Whether to accept impossible as an answer.
+                Whether to accept impossible as an answer
             lang (`str`, *optional*):
-                Language to use while running OCR.
+                Language to use while running OCR. Defaults to english.
             max_answer_len (`int`, *optional*):
-                The maximum length of predicted answers (e.g., only answers with a shorter length are
-                considered).
+                The maximum length of predicted answers (e.g., only answers with a shorter length are considered).
             max_question_len (`int`, *optional*):
                 The maximum length of the question after tokenization. It will be truncated if needed.
             max_seq_len (`int`, *optional*):
-                The maximum length of the total sentence (context + question) in tokens of each chunk
-                passed to the model. The context will be split in several chunks (using doc_stride as
-                overlap) if needed.
+                The maximum length of the total sentence (context + question) in tokens of each chunk passed to the
+                model. The context will be split in several chunks (using doc_stride as overlap) if needed.
             top_k (`int`, *optional*):
-                The number of answers to return (will be chosen by order of likelihood). Can return less
-                than top_k answers if there are not enough options available within the context.
-            word_boxes (`List[Union[List[float], str]]`, *optional*):
-                A list of words and bounding boxes (normalized 0->1000). If provided, the inference will
-                skip the OCR step and use the provided bounding boxes instead.
+                The number of answers to return (will be chosen by order of likelihood). Can return less than top_k
+                answers if there are not enough options available within the context.
+            word_boxes (`List[Union[List[float], str`, *optional*):
+                A list of words and bounding boxes (normalized 0->1000). If provided, the inference will skip the OCR
+                step and use the provided bounding boxes instead.
         Returns:
             `List[DocumentQuestionAnsweringOutputElement]`: a list of [`DocumentQuestionAnsweringOutputElement`] items containing the predicted label, associated probability, word ids, and page number.
 
@@ -1019,7 +1026,7 @@ class AsyncInferenceClient:
         >>> from huggingface_hub import AsyncInferenceClient
         >>> client = AsyncInferenceClient()
         >>> await client.document_question_answering(image="https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png", question="What is the invoice number?")
-        [DocumentQuestionAnsweringOutputElement(answer='us-001', end=16, score=0.9999666213989258, start=16, words=None)]
+        [DocumentQuestionAnsweringOutputElement(answer='us-001', end=16, score=0.9999666213989258, start=16)]
         ```
         """
         inputs: Dict[str, Any] = {"question": question, "image": _b64_encode(image)}
@@ -1121,11 +1128,10 @@ class AsyncInferenceClient:
             model (`str`, *optional*):
                 The model to use for the fill mask task. Can be a model ID hosted on the Hugging Face Hub or a URL to
                 a deployed Inference Endpoint. If not provided, the default recommended fill mask model will be used.
-            targets (`List[str]`, *optional*):
-                When passed, the model will limit the scores to the passed targets instead of looking up
-                in the whole vocabulary. If the provided targets are not in the model vocab, they will be
-                tokenized and the first resulting token will be used (with a warning, and that might be
-                slower).
+            targets (`List[str`, *optional*):
+                When passed, the model will limit the scores to the passed targets instead of looking up in the whole
+                vocabulary. If the provided targets are not in the model vocab, they will be tokenized and the first
+                resulting token will be used (with a warning, and that might be slower).
             top_k (`int`, *optional*):
                 When passed, overrides the number of predictions to return.
         Returns:
@@ -1160,7 +1166,7 @@ class AsyncInferenceClient:
         image: ContentT,
         *,
         model: Optional[str] = None,
-        function_to_apply: Optional[Literal["sigmoid", "softmax", "none"]] = None,
+        function_to_apply: Optional["ImageClassificationOutputTransform"] = None,
         top_k: Optional[int] = None,
     ) -> List[ImageClassificationOutputElement]:
         """
@@ -1172,8 +1178,8 @@ class AsyncInferenceClient:
             model (`str`, *optional*):
                 The model to use for image classification. Can be a model ID hosted on the Hugging Face Hub or a URL to a
                 deployed Inference Endpoint. If not provided, the default recommended model for image classification will be used.
-            function_to_apply (`Literal["sigmoid", "softmax", "none"]`, *optional*):
-                The function to apply to the output scores.
+            function_to_apply (`"ImageClassificationOutputTransform"`, *optional*):
+                The function to apply to the model outputs in order to retrieve the scores.
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
         Returns:
@@ -1206,7 +1212,7 @@ class AsyncInferenceClient:
         model: Optional[str] = None,
         mask_threshold: Optional[float] = None,
         overlap_mask_area_threshold: Optional[float] = None,
-        subtask: Optional[Literal["instance", "panoptic", "semantic"]] = None,
+        subtask: Optional["ImageSegmentationSubtask"] = None,
         threshold: Optional[float] = None,
     ) -> List[ImageSegmentationOutputElement]:
         """
@@ -1228,7 +1234,7 @@ class AsyncInferenceClient:
                 Threshold to use when turning the predicted masks into binary values.
             overlap_mask_area_threshold (`float`, *optional*):
                 Mask overlap threshold to eliminate small, disconnected segments.
-            subtask (`Literal["instance", "panoptic", "semantic"]`, *optional*):
+            subtask (`"ImageSegmentationSubtask"`, *optional*):
                 Segmentation task to be performed, depending on model capabilities.
             threshold (`float`, *optional*):
                 Probability threshold to filter out predicted masks.
@@ -1268,12 +1274,11 @@ class AsyncInferenceClient:
         image: ContentT,
         prompt: Optional[str] = None,
         *,
-        negative_prompt: Optional[str] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
+        negative_prompt: Optional[List[str]] = None,
         num_inference_steps: Optional[int] = None,
         guidance_scale: Optional[float] = None,
         model: Optional[str] = None,
+        target_size: Optional[ImageToImageTargetSize] = None,
         **kwargs,
     ) -> "Image":
         """
@@ -1290,21 +1295,19 @@ class AsyncInferenceClient:
                 The input image for translation. It can be raw bytes, an image file, or a URL to an online image.
             prompt (`str`, *optional*):
                 The text prompt to guide the image generation.
-            negative_prompt (`str`, *optional*):
-                A negative prompt to guide the translation process.
-            height (`int`, *optional*):
-                The height in pixels of the generated image.
-            width (`int`, *optional*):
-                The width in pixels of the generated image.
+            negative_prompt (`List[str]`, *optional*):
+                One or several prompt to guide what NOT to include in image generation.
             num_inference_steps (`int`, *optional*):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
+                For diffusion models. The number of denoising steps. More denoising steps usually lead to a higher
+                quality image at the expense of slower inference.
             guidance_scale (`float`, *optional*):
-                Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
+                For diffusion models. A higher guidance scale value encourages the model to generate images closely
+                linked to the text prompt at the expense of lower image quality.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. Defaults to None.
+            target_size (`ImageToImageTargetSize`, *optional*):
+                The size in pixel of the output image.
 
         Returns:
             `Image`: The translated image.
@@ -1327,8 +1330,7 @@ class AsyncInferenceClient:
         parameters = {
             "prompt": prompt,
             "negative_prompt": negative_prompt,
-            "height": height,
-            "width": width,
+            "target_size": target_size,
             "num_inference_steps": num_inference_steps,
             "guidance_scale": guidance_scale,
             **kwargs,
@@ -1537,26 +1539,24 @@ class AsyncInferenceClient:
                 The model to use for the question answering task. Can be a model ID hosted on the Hugging Face Hub or a URL to
                 a deployed Inference Endpoint.
             align_to_words (`bool`, *optional*):
-                Attempts to align the answer to real words. Improves quality on space separated
-                languages. Might hurt on non-space-separated languages (like Japanese or Chinese).
+                Attempts to align the answer to real words. Improves quality on space separated languages. Might hurt
+                on non-space-separated languages (like Japanese or Chinese)
             doc_stride (`int`, *optional*):
-                If the context is too long to fit with the question for the model, it will be split in
-                several chunks with some overlap. This argument controls the size of that overlap.
+                If the context is too long to fit with the question for the model, it will be split in several chunks
+                with some overlap. This argument controls the size of that overlap.
             handle_impossible_answer (`bool`, *optional*):
                 Whether to accept impossible as an answer.
             max_answer_len (`int`, *optional*):
-                The maximum length of predicted answers (e.g., only answers with a shorter length are
-                considered).
+                The maximum length of predicted answers (e.g., only answers with a shorter length are considered).
             max_question_len (`int`, *optional*):
                 The maximum length of the question after tokenization. It will be truncated if needed.
             max_seq_len (`int`, *optional*):
-                The maximum length of the total sentence (context + question) in tokens of each chunk
-                passed to the model. The context will be split in several chunks (using docStride as
-                overlap) if needed.
+                The maximum length of the total sentence (context + question) in tokens of each chunk passed to the
+                model. The context will be split in several chunks (using docStride as overlap) if needed.
             top_k (`int`, *optional*):
-                The number of answers to return (will be chosen by order of likelihood). Note that we
-                return less than topk answers if there are not enough options available within the
-                context.
+                The number of answers to return (will be chosen by order of likelihood). Note that we return less than
+                topk answers if there are not enough options available within the context.
+
         Returns:
             Union[`QuestionAnsweringOutputElement`, List[`QuestionAnsweringOutputElement`]]:
                 When top_k is 1 or not provided, it returns a single `QuestionAnsweringOutputElement`.
@@ -1660,7 +1660,7 @@ class AsyncInferenceClient:
         model: Optional[str] = None,
         clean_up_tokenization_spaces: Optional[bool] = None,
         generate_parameters: Optional[Dict[str, Any]] = None,
-        truncation: Optional[Literal["do_not_truncate", "longest_first", "only_first", "only_second"]] = None,
+        truncation: Optional["SummarizationTruncationStrategy"] = None,
     ) -> SummarizationOutput:
         """
         Generate a summary of a given text using a specified model.
@@ -1678,7 +1678,7 @@ class AsyncInferenceClient:
                 Whether to clean up the potential extra spaces in the text output.
             generate_parameters (`Dict[str, Any]`, *optional*):
                 Additional parametrization of the text generation algorithm.
-            truncation (`Literal["do_not_truncate", "longest_first", "only_first", "only_second"]`, *optional*):
+            truncation (`"SummarizationTruncationStrategy"`, *optional*):
                 The truncation strategy to use.
         Returns:
             [`SummarizationOutput`]: The generated summary text.
@@ -1714,7 +1714,9 @@ class AsyncInferenceClient:
         query: str,
         *,
         model: Optional[str] = None,
-        parameters: Optional[Dict[str, Any]] = None,
+        padding: Optional["Padding"] = None,
+        sequential: Optional[bool] = None,
+        truncation: Optional[bool] = None,
     ) -> TableQuestionAnsweringOutputElement:
         """
         Retrieve the answer to a question from information given in a table.
@@ -1728,8 +1730,14 @@ class AsyncInferenceClient:
             model (`str`):
                 The model to use for the table-question-answering task. Can be a model ID hosted on the Hugging Face
                 Hub or a URL to a deployed Inference Endpoint.
-            parameters (`Dict[str, Any]`, *optional*):
-                Additional inference parameters. Defaults to None.
+            padding (`"Padding"`, *optional*):
+                Activates and controls padding.
+            sequential (`bool`, *optional*):
+                Whether to do inference sequentially or as a batch. Batching is faster, but models like SQA require the
+                inference to be done sequentially to extract relations within sequences, given their conversational
+                nature.
+            truncation (`bool`, *optional*):
+                Activates and controls truncation.
 
         Returns:
             [`TableQuestionAnsweringOutputElement`]: a table question answering output containing the answer, coordinates, cells and the aggregator used.
@@ -1751,6 +1759,11 @@ class AsyncInferenceClient:
         TableQuestionAnsweringOutputElement(answer='36542', coordinates=[[0, 1]], cells=['36542'], aggregator='AVERAGE')
         ```
         """
+        parameters = {
+            "padding": padding,
+            "sequential": sequential,
+            "truncation": truncation,
+        }
         inputs = {
             "query": query,
             "table": table,
@@ -1875,7 +1888,7 @@ class AsyncInferenceClient:
             top_k (`int`, *optional*):
                 When specified, limits the output to the top K most probable classes.
             function_to_apply (`"TextClassificationOutputTransform"`, *optional*):
-                The function to apply to the output.
+                The function to apply to the model outputs in order to retrieve the scores.
 
         Returns:
             `List[TextClassificationOutputElement]`: a list of [`TextClassificationOutputElement`] items containing the predicted label and associated probability.
@@ -2136,7 +2149,7 @@ class AsyncInferenceClient:
             grammar ([`TextGenerationInputGrammarType`], *optional*):
                 Grammar constraints. Can be either a JSONSchema or a regex.
             max_new_tokens (`int`, *optional*):
-                Maximum number of generated tokens
+                Maximum number of generated tokens. Defaults to 100.
             repetition_penalty (`float`, *optional*):
                 The parameter for repetition penalty. 1.0 means no penalty. See [this
                 paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.
@@ -2411,10 +2424,10 @@ class AsyncInferenceClient:
         self,
         prompt: str,
         *,
-        negative_prompt: Optional[str] = None,
+        negative_prompt: Optional[List[str]] = None,
         height: Optional[float] = None,
         width: Optional[float] = None,
-        num_inference_steps: Optional[float] = None,
+        num_inference_steps: Optional[int] = None,
         guidance_scale: Optional[float] = None,
         model: Optional[str] = None,
         scheduler: Optional[str] = None,
@@ -2434,8 +2447,8 @@ class AsyncInferenceClient:
         Args:
             prompt (`str`):
                 The prompt to generate an image from.
-            negative_prompt (`str`, *optional*):
-                An optional negative prompt for the image generation.
+            negative_prompt (`List[str`, *optional*):
+                One or several prompt to guide what NOT to include in image generation.
             height (`float`, *optional*):
                 The height in pixels of the image to generate.
             width (`float`, *optional*):
@@ -2444,8 +2457,8 @@ class AsyncInferenceClient:
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             guidance_scale (`float`, *optional*):
-                Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
+                A higher guidance scale value encourages the model to generate images closely linked to the text
+                prompt, but values too high may cause saturation and other artifacts.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. If not provided, the default recommended text-to-image model will be used.
@@ -2533,44 +2546,42 @@ class AsyncInferenceClient:
                 Defaults to None.
             do_sample (`bool`, *optional*):
                 Whether to use sampling instead of greedy decoding when generating new tokens.
-            early_stopping (`Union[bool, "TextToSpeechEarlyStoppingEnum"`, *optional*):
+            early_stopping (`Union[bool, "TextToSpeechEarlyStoppingEnum"]`, *optional*):
                 Controls the stopping condition for beam-based methods.
             epsilon_cutoff (`float`, *optional*):
-                If set to float strictly between 0 and 1, only tokens with a conditional probability
-                greater than epsilon_cutoff will be sampled. In the paper, suggested values range from
-                3e-4 to 9e-4, depending on the size of the model. See [Truncation Sampling as Language
-                Model Desmoothing](https://hf.co/papers/2210.15191) for more details.
+                If set to float strictly between 0 and 1, only tokens with a conditional probability greater than
+                epsilon_cutoff will be sampled. In the paper, suggested values range from 3e-4 to 9e-4, depending on
+                the size of the model. See [Truncation Sampling as Language Model
+                Desmoothing](https://hf.co/papers/2210.15191) for more details.
             eta_cutoff (`float`, *optional*):
-                Eta sampling is a hybrid of locally typical sampling and epsilon sampling. If set to
-                float strictly between 0 and 1, a token is only considered if it is greater than either
-                eta_cutoff or sqrt(eta_cutoff) * exp(-entropy(softmax(next_token_logits))). The latter
-                term is intuitively the expected next token probability, scaled by sqrt(eta_cutoff). In
-                the paper, suggested values range from 3e-4 to 2e-3, depending on the size of the model.
-                See [Truncation Sampling as Language Model Desmoothing](https://hf.co/papers/2210.15191)
-                for more details.
+                Eta sampling is a hybrid of locally typical sampling and epsilon sampling. If set to float strictly
+                between 0 and 1, a token is only considered if it is greater than either eta_cutoff or sqrt(eta_cutoff)
+                * exp(-entropy(softmax(next_token_logits))). The latter term is intuitively the expected next token
+                probability, scaled by sqrt(eta_cutoff). In the paper, suggested values range from 3e-4 to 2e-3,
+                depending on the size of the model. See [Truncation Sampling as Language Model
+                Desmoothing](https://hf.co/papers/2210.15191) for more details.
             max_length (`int`, *optional*):
                 The maximum length (in tokens) of the generated text, including the input.
             max_new_tokens (`int`, *optional*):
-                The maximum number of tokens to generate. Takes precedence over maxLength.
+                The maximum number of tokens to generate. Takes precedence over max_length.
             min_length (`int`, *optional*):
                 The minimum length (in tokens) of the generated text, including the input.
             min_new_tokens (`int`, *optional*):
-                The minimum number of tokens to generate. Takes precedence over maxLength.
+                The minimum number of tokens to generate. Takes precedence over min_length.
             num_beam_groups (`int`, *optional*):
-                Number of groups to divide num_beams into in order to ensure diversity among different
-                groups of beams. See [this paper](https://hf.co/papers/1610.02424) for more details.
+                Number of groups to divide num_beams into in order to ensure diversity among different groups of beams.
+                See [this paper](https://hf.co/papers/1610.02424) for more details.
             num_beams (`int`, *optional*):
                 Number of beams to use for beam search.
             penalty_alpha (`float`, *optional*):
-                The value balances the model confidence and the degeneration penalty in contrastive
-                search decoding.
+                The value balances the model confidence and the degeneration penalty in contrastive search decoding.
             temperature (`float`, *optional*):
                 The value used to modulate the next token probabilities.
             top_k (`int`, *optional*):
                 The number of highest probability vocabulary tokens to keep for top-k-filtering.
             top_p (`float`, *optional*):
-                If set to float < 1, only the smallest set of most probable tokens with probabilities
-                that add up to top_p or higher are kept for generation.
+                If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to
+                top_p or higher are kept for generation.
             typical_p (`float`, *optional*):
                 Local typicality measures how similar the conditional probability of predicting a target token next is
                 to the expected conditional probability of predicting a random token next, given the partial text
@@ -2627,7 +2638,7 @@ class AsyncInferenceClient:
         text: str,
         *,
         model: Optional[str] = None,
-        aggregation_strategy: Optional[Literal["none", "simple", "first", "average", "max"]] = None,
+        aggregation_strategy: Optional["TokenClassificationAggregationStrategy"] = None,
         ignore_labels: Optional[List[str]] = None,
         stride: Optional[int] = None,
     ) -> List[TokenClassificationOutputElement]:
@@ -2642,10 +2653,10 @@ class AsyncInferenceClient:
                 The model to use for the token classification task. Can be a model ID hosted on the Hugging Face Hub or a URL to
                 a deployed Inference Endpoint. If not provided, the default recommended token classification model will be used.
                 Defaults to None.
-            aggregation_strategy (`Literal["none", "simple", "first", "average", "max"]`, *optional*):
-                The strategy used to fuse tokens based on model predictions.
-            ignore_labels (`List[str]`, *optional*):
-                A list of labels to ignore.
+            aggregation_strategy (`"TokenClassificationAggregationStrategy"`, *optional*):
+                The strategy used to fuse tokens based on model predictions
+            ignore_labels (`List[str`, *optional*):
+                A list of labels to ignore
             stride (`int`, *optional*):
                 The number of overlapping tokens between chunks when splitting the input text.
 
@@ -2704,7 +2715,7 @@ class AsyncInferenceClient:
         src_lang: Optional[str] = None,
         tgt_lang: Optional[str] = None,
         clean_up_tokenization_spaces: Optional[bool] = None,
-        truncation: Optional[Literal["do_not_truncate", "longest_first", "only_first", "only_second"]] = None,
+        truncation: Optional["TranslationTruncationStrategy"] = None,
         generate_parameters: Optional[Dict[str, Any]] = None,
     ) -> TranslationOutput:
         """
@@ -2728,7 +2739,7 @@ class AsyncInferenceClient:
                 Target language to translate to. Required for models that can translate to multiple languages.
             clean_up_tokenization_spaces (`bool`, *optional*):
                 Whether to clean up the potential extra spaces in the text output.
-            truncation (`Literal["do_not_truncate", "longest_first", "only_first", "only_second"]`, *optional*):
+            truncation (`"TranslationTruncationStrategy"`, *optional*):
                 The truncation strategy to use.
             generate_parameters (`Dict[str, Any]`, *optional*):
                 Additional parametrization of the text generation algorithm.
@@ -2752,13 +2763,13 @@ class AsyncInferenceClient:
         >>> await client.translation("My name is Wolfgang and I live in Berlin")
         'Mein Name ist Wolfgang und ich lebe in Berlin.'
         >>> await client.translation("My name is Wolfgang and I live in Berlin", model="Helsinki-NLP/opus-mt-en-fr")
-        TranslationOutput(translation_text='Je m\'appelle Wolfgang et je vis à Berlin.')
+        TranslationOutput(translation_text='Je m'appelle Wolfgang et je vis à Berlin.')
         ```
 
         Specifying languages:
         ```py
         >>> client.translation("My name is Sarah Jessica Parker but you can call me Jessica", model="facebook/mbart-large-50-many-to-many-mmt", src_lang="en_XX", tgt_lang="fr_XX")
-        "Mon nom est Sarah Jessica Parker mais vous pouvez m\'appeler Jessica"
+        "Mon nom est Sarah Jessica Parker mais vous pouvez m'appeler Jessica"
         ```
         """
         # Throw error if only one of `src_lang` and `tgt_lang` was given
@@ -2799,9 +2810,8 @@ class AsyncInferenceClient:
                 a deployed Inference Endpoint. If not provided, the default recommended visual question answering model will be used.
                 Defaults to None.
             top_k (`int`, *optional*):
-                The number of answers to return (will be chosen by order of likelihood). Note that we
-                return less than topk answers if there are not enough options available within the
-                context.
+                The number of answers to return (will be chosen by order of likelihood). Note that we return less than
+                topk answers if there are not enough options available within the context.
         Returns:
             `List[VisualQuestionAnsweringOutputElement]`: a list of [`VisualQuestionAnsweringOutputElement`] items containing the predicted label and associated probability.
 
@@ -2832,14 +2842,22 @@ class AsyncInferenceClient:
         response = await self.post(json=payload, model=model, task="visual-question-answering")
         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,
-        labels: List[str],
+        # temporarily keeping it optional for backward compatibility.
+        candidate_labels: List[str] = None,  # type: ignore
         *,
-        multi_label: bool = False,
+        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.
@@ -2847,20 +2865,22 @@ class AsyncInferenceClient:
         Args:
             text (`str`):
                 The input text to classify.
-            labels (`List[str]`):
-                List of strings. Each string is the verbalization of a possible label for the input text.
-            multi_label (`bool`):
-                Boolean. If True, the probability for each label is evaluated independently and multiple labels can have a probability close to 1 simultaneously or all probabilities can be close to 0.
-                If False, the labels are considered mutually exclusive and the probability over all labels always sums to 1. Defaults to False.
+            candidate_labels (`List[str]`):
+                The set of possible class labels to classify the text into.
+            labels (`List[str]`, *optional*):
+                (deprecated) List of strings. Each string is the verbalization of a possible label for the input text.
+            multi_label (`bool`, *optional*):
+                Whether multiple candidate labels can be true. If false, the scores are normalized such that the sum of
+                the label likelihoods for each sequence is 1. If true, the labels are considered independent and
+                probabilities are normalized for each candidate.
             hypothesis_template (`str`, *optional*):
-                A template sentence string with curly brackets to which the label strings are added. The label strings are added at the position of the curly brackets "{}".
-                Zero-shot classifiers are based on NLI models, which evaluate if a hypothesis is entailed in another text or not.
-                For example, with hypothesis_template="This text is about {}." and labels=["economics", "politics"], the system internally creates the two hypotheses "This text is about economics." and "This text is about politics.".
-                The model then evaluates for both hypotheses if they are entailed in the provided `text` or not.
+                The sentence used in conjunction with `candidate_labels` to attempt the text classification by
+                replacing the placeholder with the candidate labels.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot classification model will be used.
 
+
         Returns:
             `List[ZeroShotClassificationOutputElement]`: List of [`ZeroShotClassificationOutputElement`] items containing the predicted labels and their confidence.
 
@@ -2918,9 +2938,17 @@ 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`")
         parameters = {
-            "candidate_labels": labels,
+            "candidate_labels": candidate_labels,
             "multi_label": multi_label,
             "hypothesis_template": hypothesis_template,
         }
@@ -2936,13 +2964,21 @@ 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,
-        labels: List[str],
+        # temporarily keeping it optional for backward compatibility.
+        candidate_labels: List[str] = None,  # type: ignore
         *,
         model: Optional[str] = None,
         hypothesis_template: Optional[str] = None,
+        # deprecated argument
+        labels: List[str] = None,  # type: ignore
     ) -> List[ZeroShotImageClassificationOutputElement]:
         """
         Provide input image and text labels to predict text labels for the image.
@@ -2950,14 +2986,17 @@ class AsyncInferenceClient:
         Args:
             image (`Union[str, Path, bytes, BinaryIO]`):
                 The input image to caption. It can be raw bytes, an image file, or a URL to an online image.
-            labels (`List[str]`):
-                List of string possible labels. There must be at least 2 labels.
+            candidate_labels (`List[str]`):
+                The candidate labels for this image
+            labels (`List[str]`, *optional*):
+                (deprecated) List of string possible labels. There must be at least 2 labels.
             model (`str`, *optional*):
                 The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed
                 Inference Endpoint. This parameter overrides the model defined at the instance level. If not provided, the default recommended zero-shot image classification model will be used.
             hypothesis_template (`str`, *optional*):
-                The sentence used in conjunction with `labels` to attempt the text classification by replacing the
-                placeholder with the candidate labels.
+                The sentence used in conjunction with `candidate_labels` to attempt the image classification by
+                replacing the placeholder with the candidate labels.
+
         Returns:
             `List[ZeroShotImageClassificationOutputElement]`: List of [`ZeroShotImageClassificationOutputElement`] items containing the predicted labels and their confidence.
 
@@ -2980,13 +3019,23 @@ 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(labels) < 2:
+        if len(candidate_labels) < 2:
             raise ValueError("You must specify at least 2 classes to compare.")
-
-        inputs = {"image": _b64_encode(image), "candidateLabels": ",".join(labels)}
-        parameters = {"hypothesis_template": hypothesis_template}
-        payload = _prepare_payload(inputs, parameters=parameters)
+        parameters = {
+            "candidate_labels": candidate_labels,
+            "hypothesis_template": hypothesis_template,
+        }
+        payload = _prepare_payload(image, parameters=parameters, expect_binary=True)
         response = await self.post(
             **payload,
             model=model,