Inference Client
Last updated
Last updated
Inference is the process of using a trained model to make predictions on new data. As this process can be compute-intensive, running on a dedicated server can be an interesting option. The huggingface_hub library provides an easy way to call a service that runs inference for hosted models. There are several services you can connect to:
: a service that allows you to run accelerated inference on Hugging Face’s infrastructure for free. This service is a fast way to get started, test different models, and prototype AI products.
: a product to easily deploy models to production. Inference is run by Hugging Face in a dedicated, fully managed infrastructure on a cloud provider of your choice.
These services can be called with the object. Please refer to for more information on how to use it.
( model: typing.Optional[str] = Nonetoken: typing.Union[str, bool, NoneType] = Nonetimeout: typing.Optional[float] = Noneheaders: typing.Union[typing.Dict[str, str], NoneType] = Nonecookies: typing.Union[typing.Dict[str, str], NoneType] = None )
Parameters
model (str, optional) — The model to run inference with. Can be a model id hosted on the Hugging Face Hub, e.g. bigcode/starcoder or a URL to a deployed Inference Endpoint. Defaults to None, in which case a recommended model is automatically selected for the task.
token (str, optional) — Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
timeout (float, optional) — The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
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.
cookies (Dict[str, str], optional) — Additional cookies to send to the server.
Initialize a new Inference Client.
audio_classification
( audio: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
audio (Union[str, Path, bytes, BinaryIO]) — The audio content to classify. It can be raw audio bytes, a local audio file, or a URL pointing to an audio file.
model (str, optional) — The model to use for audio 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 audio classification will be used.
Returns
List[Dict]
The classification output containing the predicted label and its confidence.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform audio classification on the provided audio content.
Example:
Copied
automatic_speech_recognition
( audio: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → str
Parameters
audio (Union[str, Path, bytes, BinaryIO]) — The content to transcribe. It can be raw audio bytes, local audio file, or a URL to an audio file.
model (str, optional) — The model to use for ASR. 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 ASR will be used.
Returns
str
The transcribed text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform automatic speech recognition (ASR or audio-to-text) on the given audio content.
Example:
Copied
conversational
( text: strgenerated_responses: typing.Optional[typing.List[str]] = Nonepast_user_inputs: typing.Optional[typing.List[str]] = Noneparameters: typing.Union[typing.Dict[str, typing.Any], NoneType] = Nonemodel: typing.Optional[str] = None ) → Dict
Parameters
text (str) — The last input from the user in the conversation.
generated_responses (List[str], optional) — A list of strings corresponding to the earlier replies from the model. Defaults to None.
past_user_inputs (List[str], optional) — A list of strings corresponding to the earlier replies from the user. Should be the same length as generated_responses. Defaults to None.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
Dict
The generated conversational output.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Generate conversational responses based on the given input text (i.e. chat with the API).
Example:
Copied
document_question_answering
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]question: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
question (str) — Question to be answered.
model (str, optional) — The model to use for the document question answering 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 document question answering model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label, associated probability, word ids, and page number.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Answer questions on document images.
Example:
Copied
feature_extraction
( text: strmodel: typing.Optional[str] = None ) → np.ndarray
Parameters
text (str) — The text to embed.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
np.ndarray
The embedding representing the input text as a float32 numpy array.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Generate embeddings for a given text.
Example:
Copied
fill_mask
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — a string to be filled from, must contain the [MASK] token (check model card for exact name of the mask).
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. Defaults to None.
Returns
List[Dict]
a list of fill mask output dictionaries containing the predicted label, associated probability, token reference, and completed text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Fill in a hole with a missing word (token to be precise).
Example:
Copied
get_model_status
( model: typing.Optional[str] = None ) → ModelStatus
Parameters
Returns
ModelStatus
An instance of ModelStatus dataclass, containing information, about the state of the model: load, state, compute type and framework.
Get the status of a model hosted on the Inference API.
Example:
Copied
image_classification
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to classify. It can be raw bytes, an image file, or a URL to an online image.
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.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image classification on the given image using the specified model.
Example:
Copied
image_segmentation
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to segment. It can be raw bytes, an image file, or a URL to an online image.
model (str, optional) — The model to use for image segmentation. 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 segmentation will be used.
Returns
List[Dict]
A list of dictionaries containing the segmented masks and associated attributes.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image segmentation on the given image using the specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
image_to_image
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]prompt: typing.Optional[str] = Nonenegative_prompt: typing.Optional[str] = Noneheight: typing.Optional[int] = Nonewidth: typing.Optional[int] = Nonenum_inference_steps: typing.Optional[int] = Noneguidance_scale: typing.Optional[float] = Nonemodel: typing.Optional[str] = None**kwargs ) → Image
Parameters
image (Union[str, Path, bytes, BinaryIO]) — 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.
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.
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.
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.
Returns
Image
The translated image.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image-to-image translation using a specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
image_to_text
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → str
Parameters
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..
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.
Returns
str
The generated text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Takes an input image and return text.
Models can have very different outputs depending on your use case (image captioning, optical character recognition (OCR), Pix2Struct, etc). Please have a look to the model card to learn more about a model’s specificities.
Example:
Copied
list_deployed_models
( frameworks: typing.Union[NoneType, str, typing.Literal['all'], typing.List[str]] = None ) → Dict[str, List[str]]
Parameters
frameworks (Literal["all"] or List[str] or str, optional) — The frameworks to filter on. By default only a subset of the available frameworks are tested. If set to “all”, all available frameworks will be tested. It is also possible to provide a single framework or a custom set of frameworks to check.
Returns
Dict[str, List[str]]
A dictionary mapping task names to a sorted list of model IDs.
List models currently deployed on the Inference API service.
This helper checks deployed models framework by framework. By default, it will check the 4 main frameworks that are supported and account for 95% of the hosted models. However, if you want a complete list of models you can specify frameworks="all" as input. Alternatively, if you know before-hand which framework you are interested in, you can also restrict to search to this one (e.g. frameworks="text-generation-inference"). The more frameworks are checked, the more time it will take.
Example:
Copied
object_detection
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[ObjectDetectionOutput]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to detect objects on. It can be raw bytes, an image file, or a URL to an online image.
model (str, optional) — The model to use for object detection. 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 object detection (DETR) will be used.
Returns
List[ObjectDetectionOutput]
A list of dictionaries containing the bounding boxes and associated attributes.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
ValueError — If the request output is not a List.
Perform object detection on the given image using the specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
post
( json: typing.Union[str, typing.Dict, typing.List, NoneType] = Nonedata: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path, NoneType] = Nonemodel: typing.Optional[str] = Nonetask: typing.Optional[str] = Nonestream: bool = False ) → bytes
Parameters
json (Union[str, Dict, List], optional) — The JSON data to send in the request body. Defaults to None.
data (Union[str, Path, bytes, BinaryIO], optional) — The content to send in the request body. It can be raw bytes, a pointer to an opened file, a local file path, or a URL to an online resource (image, audio file,…). If both json and data are passed, data will take precedence. At least json or data must be provided. Defaults to None.
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. Will override the model defined at the instance level. Defaults to None.
task (str, optional) — The task to perform on the inference. Used only to default to a recommended model if model is not provided. At least model or task must be provided. Defaults to None.
stream (bool, optional) — Whether to iterate over streaming APIs.
Returns
bytes
The raw bytes returned by the server.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Make a POST request to the inference server.
question_answering
( question: strcontext: strmodel: typing.Optional[str] = None ) → Dict
Parameters
question (str) — Question to be answered.
context (str) — The context of the question.
model (str) — 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.
Returns
Dict
a dictionary of question answering output containing the score, start index, end index, and answer.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Retrieve the answer to a question from a given text.
Example:
Copied
sentence_similarity
( sentence: strother_sentences: typing.List[str]model: typing.Optional[str] = None ) → List[float]
Parameters
sentence (str) — The main sentence to compare to others.
other_sentences (List[str]) — The list of sentences to compare to.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
List[float]
The embedding representing the input text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Compute the semantic similarity between a sentence and a list of other sentences by comparing their embeddings.
Example:
Copied
summarization
( text: strparameters: typing.Union[typing.Dict[str, typing.Any], NoneType] = Nonemodel: typing.Optional[str] = None ) → str
Parameters
text (str) — The input text to summarize.
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.
Returns
str
The generated summary text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Generate a summary of a given text using a specified model.
Example:
Copied
table_question_answering
( table: typing.Dict[str, typing.Any]query: strmodel: typing.Optional[str] = None ) → Dict
Parameters
table (str) — A table of data represented as a dict of lists where entries are headers and the lists are all the values, all lists must have the same size.
query (str) — The query in plain text that you want to ask the table.
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.
Returns
Dict
a dictionary of table question answering output containing the answer, coordinates, cells and the aggregator used.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Retrieve the answer to a question from information given in a table.
Example:
Copied
tabular_classification
( table: typing.Dict[str, typing.Any]model: str ) → List
Parameters
table (Dict[str, Any]) — Set of attributes to classify.
model (str) — The model to use for the tabular-classification task. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint.
Returns
List
a list of labels, one per row in the initial table.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Classifying a target category (a group) based on a set of attributes.
Example:
Copied
tabular_regression
( table: typing.Dict[str, typing.Any]model: str ) → List
Parameters
table (Dict[str, Any]) — Set of attributes stored in a table. The attributes used to predict the target can be both numerical and categorical.
model (str) — The model to use for the tabular-regression task. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint.
Returns
List
a list of predicted numerical target values.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Predicting a numerical target value given a set of attributes/features in a table.
Example:
Copied
text_classification
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — A string to be classified.
model (str, optional) — The model to use for the text 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 text classification model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform text classification (e.g. sentiment-analysis) on the given text.
Example:
Copied
text_generation
( prompt: strdetails: bool = Falsestream: bool = Falsemodel: typing.Optional[str] = Nonedo_sample: bool = Falsemax_new_tokens: int = 20best_of: typing.Optional[int] = Nonerepetition_penalty: typing.Optional[float] = Nonereturn_full_text: bool = Falseseed: typing.Optional[int] = Nonestop_sequences: typing.Optional[typing.List[str]] = Nonetemperature: typing.Optional[float] = Nonetop_k: typing.Optional[int] = Nonetop_p: typing.Optional[float] = Nonetruncate: typing.Optional[int] = Nonetypical_p: typing.Optional[float] = Nonewatermark: bool = Falsedecoder_input_details: bool = False ) → Union[str, TextGenerationResponse, Iterable[str], Iterable[TextGenerationStreamResponse]]
Parameters
prompt (str) — Input text.
details (bool, optional) — By default, text_generation returns a string. Pass details=True if you want a detailed output (tokens, probabilities, seed, finish reason, etc.). Only available for models running on with the text-generation-inference backend.
stream (bool, optional) — By default, text_generation returns the full generated text. Pass stream=True if you want a stream of tokens to be returned. Only available for models running on with the text-generation-inference backend.
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.
do_sample (bool) — Activate logits sampling
max_new_tokens (int) — Maximum number of generated tokens
best_of (int) — Generate best_of sequences and return the one if the highest token logprobs
return_full_text (bool) — Whether to prepend the prompt to the generated text
seed (int) — Random sampling seed
stop_sequences (List[str]) — Stop generating tokens if a member of stop_sequences is generated
temperature (float) — The value used to module the logits distribution.
top_k (int) — The number of highest probability vocabulary tokens to keep for top-k-filtering.
top_p (float) — If set to < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
truncate (int) — Truncate inputs tokens to the given size
decoder_input_details (bool) — Return the decoder input token logprobs and ids. You must set details=True as well for it to be taken into account. Defaults to False.
Returns
Union[str, TextGenerationResponse, Iterable[str], Iterable[TextGenerationStreamResponse]]
Generated text returned from the server:
if stream=False and details=False, the generated text is returned as a str (default)
if stream=True and details=False, the generated text is returned token by token as a Iterable[str]
Raises
ValidationError — If input values are not valid. No HTTP call is made to the server.
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Given a prompt, generate the following text.
It is recommended to have Pydantic installed in order to get inputs validated. This is preferable as it allow early failures.
API endpoint is supposed to run with the text-generation-inference backend (TGI). This backend is the go-to solution to run large language models at scale. However, for some smaller models (e.g. “gpt2”) the default transformers + api-inference solution is still in use. Both approaches have very similar APIs, but not exactly the same. This method is compatible with both approaches but some parameters are only available for text-generation-inference. If some parameters are ignored, a warning message is triggered but the process continues correctly.
Example:
Copied
text_to_image
( prompt: strnegative_prompt: typing.Optional[str] = Noneheight: typing.Optional[float] = Nonewidth: typing.Optional[float] = Nonenum_inference_steps: typing.Optional[float] = Noneguidance_scale: typing.Optional[float] = Nonemodel: typing.Optional[str] = None**kwargs ) → Image
Parameters
prompt (str) — The prompt to generate an image from.
negative_prompt (str, optional) — An optional negative prompt for the image generation.
height (float, optional) — The height in pixels of the image to generate.
width (float, optional) — The width in pixels of the image to generate.
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.
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.
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.
Returns
Image
The generated image.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Generate an image based on a given text using a specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
text_to_speech
( text: strmodel: typing.Optional[str] = None ) → bytes
Parameters
text (str) — The text to synthesize.
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.
Returns
bytes
The generated audio.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Synthesize an audio of a voice pronouncing a given text.
Example:
Copied
token_classification
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — A string to be classified.
model (str, optional) — 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.
Returns
List[Dict]
List of token classification outputs containing the entity group, confidence score, word, start and end index.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Perform token classification on the given text. Usually used for sentence parsing, either grammatical, or Named Entity Recognition (NER) to understand keywords contained within text.
Example:
Copied
translation
( text: strmodel: typing.Optional[str] = None ) → str
Parameters
text (str) — A string to be translated.
model (str, optional) — The model to use for the translation 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 translation model will be used. Defaults to None.
Returns
str
The generated translated text.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Convert text from one language to another.
Example:
Copied
visual_question_answering
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]question: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
question (str) — Question to be answered.
model (str, optional) — The model to use for the visual question answering 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 visual question answering model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
InferenceTimeoutError or HTTPError
InferenceTimeoutError — If the model is unavailable or the request times out.
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Answering open-ended questions based on an image.
Example:
Copied
zero_shot_classification
( text: strlabels: typing.List[str]multi_label: bool = Falsemodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — The input text to classify.
labels (List[str]) — List of string possible labels. There must be at least 2 labels.
multi_label (bool) — Boolean that is set to True if classes can overlap.
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.
Returns
List[Dict]
List of classification outputs containing the predicted labels and their confidence.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Provide as input a text and a set of candidate labels to classify the input text.
Example:
Copied
zero_shot_image_classification
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]labels: typing.List[str]model: typing.Optional[str] = None ) → List[Dict]
Parameters
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.
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.
Returns
List[Dict]
List of classification outputs containing the predicted labels and their confidence.
Raises
HTTPError — If the request fails with an HTTP error status code other than HTTP 503.
Provide input image and text labels to predict text labels for the image.
Example:
Copied
An async version of the client is also provided, based on asyncio and aiohttp. To use it, you can either install aiohttp directly or use the [inference] extra:
Copied
( model: typing.Optional[str] = Nonetoken: typing.Union[str, bool, NoneType] = Nonetimeout: typing.Optional[float] = Noneheaders: typing.Union[typing.Dict[str, str], NoneType] = Nonecookies: typing.Union[typing.Dict[str, str], NoneType] = None )
Parameters
model (str, optional) — The model to run inference with. Can be a model id hosted on the Hugging Face Hub, e.g. bigcode/starcoder or a URL to a deployed Inference Endpoint. Defaults to None, in which case a recommended model is automatically selected for the task.
token (str, optional) — Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server.
timeout (float, optional) — The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available.
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.
cookies (Dict[str, str], optional) — Additional cookies to send to the server.
Initialize a new Inference Client.
audio_classification
( audio: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
audio (Union[str, Path, bytes, BinaryIO]) — The audio content to classify. It can be raw audio bytes, a local audio file, or a URL pointing to an audio file.
model (str, optional) — The model to use for audio 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 audio classification will be used.
Returns
List[Dict]
The classification output containing the predicted label and its confidence.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform audio classification on the provided audio content.
Example:
Copied
automatic_speech_recognition
( audio: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → str
Parameters
audio (Union[str, Path, bytes, BinaryIO]) — The content to transcribe. It can be raw audio bytes, local audio file, or a URL to an audio file.
model (str, optional) — The model to use for ASR. 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 ASR will be used.
Returns
str
The transcribed text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform automatic speech recognition (ASR or audio-to-text) on the given audio content.
Example:
Copied
conversational
( text: strgenerated_responses: typing.Optional[typing.List[str]] = Nonepast_user_inputs: typing.Optional[typing.List[str]] = Noneparameters: typing.Union[typing.Dict[str, typing.Any], NoneType] = Nonemodel: typing.Optional[str] = None ) → Dict
Parameters
text (str) — The last input from the user in the conversation.
generated_responses (List[str], optional) — A list of strings corresponding to the earlier replies from the model. Defaults to None.
past_user_inputs (List[str], optional) — A list of strings corresponding to the earlier replies from the user. Should be the same length as generated_responses. Defaults to None.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
Dict
The generated conversational output.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Generate conversational responses based on the given input text (i.e. chat with the API).
Example:
Copied
document_question_answering
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]question: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
question (str) — Question to be answered.
model (str, optional) — The model to use for the document question answering 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 document question answering model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label, associated probability, word ids, and page number.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Answer questions on document images.
Example:
Copied
feature_extraction
( text: strmodel: typing.Optional[str] = None ) → np.ndarray
Parameters
text (str) — The text to embed.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
np.ndarray
The embedding representing the input text as a float32 numpy array.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Generate embeddings for a given text.
Example:
Copied
fill_mask
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — a string to be filled from, must contain the [MASK] token (check model card for exact name of the mask).
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. Defaults to None.
Returns
List[Dict]
a list of fill mask output dictionaries containing the predicted label, associated probability, token reference, and completed text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Fill in a hole with a missing word (token to be precise).
Example:
Copied
get_model_status
( model: typing.Optional[str] = None ) → ModelStatus
Parameters
Returns
ModelStatus
An instance of ModelStatus dataclass, containing information, about the state of the model: load, state, compute type and framework.
Get the status of a model hosted on the Inference API.
Example:
Copied
image_classification
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to classify. It can be raw bytes, an image file, or a URL to an online image.
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.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image classification on the given image using the specified model.
Example:
Copied
image_segmentation
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to segment. It can be raw bytes, an image file, or a URL to an online image.
model (str, optional) — The model to use for image segmentation. 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 segmentation will be used.
Returns
List[Dict]
A list of dictionaries containing the segmented masks and associated attributes.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image segmentation on the given image using the specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
image_to_image
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]prompt: typing.Optional[str] = Nonenegative_prompt: typing.Optional[str] = Noneheight: typing.Optional[int] = Nonewidth: typing.Optional[int] = Nonenum_inference_steps: typing.Optional[int] = Noneguidance_scale: typing.Optional[float] = Nonemodel: typing.Optional[str] = None**kwargs ) → Image
Parameters
image (Union[str, Path, bytes, BinaryIO]) — 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.
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.
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.
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.
Returns
Image
The translated image.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform image-to-image translation using a specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
image_to_text
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → str
Parameters
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..
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.
Returns
str
The generated text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Takes an input image and return text.
Models can have very different outputs depending on your use case (image captioning, optical character recognition (OCR), Pix2Struct, etc). Please have a look to the model card to learn more about a model’s specificities.
Example:
Copied
list_deployed_models
( frameworks: typing.Union[NoneType, str, typing.Literal['all'], typing.List[str]] = None ) → Dict[str, List[str]]
Parameters
frameworks (Literal["all"] or List[str] or str, optional) — The frameworks to filter on. By default only a subset of the available frameworks are tested. If set to “all”, all available frameworks will be tested. It is also possible to provide a single framework or a custom set of frameworks to check.
Returns
Dict[str, List[str]]
A dictionary mapping task names to a sorted list of model IDs.
List models currently deployed on the Inference API service.
This helper checks deployed models framework by framework. By default, it will check the 4 main frameworks that are supported and account for 95% of the hosted models. However, if you want a complete list of models you can specify frameworks="all" as input. Alternatively, if you know before-hand which framework you are interested in, you can also restrict to search to this one (e.g. frameworks="text-generation-inference"). The more frameworks are checked, the more time it will take.
Example:
Copied
object_detection
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]model: typing.Optional[str] = None ) → List[ObjectDetectionOutput]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The image to detect objects on. It can be raw bytes, an image file, or a URL to an online image.
model (str, optional) — The model to use for object detection. 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 object detection (DETR) will be used.
Returns
List[ObjectDetectionOutput]
A list of dictionaries containing the bounding boxes and associated attributes.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
ValueError — If the request output is not a List.
Perform object detection on the given image using the specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
post
( json: typing.Union[str, typing.Dict, typing.List, NoneType] = Nonedata: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path, NoneType] = Nonemodel: typing.Optional[str] = Nonetask: typing.Optional[str] = Nonestream: bool = False ) → bytes
Parameters
json (Union[str, Dict, List], optional) — The JSON data to send in the request body. Defaults to None.
data (Union[str, Path, bytes, BinaryIO], optional) — The content to send in the request body. It can be raw bytes, a pointer to an opened file, a local file path, or a URL to an online resource (image, audio file,…). If both json and data are passed, data will take precedence. At least json or data must be provided. Defaults to None.
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. Will override the model defined at the instance level. Defaults to None.
task (str, optional) — The task to perform on the inference. Used only to default to a recommended model if model is not provided. At least model or task must be provided. Defaults to None.
stream (bool, optional) — Whether to iterate over streaming APIs.
Returns
bytes
The raw bytes returned by the server.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Make a POST request to the inference server.
question_answering
( question: strcontext: strmodel: typing.Optional[str] = None ) → Dict
Parameters
question (str) — Question to be answered.
context (str) — The context of the question.
model (str) — 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.
Returns
Dict
a dictionary of question answering output containing the score, start index, end index, and answer.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Retrieve the answer to a question from a given text.
Example:
Copied
sentence_similarity
( sentence: strother_sentences: typing.List[str]model: typing.Optional[str] = None ) → List[float]
Parameters
sentence (str) — The main sentence to compare to others.
other_sentences (List[str]) — The list of sentences to compare to.
model (str, optional) — The model to use for the conversational 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 conversational model will be used. Defaults to None.
Returns
List[float]
The embedding representing the input text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Compute the semantic similarity between a sentence and a list of other sentences by comparing their embeddings.
Example:
Copied
summarization
( text: strparameters: typing.Union[typing.Dict[str, typing.Any], NoneType] = Nonemodel: typing.Optional[str] = None ) → str
Parameters
text (str) — The input text to summarize.
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.
Returns
str
The generated summary text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Generate a summary of a given text using a specified model.
Example:
Copied
table_question_answering
( table: typing.Dict[str, typing.Any]query: strmodel: typing.Optional[str] = None ) → Dict
Parameters
table (str) — A table of data represented as a dict of lists where entries are headers and the lists are all the values, all lists must have the same size.
query (str) — The query in plain text that you want to ask the table.
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.
Returns
Dict
a dictionary of table question answering output containing the answer, coordinates, cells and the aggregator used.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Retrieve the answer to a question from information given in a table.
Example:
Copied
tabular_classification
( table: typing.Dict[str, typing.Any]model: str ) → List
Parameters
table (Dict[str, Any]) — Set of attributes to classify.
model (str) — The model to use for the tabular-classification task. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint.
Returns
List
a list of labels, one per row in the initial table.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Classifying a target category (a group) based on a set of attributes.
Example:
Copied
tabular_regression
( table: typing.Dict[str, typing.Any]model: str ) → List
Parameters
table (Dict[str, Any]) — Set of attributes stored in a table. The attributes used to predict the target can be both numerical and categorical.
model (str) — The model to use for the tabular-regression task. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint.
Returns
List
a list of predicted numerical target values.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Predicting a numerical target value given a set of attributes/features in a table.
Example:
Copied
text_classification
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — A string to be classified.
model (str, optional) — The model to use for the text 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 text classification model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform text classification (e.g. sentiment-analysis) on the given text.
Example:
Copied
text_generation
( prompt: strdetails: bool = Falsestream: bool = Falsemodel: typing.Optional[str] = Nonedo_sample: bool = Falsemax_new_tokens: int = 20best_of: typing.Optional[int] = Nonerepetition_penalty: typing.Optional[float] = Nonereturn_full_text: bool = Falseseed: typing.Optional[int] = Nonestop_sequences: typing.Optional[typing.List[str]] = Nonetemperature: typing.Optional[float] = Nonetop_k: typing.Optional[int] = Nonetop_p: typing.Optional[float] = Nonetruncate: typing.Optional[int] = Nonetypical_p: typing.Optional[float] = Nonewatermark: bool = Falsedecoder_input_details: bool = False ) → Union[str, TextGenerationResponse, Iterable[str], Iterable[TextGenerationStreamResponse]]
Parameters
prompt (str) — Input text.
details (bool, optional) — By default, text_generation returns a string. Pass details=True if you want a detailed output (tokens, probabilities, seed, finish reason, etc.). Only available for models running on with the text-generation-inference backend.
stream (bool, optional) — By default, text_generation returns the full generated text. Pass stream=True if you want a stream of tokens to be returned. Only available for models running on with the text-generation-inference backend.
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.
do_sample (bool) — Activate logits sampling
max_new_tokens (int) — Maximum number of generated tokens
best_of (int) — Generate best_of sequences and return the one if the highest token logprobs
return_full_text (bool) — Whether to prepend the prompt to the generated text
seed (int) — Random sampling seed
stop_sequences (List[str]) — Stop generating tokens if a member of stop_sequences is generated
temperature (float) — The value used to module the logits distribution.
top_k (int) — The number of highest probability vocabulary tokens to keep for top-k-filtering.
top_p (float) — If set to < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
truncate (int) — Truncate inputs tokens to the given size
decoder_input_details (bool) — Return the decoder input token logprobs and ids. You must set details=True as well for it to be taken into account. Defaults to False.
Returns
Union[str, TextGenerationResponse, Iterable[str], Iterable[TextGenerationStreamResponse]]
Generated text returned from the server:
if stream=False and details=False, the generated text is returned as a str (default)
if stream=True and details=False, the generated text is returned token by token as a Iterable[str]
Raises
ValidationError — If input values are not valid. No HTTP call is made to the server.
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Given a prompt, generate the following text.
It is recommended to have Pydantic installed in order to get inputs validated. This is preferable as it allow early failures.
API endpoint is supposed to run with the text-generation-inference backend (TGI). This backend is the go-to solution to run large language models at scale. However, for some smaller models (e.g. “gpt2”) the default transformers + api-inference solution is still in use. Both approaches have very similar APIs, but not exactly the same. This method is compatible with both approaches but some parameters are only available for text-generation-inference. If some parameters are ignored, a warning message is triggered but the process continues correctly.
Example:
Copied
text_to_image
( prompt: strnegative_prompt: typing.Optional[str] = Noneheight: typing.Optional[float] = Nonewidth: typing.Optional[float] = Nonenum_inference_steps: typing.Optional[float] = Noneguidance_scale: typing.Optional[float] = Nonemodel: typing.Optional[str] = None**kwargs ) → Image
Parameters
prompt (str) — The prompt to generate an image from.
negative_prompt (str, optional) — An optional negative prompt for the image generation.
height (float, optional) — The height in pixels of the image to generate.
width (float, optional) — The width in pixels of the image to generate.
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.
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.
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.
Returns
Image
The generated image.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Generate an image based on a given text using a specified model.
You must have PIL installed if you want to work with images (pip install Pillow).
Example:
Copied
text_to_speech
( text: strmodel: typing.Optional[str] = None ) → bytes
Parameters
text (str) — The text to synthesize.
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.
Returns
bytes
The generated audio.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Synthesize an audio of a voice pronouncing a given text.
Example:
Copied
token_classification
( text: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — A string to be classified.
model (str, optional) — 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.
Returns
List[Dict]
List of token classification outputs containing the entity group, confidence score, word, start and end index.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Perform token classification on the given text. Usually used for sentence parsing, either grammatical, or Named Entity Recognition (NER) to understand keywords contained within text.
Example:
Copied
translation
( text: strmodel: typing.Optional[str] = None ) → str
Parameters
text (str) — A string to be translated.
model (str, optional) — The model to use for the translation 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 translation model will be used. Defaults to None.
Returns
str
The generated translated text.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Convert text from one language to another.
Example:
Copied
visual_question_answering
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]question: strmodel: typing.Optional[str] = None ) → List[Dict]
Parameters
image (Union[str, Path, bytes, BinaryIO]) — The input image for the context. It can be raw bytes, an image file, or a URL to an online image.
question (str) — Question to be answered.
model (str, optional) — The model to use for the visual question answering 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 visual question answering model will be used. Defaults to None.
Returns
List[Dict]
a list of dictionaries containing the predicted label and associated probability.
Raises
InferenceTimeoutError or aiohttp.ClientResponseError
InferenceTimeoutError — If the model is unavailable or the request times out.
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Answering open-ended questions based on an image.
Example:
Copied
zero_shot_classification
( text: strlabels: typing.List[str]multi_label: bool = Falsemodel: typing.Optional[str] = None ) → List[Dict]
Parameters
text (str) — The input text to classify.
labels (List[str]) — List of string possible labels. There must be at least 2 labels.
multi_label (bool) — Boolean that is set to True if classes can overlap.
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.
Returns
List[Dict]
List of classification outputs containing the predicted labels and their confidence.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Provide as input a text and a set of candidate labels to classify the input text.
Example:
Copied
zero_shot_image_classification
( image: typing.Union[bytes, typing.BinaryIO, str, pathlib.Path]labels: typing.List[str]model: typing.Optional[str] = None ) → List[Dict]
Parameters
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.
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.
Returns
List[Dict]
List of classification outputs containing the predicted labels and their confidence.
Raises
aiohttp.ClientResponseError — If the request fails with an HTTP error status code other than HTTP 503.
Provide input image and text labels to predict text labels for the image.
Example:
Copied
( *args**kwargs )
Error raised when a model is unavailable or the request times out.
For most tasks, the return value has a built-in type (string, list, image…). Here is a list for the more complex types.
( *args**kwargs )
Parameters
label (str) — The label predicted by the model.
score (float) — The score of the label predicted by the model.
( *args**kwargs )
Parameters
generated_responses (List[str]) — A list of the responses from the model.
past_user_inputs (List[str]) — A list of the inputs from the user. Must be the same length as generated_responses.
( *args**kwargs )
Parameters
generated_text (str) — The last response from the model.
conversation (ConversationalOutputConversation) — The past conversation.
warnings (List[str]) — A list of warnings associated with the process.
( *args**kwargs )
Parameters
label (str) — The label corresponding to the mask.
mask (Image) — An Image object representing the mask predicted by the model.
score (float) — The score associated with the label for this mask.
( *args**kwargs )
Parameters
entity_group (str) — The type for the entity being recognized (model specific).
score (float) — The score of the label predicted by the model.
word (str) — The string that was captured.
start (int) — The offset stringwise where the answer is located. Useful to disambiguate if word occurs multiple times.
end (int) — The offset stringwise where the answer is located. Useful to disambiguate if word occurs multiple times.
( do_sample: bool = Falsemax_new_tokens: int = 20repetition_penalty: typing.Optional[float] = Nonereturn_full_text: bool = Falsestop: typing.List[str] = <factory>seed: typing.Optional[int] = Nonetemperature: typing.Optional[float] = Nonetop_k: typing.Optional[int] = Nonetop_p: typing.Optional[float] = Nonetruncate: typing.Optional[int] = Nonetypical_p: typing.Optional[float] = Nonebest_of: typing.Optional[int] = Nonewatermark: bool = Falsedetails: bool = Falsedecoder_input_details: bool = False )
Parameters
do_sample (bool, optional) — Activate logits sampling. Defaults to False.
max_new_tokens (int, optional) — Maximum number of generated tokens. Defaults to 20.
return_full_text (bool, optional) — Whether to prepend the prompt to the generated text. Defaults to False.
stop (List[str], optional) — Stop generating tokens if a member of stop_sequences is generated. Defaults to an empty list.
seed (Optional[int], optional) — Random sampling seed. Defaults to None.
temperature (Optional[float], optional) — The value used to modulate the logits distribution. Defaults to None.
top_k (Optional[int], optional) — The number of highest probability vocabulary tokens to keep for top-k-filtering. Defaults to None.
top_p (Optional[float], optional) — If set to a value less than 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation. Defaults to None.
truncate (Optional[int], optional) — Truncate input tokens to the given size. Defaults to None.
best_of (Optional[int], optional) — Generate best_of sequences and return the one with the highest token logprobs. Defaults to None.
details (bool, optional) — Get generation details. Defaults to False.
decoder_input_details (bool, optional) — Get decoder input token logprobs and ids. Defaults to False.
Parameters for text generation.
( generated_text: strdetails: typing.Optional[huggingface_hub.inference._text_generation.Details] = None )
Parameters
generated_text (str) — The generated text.
details (Optional[Details]) — Generation details. Returned only if details=True is sent to the server.
Represents a response for text generation.
Only returned when details=True, otherwise a string is returned.
( token: Tokengenerated_text: typing.Optional[str] = Nonedetails: typing.Optional[huggingface_hub.inference._text_generation.StreamDetails] = None )
Parameters
token (Token) — The generated token.
generated_text (Optional[str], optional) — The complete generated text. Only available when the generation is finished.
details (Optional[StreamDetails], optional) — Generation details. Only available when the generation is finished.
Represents a response for streaming text generation.
Only returned when details=True and stream=True.
( id: inttext: strlogprob: typing.Optional[float] = None )
Parameters
id (int) — Token ID from the model tokenizer.
text (str) — Token text.
logprob (float or None) — Log probability of the token. Optional since the logprob of the first token cannot be computed.
Represents an input token.
( id: inttext: strlogprob: floatspecial: bool )
Parameters
id (int) — Token ID from the model tokenizer.
text (str) — Token text.
logprob (float) — Log probability of the token.
special (bool) — Indicates whether the token is a special token. It can be used to ignore tokens when concatenating.
Represents a token.
( valuenames = Nonemodule = Nonequalname = Nonetype = Nonestart = 1 )
An enumeration.
( generated_text: strfinish_reason: FinishReasongenerated_tokens: intseed: typing.Optional[int] = Noneprefill: typing.List[huggingface_hub.inference._text_generation.InputToken] = <factory>tokens: typing.List[huggingface_hub.inference._text_generation.Token] = <factory> )
Parameters
generated_text (str) — The generated text.
finish_reason (FinishReason) — The reason for the generation to finish, represented by a FinishReason value.
generated_tokens (int) — The number of generated tokens in the sequence.
seed (Optional[int]) — The sampling seed if sampling was activated.
prefill (List[InputToken]) — The decoder input tokens. Empty if decoder_input_details is False. Defaults to an empty list.
tokens (List[Token]) — The generated tokens. Defaults to an empty list.
Represents a best-of sequence generated during text generation.
( finish_reason: FinishReasongenerated_tokens: intseed: typing.Optional[int] = Noneprefill: typing.List[huggingface_hub.inference._text_generation.InputToken] = <factory>tokens: typing.List[huggingface_hub.inference._text_generation.Token] = <factory>best_of_sequences: typing.Optional[typing.List[huggingface_hub.inference._text_generation.BestOfSequence]] = None )
Parameters
finish_reason (FinishReason) — The reason for the generation to finish, represented by a FinishReason value.
generated_tokens (int) — The number of generated tokens.
seed (Optional[int]) — The sampling seed if sampling was activated.
prefill (List[InputToken], optional) — The decoder input tokens. Empty if decoder_input_details is False. Defaults to an empty list.
tokens (List[Token]) — The generated tokens. Defaults to an empty list.
best_of_sequences (Optional[List[BestOfSequence]]) — Additional sequences when using the best_of parameter.
Represents details of a text generation.
( finish_reason: FinishReasongenerated_tokens: intseed: typing.Optional[int] = None )
Parameters
finish_reason (FinishReason) — The reason for the generation to finish, represented by a FinishReason value.
generated_tokens (int) — The number of generated tokens.
seed (Optional[int]) — The sampling seed if sampling was activated.
Represents details of a text generation stream.
( repo_id: strtask: typing.Optional[str] = Nonetoken: typing.Optional[str] = Nonegpu: bool = False )
Client to configure requests and make calls to the HuggingFace Inference API.
Example:
Copied
__init__
( repo_id: strtask: typing.Optional[str] = Nonetoken: typing.Optional[str] = Nonegpu: bool = False )
Parameters
repo_id (str) — Id of repository (e.g. user/bert-base-uncased).
task (str, optional, defaults None) — Whether to force a task instead of using task specified in the repository.
gpu (bool, optional, defaults False) — Whether to use GPU instead of CPU for inference(requires Startup plan at least).
Inits headers and API call information.
__call__
( inputs: typing.Union[str, typing.Dict, typing.List[str], typing.List[typing.List[str]], NoneType] = Noneparams: typing.Optional[typing.Dict] = Nonedata: typing.Optional[bytes] = Noneraw_response: bool = False )
Parameters
inputs (str or Dict or List[str] or List[List[str]], optional) — Inputs for the prediction.
params (Dict, optional) — Additional parameters for the models. Will be sent as parameters in the payload.
data (bytes, optional) — Bytes content of the request. In this case, leave inputs and params empty.
raw_response (bool, defaults to False) — If True, the raw Response object is returned. You can parse its content as preferred. By default, the content is parsed into a more practical format (json dictionary or PIL Image for example).
Make a call to the Inference API.
aims to provide a unified experience to perform inference. The client can be used seamlessly with either the (free) Inference API or self-hosted Inference Endpoints.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
parameters (Dict[str, Any], optional) — Additional parameters for the conversational task. Defaults to None. For more details about the available parameters, please refer to
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
model (str, optional) — Identifier of the model for witch the status gonna be checked. If model is not provided, the model associated with this instance of will be used. Only InferenceAPI service can be checked so the identifier cannot be a URL.
This endpoint is mostly useful when you already know which model you want to use and want to check its availability. If you want to discover already deployed models, you should rather use .
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
This endpoint is mostly useful for discoverability. If you already know which model you want to use and want to check its availability, you can directly use .
or HTTPError or ValueError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
parameters (Dict[str, Any], optional) — Additional parameters for summarization. Check out this for more details.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
repetition_penalty (float) — The parameter for repetition penalty. 1.0 means no penalty. See for more details.
typical_p (float) — Typical Decoding mass See for more information
watermark (bool) — Watermarking with
if stream=False and details=True, the generated text is returned with more details as a
if details=True and stream=True, the generated text is returned token by token as a iterable of
ValidationError or or HTTPError
— If the model is unavailable or the request times out.
To learn more about the TGI project, please refer to .
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
Check out for more information on how to choose the best model for your specific use case. Source and target languages usually depends on the model.
or HTTPError
— If the model is unavailable or the request times out.
or HTTPError
— If the model is unavailable or the request times out.
aims to provide a unified experience to perform inference. The client can be used seamlessly with either the (free) Inference API or self-hosted Inference Endpoints.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
parameters (Dict[str, Any], optional) — Additional parameters for the conversational task. Defaults to None. For more details about the available parameters, please refer to
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
model (str, optional) — Identifier of the model for witch the status gonna be checked. If model is not provided, the model associated with this instance of will be used. Only InferenceAPI service can be checked so the identifier cannot be a URL.
This endpoint is mostly useful when you already know which model you want to use and want to check its availability. If you want to discover already deployed models, you should rather use .
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
This endpoint is mostly useful for discoverability. If you already know which model you want to use and want to check its availability, you can directly use .
or aiohttp.ClientResponseError or ValueError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
parameters (Dict[str, Any], optional) — Additional parameters for summarization. Check out this for more details.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
repetition_penalty (float) — The parameter for repetition penalty. 1.0 means no penalty. See for more details.
typical_p (float) — Typical Decoding mass See for more information
watermark (bool) — Watermarking with
if stream=False and details=True, the generated text is returned with more details as a
if details=True and stream=True, the generated text is returned token by token as a iterable of
ValidationError or or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
To learn more about the TGI project, please refer to .
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
Check out for more information on how to choose the best model for your specific use case. Source and target languages usually depends on the model.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
or aiohttp.ClientResponseError
— If the model is unavailable or the request times out.
Dictionary containing the output of a and task.
Dictionary containing the “conversation” part of a task.
Dictionary containing the output of a task.
Dictionary containing information about a task. In practice, image segmentation returns a list of ImageSegmentationOutput with 1 item per mask.
Dictionary containing the output of a task.
task has a greater support than other tasks in InferenceClient. In particular, user inputs and server outputs are validated using if this package is installed. Therefore, we recommend installing it (pip install pydantic) for a better user experience.
You can find below the dataclasses used to validate data and in particular (input), (output) and (streaming output).
repetition_penalty (Optional[float], optional) — The parameter for repetition penalty. A value of 1.0 means no penalty. See for more details. Defaults to None.
typical_p (Optional[float], optional) — Typical Decoding mass. See for more information. Defaults to None.
watermark (bool, optional) — Watermarking with . Defaults to False.
InferenceAPI is the legacy way to call the Inference API. The interface is more simplistic and requires knowing the input parameters and output format for each task. It also lacks the ability to connect to other services like Inference Endpoints or AWS SageMaker. InferenceAPI will soon be deprecated so we recommend using whenever possible. Check out to learn how to switch from InferenceAPI to in your scripts.
token (str, optional) — The API token to use as HTTP bearer authorization. This is not the authentication token. You can find the token in . Alternatively, you can find both your organizations and personal API tokens using HfApi().whoami(token).