>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.audio_classification("audio.flac")
[
    AudioClassificationOutputElement(score=0.4976358711719513, label='hap'),
    AudioClassificationOutputElement(score=0.3677836060523987, label='neu'),
    ...
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> audio_output = client.audio_to_audio("audio.flac")
>>> for i, item in enumerate(audio_output):
>>>     with open(f"output_{i}.flac", "wb") as f:
            f.write(item.blob)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.automatic_speech_recognition("hello_world.flac").text
"hello world"

>>> from huggingface_hub import InferenceClient
>>> messages = [{"role": "user", "content": "What is the capital of France?"}]
>>> client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
>>> client.chat_completion(messages, max_tokens=100)
ChatCompletionOutput(
    choices=[
        ChatCompletionOutputComplete(
            finish_reason='eos_token',
            index=0,
            message=ChatCompletionOutputMessage(
                role='assistant',
                content='The capital of France is Paris.',
                name=None,
                tool_calls=None
            ),
            logprobs=None
        )
    ],
    created=1719907176,
    id='',
    model='meta-llama/Meta-Llama-3-8B-Instruct',
    object='text_completion',
    system_fingerprint='2.0.4-sha-f426a33',
    usage=ChatCompletionOutputUsage(
        completion_tokens=8,
        prompt_tokens=17,
        total_tokens=25
    )
)

>>> from huggingface_hub import InferenceClient
>>> messages = [{"role": "user", "content": "What is the capital of France?"}]
>>> client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
>>> for token in client.chat_completion(messages, max_tokens=10, stream=True):
...     print(token)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content='The', role='assistant'), index=0, finish_reason=None)], created=1710498504)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content=' capital', role='assistant'), index=0, finish_reason=None)], created=1710498504)
(...)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content=' may', role='assistant'), index=0, finish_reason=None)], created=1710498504)

# instead of `from openai import OpenAI`
from huggingface_hub import InferenceClient

# instead of `client = OpenAI(...)`
client = InferenceClient(
    base_url=...,
    api_key=...,
)

output = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Count to 10"},
    ],
    stream=True,
    max_tokens=1024,
)

for chunk in output:
    print(chunk.choices[0].delta.content)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="together",  # Use Together AI provider
...     api_key="<together_api_key>",  # Pass your Together API key directly
... )
>>> client.chat_completion(
...     model="meta-llama/Meta-Llama-3-8B-Instruct",
...     messages=[{"role": "user", "content": "What is the capital of France?"}],
...     extra_body={"safety_model": "Meta-Llama/Llama-Guard-7b"},
... )

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="novita",  # Use Novita provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> client.chat_completion(
...     model="meta-llama/Meta-Llama-3-8B-Instruct",
...     messages=[{"role": "user", "content": "What is the capital of France?"}],
... )

>>> from huggingface_hub import InferenceClient

# provide a remote URL
>>> image_url ="https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
# or a base64-encoded image
>>> image_path = "/path/to/image.jpeg"
>>> with open(image_path, "rb") as f:
...     base64_image = base64.b64encode(f.read()).decode("utf-8")
>>> image_url = f"data:image/jpeg;base64,{base64_image}"

>>> client = InferenceClient("meta-llama/Llama-3.2-11B-Vision-Instruct")
>>> output = client.chat.completions.create(
...     messages=[
...         {
...             "role": "user",
...             "content": [
...                 {
...                     "type": "image_url",
...                     "image_url": {"url": image_url},
...                 },
...                 {
...                     "type": "text",
...                     "text": "Describe this image in one sentence.",
...                 },
...             ],
...         },
...     ],
... )
>>> output
The image depicts the iconic Statue of Liberty situated in New York Harbor, New York, on a clear day.

>>> client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
>>> messages = [
...     {
...         "role": "system",
...         "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.",
...     },
...     {
...         "role": "user",
...         "content": "What's the weather like the next 3 days in San Francisco, CA?",
...     },
... ]
>>> tools = [
...     {
...         "type": "function",
...         "function": {
...             "name": "get_current_weather",
...             "description": "Get the current weather",
...             "parameters": {
...                 "type": "object",
...                 "properties": {
...                     "location": {
...                         "type": "string",
...                         "description": "The city and state, e.g. San Francisco, CA",
...                     },
...                     "format": {
...                         "type": "string",
...                         "enum": ["celsius", "fahrenheit"],
...                         "description": "The temperature unit to use. Infer this from the users location.",
...                     },
...                 },
...                 "required": ["location", "format"],
...             },
...         },
...     },
...     {
...         "type": "function",
...         "function": {
...             "name": "get_n_day_weather_forecast",
...             "description": "Get an N-day weather forecast",
...             "parameters": {
...                 "type": "object",
...                 "properties": {
...                     "location": {
...                         "type": "string",
...                         "description": "The city and state, e.g. San Francisco, CA",
...                     },
...                     "format": {
...                         "type": "string",
...                         "enum": ["celsius", "fahrenheit"],
...                         "description": "The temperature unit to use. Infer this from the users location.",
...                     },
...                     "num_days": {
...                         "type": "integer",
...                         "description": "The number of days to forecast",
...                     },
...                 },
...                 "required": ["location", "format", "num_days"],
...             },
...         },
...     },
... ]

>>> response = client.chat_completion(
...     model="meta-llama/Meta-Llama-3-70B-Instruct",
...     messages=messages,
...     tools=tools,
...     tool_choice="auto",
...     max_tokens=500,
... )
>>> response.choices[0].message.tool_calls[0].function
ChatCompletionOutputFunctionDefinition(
    arguments={
        'location': 'San Francisco, CA',
        'format': 'fahrenheit',
        'num_days': 3
    },
    name='get_n_day_weather_forecast',
    description=None
)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
>>> messages = [
...     {
...         "role": "user",
...         "content": "I saw a puppy a cat and a raccoon during my bike ride in the park. What did I see and when?",
...     },
... ]
>>> response_format = {
...     "type": "json",
...     "value": {
...         "properties": {
...             "location": {"type": "string"},
...             "activity": {"type": "string"},
...             "animals_seen": {"type": "integer", "minimum": 1, "maximum": 5},
...             "animals": {"type": "array", "items": {"type": "string"}},
...         },
...         "required": ["location", "activity", "animals_seen", "animals"],
...     },
... }
>>> response = client.chat_completion(
...     messages=messages,
...     response_format=response_format,
...     max_tokens=500,
... )
>>> response.choices[0].message.content
'{

y": "bike ride",
": ["puppy", "cat", "raccoon"],
_seen": 3,
n": "park"}'

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> 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)]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.feature_extraction("Hi, who are you?")
array([[ 2.424802  ,  2.93384   ,  1.1750331 , ...,  1.240499, -0.13776633, -0.7889173 ],
[-0.42943227, -0.6364878 , -1.693462  , ...,  0.41978157, -2.4336355 ,  0.6162071 ],
...,
[ 0.28552425, -0.928395  , -1.2077185 , ...,  0.76810825, -2.1069427 ,  0.6236161 ]], dtype=float32)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.fill_mask("The goal of life is <mask>.")
[
    FillMaskOutputElement(score=0.06897063553333282, token=11098, token_str=' happiness', sequence='The goal of life is happiness.'),
    FillMaskOutputElement(score=0.06554922461509705, token=45075, token_str=' immortality', sequence='The goal of life is immortality.')
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
>>> client.get_endpoint_info()
{
    'model_id': 'meta-llama/Meta-Llama-3-70B-Instruct',
    'model_sha': None,
    'model_dtype': 'torch.float16',
    'model_device_type': 'cuda',
    'model_pipeline_tag': None,
    'max_concurrent_requests': 128,
    'max_best_of': 2,
    'max_stop_sequences': 4,
    'max_input_length': 8191,
    'max_total_tokens': 8192,
    'waiting_served_ratio': 0.3,
    'max_batch_total_tokens': 1259392,
    'max_waiting_tokens': 20,
    'max_batch_size': None,
    'validation_workers': 32,
    'max_client_batch_size': 4,
    'version': '2.0.2',
    'sha': 'dccab72549635c7eb5ddb17f43f0b7cdff07c214',
    'docker_label': 'sha-dccab72'
}

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient("https://jzgu0buei5.us-east-1.aws.endpoints.huggingface.cloud")
>>> client.health_check()
True

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.image_classification("https://upload.wikimedia.org/wikipedia/commons/thumb/4/43/Cute_dog.jpg/320px-Cute_dog.jpg")
[ImageClassificationOutputElement(label='Blenheim spaniel', score=0.9779096841812134), ...]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.image_segmentation("cat.jpg")
[ImageSegmentationOutputElement(score=0.989008, label='LABEL_184', mask=<PIL.PngImagePlugin.PngImageFile image mode=L size=400x300 at 0x7FDD2B129CC0>), ...]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> image = client.image_to_image("cat.jpg", prompt="turn the cat into a tiger")
>>> image.save("tiger.jpg")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.image_to_text("cat.jpg")
'a cat standing in a grassy field '
>>> client.image_to_text("https://upload.wikimedia.org/wikipedia/commons/thumb/4/43/Cute_dog.jpg/320px-Cute_dog.jpg")
'a dog laying on the grass next to a flower pot '

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> video = client.image_to_video("cat.jpg", model="Wan-AI/Wan2.2-I2V-A14B", prompt="turn the cat into a tiger")
>>> with open("tiger.mp4", "wb") as f:
...     f.write(video)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.object_detection("people.jpg")
[ObjectDetectionOutputElement(score=0.9486683011054993, label='person', box=ObjectDetectionBoundingBox(xmin=59, ymin=39, xmax=420, ymax=510)), ...]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.question_answering(question="What's my name?", context="My name is Clara and I live in Berkeley.")
QuestionAnsweringOutputElement(answer='Clara', end=16, score=0.9326565265655518, start=11)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.sentence_similarity(
...     "Machine learning is so easy.",
...     other_sentences=[
...         "Deep learning is so straightforward.",
...         "This is so difficult, like rocket science.",
...         "I can't believe how much I struggled with this.",
...     ],
... )
[0.7785726189613342, 0.45876261591911316, 0.2906220555305481]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.summarization("The Eiffel tower...")
SummarizationOutput(generated_text="The Eiffel tower is one of the most famous landmarks in the world....")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> query = "How many stars does the transformers repository have?"
>>> table = {"Repository": ["Transformers", "Datasets", "Tokenizers"], "Stars": ["36542", "4512", "3934"]}
>>> client.table_question_answering(table, query, model="google/tapas-base-finetuned-wtq")
TableQuestionAnsweringOutputElement(answer='36542', coordinates=[[0, 1]], cells=['36542'], aggregator='AVERAGE')

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> table = {
...     "fixed_acidity": ["7.4", "7.8", "10.3"],
...     "volatile_acidity": ["0.7", "0.88", "0.32"],
...     "citric_acid": ["0", "0", "0.45"],
...     "residual_sugar": ["1.9", "2.6", "6.4"],
...     "chlorides": ["0.076", "0.098", "0.073"],
...     "free_sulfur_dioxide": ["11", "25", "5"],
...     "total_sulfur_dioxide": ["34", "67", "13"],
...     "density": ["0.9978", "0.9968", "0.9976"],
...     "pH": ["3.51", "3.2", "3.23"],
...     "sulphates": ["0.56", "0.68", "0.82"],
...     "alcohol": ["9.4", "9.8", "12.6"],
... }
>>> client.tabular_classification(table=table, model="julien-c/wine-quality")
["5", "5", "5"]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> table = {
...     "Height": ["11.52", "12.48", "12.3778"],
...     "Length1": ["23.2", "24", "23.9"],
...     "Length2": ["25.4", "26.3", "26.5"],
...     "Length3": ["30", "31.2", "31.1"],
...     "Species": ["Bream", "Bream", "Bream"],
...     "Width": ["4.02", "4.3056", "4.6961"],
... }
>>> client.tabular_regression(table, model="scikit-learn/Fish-Weight")
[110, 120, 130]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.text_classification("I like you")
[
    TextClassificationOutputElement(label='POSITIVE', score=0.9998695850372314),
    TextClassificationOutputElement(label='NEGATIVE', score=0.0001304351753788069),
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()

# Case 1: generate text
>>> client.text_generation("The huggingface_hub library is ", max_new_tokens=12)
'100% open source and built to be easy to use.'

# Case 2: iterate over the generated tokens. Useful for large generation.
>>> for token in client.text_generation("The huggingface_hub library is ", max_new_tokens=12, stream=True):
...     print(token)
100
%
open
source
and
built
to
be
easy
to
use
.

# Case 3: get more details about the generation process.
>>> client.text_generation("The huggingface_hub library is ", max_new_tokens=12, details=True)
TextGenerationOutput(
    generated_text='100% open source and built to be easy to use.',
    details=TextGenerationDetails(
        finish_reason='length',
        generated_tokens=12,
        seed=None,
        prefill=[
            TextGenerationPrefillOutputToken(id=487, text='The', logprob=None),
            TextGenerationPrefillOutputToken(id=53789, text=' hugging', logprob=-13.171875),
            (...)
            TextGenerationPrefillOutputToken(id=204, text=' ', logprob=-7.0390625)
        ],
        tokens=[
            TokenElement(id=1425, text='100', logprob=-1.0175781, special=False),
            TokenElement(id=16, text='%', logprob=-0.0463562, special=False),
            (...)
            TokenElement(id=25, text='.', logprob=-0.5703125, special=False)
        ],
        best_of_sequences=None
    )
)

# Case 4: iterate over the generated tokens with more details.
# Last object is more complete, containing the full generated text and the finish reason.
>>> for details in client.text_generation("The huggingface_hub library is ", max_new_tokens=12, details=True, stream=True):
...     print(details)
...
TextGenerationStreamOutput(token=TokenElement(id=1425, text='100', logprob=-1.0175781, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=16, text='%', logprob=-0.0463562, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=1314, text=' open', logprob=-1.3359375, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=3178, text=' source', logprob=-0.28100586, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=273, text=' and', logprob=-0.5961914, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=3426, text=' built', logprob=-1.9423828, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=271, text=' to', logprob=-1.4121094, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=314, text=' be', logprob=-1.5224609, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=1833, text=' easy', logprob=-2.1132812, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=271, text=' to', logprob=-0.08520508, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(id=745, text=' use', logprob=-0.39453125, special=False), generated_text=None, details=None)
TextGenerationStreamOutput(token=TokenElement(
    id=25,
    text='.',
    logprob=-0.5703125,
    special=False),
    generated_text='100% open source and built to be easy to use.',
    details=TextGenerationStreamOutputStreamDetails(finish_reason='length', generated_tokens=12, seed=None)
)

# Case 5: generate constrained output using grammar
>>> response = client.text_generation(
...     prompt="I saw a puppy a cat and a raccoon during my bike ride in the park",
...     model="HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
...     max_new_tokens=100,
...     repetition_penalty=1.3,
...     grammar={
...         "type": "json",
...         "value": {
...             "properties": {
...                 "location": {"type": "string"},
...                 "activity": {"type": "string"},
...                 "animals_seen": {"type": "integer", "minimum": 1, "maximum": 5},
...                 "animals": {"type": "array", "items": {"type": "string"}},
...             },
...             "required": ["location", "activity", "animals_seen", "animals"],
...         },
...     },
... )
>>> json.loads(response)
{
    "activity": "bike riding",
    "animals": ["puppy", "cat", "raccoon"],
    "animals_seen": 3,
    "location": "park"
}

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()

>>> image = client.text_to_image("An astronaut riding a horse on the moon.")
>>> image.save("astronaut.png")

>>> image = client.text_to_image(
...     "An astronaut riding a horse on the moon.",
...     negative_prompt="low resolution, blurry",
...     model="stabilityai/stable-diffusion-2-1",
... )
>>> image.save("better_astronaut.png")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="fal-ai",  # Use fal.ai provider
...     api_key="fal-ai-api-key",  # Pass your fal.ai API key
... )
>>> image = client.text_to_image(
...     "A majestic lion in a fantasy forest",
...     model="black-forest-labs/FLUX.1-schnell",
... )
>>> image.save("lion.png")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",  # Use replicate provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> image = client.text_to_image(
...     "An astronaut riding a horse on the moon.",
...     model="black-forest-labs/FLUX.1-dev",
... )
>>> image.save("astronaut.png")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",  # Use replicate provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> image = client.text_to_image(
...     "An astronaut riding a horse on the moon.",
...     model="black-forest-labs/FLUX.1-schnell",
...     extra_body={"output_quality": 100},
... )
>>> image.save("astronaut.png")

>>> from pathlib import Path
>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()

>>> audio = client.text_to_speech("Hello world")
>>> Path("hello_world.flac").write_bytes(audio)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",
...     api_key="your-replicate-api-key",  # Pass your Replicate API key directly
... )
>>> audio = client.text_to_speech(
...     text="Hello world",
...     model="OuteAI/OuteTTS-0.3-500M",
... )
>>> Path("hello_world.flac").write_bytes(audio)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",
...     api_key="hf_...",  # Pass your HF token
... )
>>> audio =client.text_to_speech(
...     text="Hello world",
...     model="OuteAI/OuteTTS-0.3-500M",
... )
>>> Path("hello_world.flac").write_bytes(audio)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",  # Use replicate provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> audio = client.text_to_speech(
...     "Hello, my name is Kororo, an awesome text-to-speech model.",
...     model="hexgrad/Kokoro-82M",
...     extra_body={"voice": "af_nicole"},
... )
>>> Path("hello.flac").write_bytes(audio)

>>> from huggingface_hub import InferenceClient
>>> lyrics = '''
... [verse]
... In the town where I was born
... Lived a man who sailed to sea
... And he told us of his life
... In the land of submarines
... So we sailed on to the sun
... 'Til we found a sea of green
... And we lived beneath the waves
... In our yellow submarine

... [chorus]
... We all live in a yellow submarine
... Yellow submarine, yellow submarine
... We all live in a yellow submarine
... Yellow submarine, yellow submarine
... '''
>>> genres = "pavarotti-style tenor voice"
>>> client = InferenceClient(
...     provider="fal-ai",
...     model="m-a-p/YuE-s1-7B-anneal-en-cot",
...     api_key=...,
... )
>>> audio = client.text_to_speech(lyrics, extra_body={"genres": genres})
>>> with open("output.mp3", "wb") as f:
...     f.write(audio)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="fal-ai",  # Using fal.ai provider
...     api_key="fal-ai-api-key",  # Pass your fal.ai API key
... )
>>> video = client.text_to_video(
...     "A majestic lion running in a fantasy forest",
...     model="tencent/HunyuanVideo",
... )
>>> with open("lion.mp4", "wb") as file:
...     file.write(video)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="replicate",  # Using replicate provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> video = client.text_to_video(
...     "A cat running in a park",
...     model="genmo/mochi-1-preview",
... )
>>> with open("cat.mp4", "wb") as file:
...     file.write(video)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.token_classification("My name is Sarah Jessica Parker but you can call me Jessica")
[
    TokenClassificationOutputElement(
        entity_group='PER',
        score=0.9971321225166321,
        word='Sarah Jessica Parker',
        start=11,
        end=31,
    ),
    TokenClassificationOutputElement(
        entity_group='PER',
        score=0.9773476123809814,
        word='Jessica',
        start=52,
        end=59,
    )
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.translation("My name is Wolfgang and I live in Berlin")
'Mein Name ist Wolfgang und ich lebe in Berlin.'
>>> 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.')

>>> 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"

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.visual_question_answering(
...     image="https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg",
...     question="What is the animal doing?"
... )
[
    VisualQuestionAnsweringOutputElement(score=0.778609573841095, answer='laying down'),
    VisualQuestionAnsweringOutputElement(score=0.6957435607910156, answer='sitting'),
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> text = (
...     "A new model offers an explanation for how the Galilean satellites formed around the solar system's"
...     "largest world. Konstantin Batygin did not set out to solve one of the solar system's most puzzling"
...     " mysteries when he went for a run up a hill in Nice, France."
... )
>>> labels = ["space & cosmos", "scientific discovery", "microbiology", "robots", "archeology"]
>>> client.zero_shot_classification(text, labels)
[
    ZeroShotClassificationOutputElement(label='scientific discovery', score=0.7961668968200684),
    ZeroShotClassificationOutputElement(label='space & cosmos', score=0.18570658564567566),
    ZeroShotClassificationOutputElement(label='microbiology', score=0.00730885099619627),
    ZeroShotClassificationOutputElement(label='archeology', score=0.006258360575884581),
    ZeroShotClassificationOutputElement(label='robots', score=0.004559356719255447),
]
>>> client.zero_shot_classification(text, labels, multi_label=True)
[
    ZeroShotClassificationOutputElement(label='scientific discovery', score=0.9829297661781311),
    ZeroShotClassificationOutputElement(label='space & cosmos', score=0.755190908908844),
    ZeroShotClassificationOutputElement(label='microbiology', score=0.0005462635890580714),
    ZeroShotClassificationOutputElement(label='archeology', score=0.00047131875180639327),
    ZeroShotClassificationOutputElement(label='robots', score=0.00030448526376858354),
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> client.zero_shot_classification(
...    text="I really like our dinner and I'm very happy. I don't like the weather though.",
...    candidate_labels=["positive", "negative", "pessimistic", "optimistic"],
...    multi_label=True,
...    hypothesis_template="This text is {} towards the weather"
... )
[
    ZeroShotClassificationOutputElement(label='negative', score=0.9231801629066467),
    ZeroShotClassificationOutputElement(label='pessimistic', score=0.8760990500450134),
    ZeroShotClassificationOutputElement(label='optimistic', score=0.0008674879791215062),
    ZeroShotClassificationOutputElement(label='positive', score=0.0005250611575320363)
]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()

>>> client.zero_shot_image_classification(
...     "https://upload.wikimedia.org/wikipedia/commons/thumb/4/43/Cute_dog.jpg/320px-Cute_dog.jpg",
...     candidate_labels=["dog", "cat", "horse"],
... )
[ZeroShotImageClassificationOutputElement(label='dog', score=0.956),...]

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> client = AsyncInferenceClient()
>>> await client.audio_classification("audio.flac")
[
    AudioClassificationOutputElement(score=0.4976358711719513, label='hap'),
    AudioClassificationOutputElement(score=0.3677836060523987, label='neu'),
    ...
]

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> client = AsyncInferenceClient()
>>> audio_output = await client.audio_to_audio("audio.flac")
>>> async for i, item in enumerate(audio_output):
>>>     with open(f"output_{i}.flac", "wb") as f:
            f.write(item.blob)

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> client = AsyncInferenceClient()
>>> await client.automatic_speech_recognition("hello_world.flac").text
"hello world"

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> messages = [{"role": "user", "content": "What is the capital of France?"}]
>>> client = AsyncInferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
>>> await client.chat_completion(messages, max_tokens=100)
ChatCompletionOutput(
    choices=[
        ChatCompletionOutputComplete(
            finish_reason='eos_token',
            index=0,
            message=ChatCompletionOutputMessage(
                role='assistant',
                content='The capital of France is Paris.',
                name=None,
                tool_calls=None
            ),
            logprobs=None
        )
    ],
    created=1719907176,
    id='',
    model='meta-llama/Meta-Llama-3-8B-Instruct',
    object='text_completion',
    system_fingerprint='2.0.4-sha-f426a33',
    usage=ChatCompletionOutputUsage(
        completion_tokens=8,
        prompt_tokens=17,
        total_tokens=25
    )
)

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> messages = [{"role": "user", "content": "What is the capital of France?"}]
>>> client = AsyncInferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
>>> async for token in await client.chat_completion(messages, max_tokens=10, stream=True):
...     print(token)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content='The', role='assistant'), index=0, finish_reason=None)], created=1710498504)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content=' capital', role='assistant'), index=0, finish_reason=None)], created=1710498504)
(...)
ChatCompletionStreamOutput(choices=[ChatCompletionStreamOutputChoice(delta=ChatCompletionStreamOutputDelta(content=' may', role='assistant'), index=0, finish_reason=None)], created=1710498504)

# Must be run in an async context
# instead of `from openai import OpenAI`
from huggingface_hub import AsyncInferenceClient

# instead of `client = OpenAI(...)`
client = AsyncInferenceClient(
    base_url=...,
    api_key=...,
)

output = await client.chat.completions.create(
    model="meta-llama/Meta-Llama-3-8B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Count to 10"},
    ],
    stream=True,
    max_tokens=1024,
)

for chunk in output:
    print(chunk.choices[0].delta.content)

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="together",  # Use Together AI provider
...     api_key="<together_api_key>",  # Pass your Together API key directly
... )
>>> client.chat_completion(
...     model="meta-llama/Meta-Llama-3-8B-Instruct",
...     messages=[{"role": "user", "content": "What is the capital of France?"}],
...     extra_body={"safety_model": "Meta-Llama/Llama-Guard-7b"},
... )

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(
...     provider="novita",  # Use Novita provider
...     api_key="hf_...",  # Pass your HF token
... )
>>> client.chat_completion(
...     model="meta-llama/Meta-Llama-3-8B-Instruct",
...     messages=[{"role": "user", "content": "What is the capital of France?"}],
... )

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient

# provide a remote URL
>>> image_url ="https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
# or a base64-encoded image
>>> image_path = "/path/to/image.jpeg"
>>> with open(image_path, "rb") as f:
...     base64_image = base64.b64encode(f.read()).decode("utf-8")
>>> image_url = f"data:image/jpeg;base64,{base64_image}"

>>> client = AsyncInferenceClient("meta-llama/Llama-3.2-11B-Vision-Instruct")
>>> output = await client.chat.completions.create(
...     messages=[
...         {
...             "role": "user",
...             "content": [
...                 {
...                     "type": "image_url",
...                     "image_url": {"url": image_url},
...                 },
...                 {
...                     "type": "text",
...                     "text": "Describe this image in one sentence.",
...                 },
...             ],
...         },
...     ],
... )
>>> output
The image depicts the iconic Statue of Liberty situated in New York Harbor, New York, on a clear day.

# Must be run in an async context
>>> client = AsyncInferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
>>> messages = [
...     {
...         "role": "system",
...         "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.",
...     },
...     {
...         "role": "user",
...         "content": "What's the weather like the next 3 days in San Francisco, CA?",
...     },
... ]
>>> tools = [
...     {
...         "type": "function",
...         "function": {
...             "name": "get_current_weather",
...             "description": "Get the current weather",
...             "parameters": {
...                 "type": "object",
...                 "properties": {
...                     "location": {
...                         "type": "string",
...                         "description": "The city and state, e.g. San Francisco, CA",
...                     },
...                     "format": {
...                         "type": "string",
...                         "enum": ["celsius", "fahrenheit"],
...                         "description": "The temperature unit to use. Infer this from the users location.",
...                     },
...                 },
...                 "required": ["location", "format"],
...             },
...         },
...     },
...     {
...         "type": "function",
...         "function": {
...             "name": "get_n_day_weather_forecast",
...             "description": "Get an N-day weather forecast",
...             "parameters": {
...                 "type": "object",
...                 "properties": {
...                     "location": {
...                         "type": "string",
...                         "description": "The city and state, e.g. San Francisco, CA",
...                     },
...                     "format": {
...                         "type": "string",
...                         "enum": ["celsius", "fahrenheit"],
...                         "description": "The temperature unit to use. Infer this from the users location.",
...                     },
...                     "num_days": {
...                         "type": "integer",
...                         "description": "The number of days to forecast",
...                     },
...                 },
...                 "required": ["location", "format", "num_days"],
...             },
...         },
...     },
... ]

>>> response = await client.chat_completion(
...     model="meta-llama/Meta-Llama-3-70B-Instruct",
...     messages=messages,
...     tools=tools,
...     tool_choice="auto",
...     max_tokens=500,
... )
>>> response.choices[0].message.tool_calls[0].function
ChatCompletionOutputFunctionDefinition(
    arguments={
        'location': 'San Francisco, CA',
        'format': 'fahrenheit',
        'num_days': 3
    },
    name='get_n_day_weather_forecast',
    description=None
)

# Must be run in an async context
>>> from huggingface_hub import AsyncInferenceClient
>>> client = AsyncInferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
>>> messages = [
...     {
...         "role": "user",
...         "content": "I saw a puppy a cat and a raccoon during my bike ride in the park. What did I see and when?",
...     },
... ]
>>> response_format = {
...     "type": "json",
...     "value": {
...         "properties": {
...             "location": {"type": "string"},
...             "activity": {"type": "string"},
...             "animals_seen": {"type": "integer", "minimum": 1, "maximum": 5},
...             "animals": {"type": "array", "items": {"type": "string"}},
...         },
...         "required": ["location", "activity", "animals_seen", "animals"],
...     },
... }
>>> response = await client.chat_completion(
...     messages=messages,
...     response_format=response_format,
...     max_tokens=500,
... )
>>> response.choices[0].message.content
'{

y": "bike ride",
": ["puppy", "cat", "raccoon"],
_seen": 3,
n": "park"}'