>>> 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' is a PIL.Image object

>>> 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
# Initialize client for a specific model
>>> client = InferenceClient(model="prompthero/openjourney-v4")
>>> client.text_to_image(...)
# Or use a generic client but pass your model as an argument
>>> client = InferenceClient()
>>> client.text_to_image(..., model="prompthero/openjourney-v4")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(model="https://uu149rez6gw9ehej.eu-west-1.aws.endpoints.huggingface.cloud/deepfloyd-if")
# or
>>> client = InferenceClient()
>>> client.text_to_image(..., model="https://uu149rez6gw9ehej.eu-west-1.aws.endpoints.huggingface.cloud/deepfloyd-if")

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient(token="hf_***")

- from openai import OpenAI
+ from huggingface_hub import InferenceClient

- 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)

import asyncio
- from openai import AsyncOpenAI
+ from huggingface_hub import AsyncInferenceClient

- client = AsyncOpenAI()
+ client = AsyncInferenceClient()

async def main():
    stream = await client.chat.completions.create(
        model="meta-llama/Meta-Llama-3-8B-Instruct",
        messages=[{"role": "user", "content": "Say this is a test"}],
        stream=True,
    )
    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="")

asyncio.run(main())

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> response = client.post(json={"inputs": "An astronaut riding a horse on the moon."}, model="stabilityai/stable-diffusion-2-1")
>>> response.content # raw bytes
b'...'

pip install --upgrade huggingface_hub[inference]
# or
# pip install aiohttp

# Code must be run in a asyncio concurrent context.
# $ python -m asyncio
>>> from huggingface_hub import AsyncInferenceClient
>>> client = AsyncInferenceClient()

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

>>> async for token in await client.text_generation("The Huggingface Hub is", stream=True):
...     print(token, end="")
 a platform for sharing and discussing ML-related content.

>>> from huggingface_hub import InferenceClient, InferenceTimeoutError
>>> client = InferenceClient(timeout=30)
>>> try:
...     client.text_to_image(...)
... except InferenceTimeoutError:
...     print("Inference timed out after 30s.")

>>> 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")
[{'score': 0.9779096841812134, 'label': 'Blenheim spaniel'}, ...]

>>> from huggingface_hub import InferenceApi
>>> inference = InferenceApi(repo_id="bert-base-uncased", token=API_TOKEN)

>>> from huggingface_hub import InferenceClient
>>> inference = InferenceClient(model="bert-base-uncased", token=API_TOKEN)

>>> from huggingface_hub import InferenceApi
>>> inference = InferenceApi(repo_id="paraphrase-xlm-r-multilingual-v1", task="feature-extraction")
>>> inference(...)

>>> from huggingface_hub import InferenceClient
>>> inference = InferenceClient()
>>> inference.feature_extraction(..., model="paraphrase-xlm-r-multilingual-v1")

>>> from huggingface_hub import InferenceApi
>>> inference = InferenceApi(repo_id="bert-base-uncased")
>>> inference(inputs="The goal of life is [MASK].")
[{'sequence': 'the goal of life is life.', 'score': 0.10933292657136917, 'token': 2166, 'token_str': 'life'}]

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> response = client.post(json={"inputs": "The goal of life is [MASK]."}, model="bert-base-uncased")
>>> response.json()
[{'sequence': 'the goal of life is life.', 'score': 0.10933292657136917, 'token': 2166, 'token_str': 'life'}]

>>> from huggingface_hub import InferenceApi
>>> inference = InferenceApi(repo_id="typeform/distilbert-base-uncased-mnli")
>>> inputs = "Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!"
>>> params = {"candidate_labels":["refund", "legal", "faq"]}
>>> inference(inputs, params)
{'sequence': 'Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!', 'labels': ['refund', 'faq', 'legal'], 'scores': [0.9378499388694763, 0.04914155602455139, 0.013008488342165947]}

>>> from huggingface_hub import InferenceClient
>>> client = InferenceClient()
>>> inputs = "Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!"
>>> params = {"candidate_labels":["refund", "legal", "faq"]}
>>> response = client.post(json={"inputs": inputs, "parameters": params}, model="typeform/distilbert-base-uncased-mnli")
>>> response.json()
{'sequence': 'Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!', 'labels': ['refund', 'faq', 'legal'], 'scores': [0.9378499388694763, 0.04914155602455139, 0.013008488342165947]}