Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / 101-course /pr_4 /en /chapter2 /2.html
rtrm's picture
rtrm
download
raw
34 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Inference Providers&quot;,&quot;local&quot;:&quot;inference-providers&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Key ideas&quot;,&quot;local&quot;:&quot;key-ideas&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Quickstart (Python)&quot;,&quot;local&quot;:&quot;quickstart-python&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Authentication&quot;,&quot;local&quot;:&quot;authentication&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;cURL example&quot;,&quot;local&quot;:&quot;curl-example&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Your first API call (Text-to-Image)&quot;,&quot;local&quot;:&quot;your-first-api-call-text-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Streaming&quot;,&quot;local&quot;:&quot;streaming&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Provider selection&quot;,&quot;local&quot;:&quot;provider-selection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Error handling and timeouts&quot;,&quot;local&quot;:&quot;error-handling-and-timeouts&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/101-course/pr_4/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/entry/start.b6742992.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/scheduler.1d51f4c0.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/singletons.023d1c68.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/index.fa8592cf.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/paths.daa2f795.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/entry/app.8b986792.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/index.fda43871.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/nodes/0.b5fb3b56.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/nodes/11.9bd6edcb.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/Tip.e808fe4c.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/CodeBlock.16130beb.js">
 <link rel="modulepreload" href="/docs/101-course/pr_4/en/_app/immutable/chunks/getInferenceSnippets.58a43ad0.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Inference Providers&quot;,&quot;local&quot;:&quot;inference-providers&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Key ideas&quot;,&quot;local&quot;:&quot;key-ideas&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Quickstart (Python)&quot;,&quot;local&quot;:&quot;quickstart-python&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Authentication&quot;,&quot;local&quot;:&quot;authentication&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;cURL example&quot;,&quot;local&quot;:&quot;curl-example&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Your first API call (Text-to-Image)&quot;,&quot;local&quot;:&quot;your-first-api-call-text-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Streaming&quot;,&quot;local&quot;:&quot;streaming&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Provider selection&quot;,&quot;local&quot;:&quot;provider-selection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Error handling and timeouts&quot;,&quot;local&quot;:&quot;error-handling-and-timeouts&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="inference-providers" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#inference-providers"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Inference Providers</span></h1> <p data-svelte-h="svelte-taitlg">Inference Providers are a simple, hosted way to run models via API without deploying infrastructure. You can route requests automatically to an available provider or choose a specific provider for a model.</p> <p data-svelte-h="svelte-pxppmp">In this unit you’ll learn the basics, make a first call, and then build a small app. Keep an eye on the Tips — they highlight common gotchas and best practices.</p> <h2 class="relative group"><a id="key-ideas" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#key-ideas"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Key ideas</span></h2> <ul data-svelte-h="svelte-91m7iu"><li>One client, many models: call text, image, and audio models with consistent APIs</li> <li>Automatic or explicit provider selection</li> <li>Streaming support for token-by-token generation</li> <li>Simple auth using your Hugging Face token</li></ul> <h2 class="relative group"><a id="quickstart-python" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#quickstart-python"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Quickstart (Python)</span></h2> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> InferenceClient
<span class="hljs-comment"># Create a client. By default, it will auto-pick a provider.</span>
client = InferenceClient()
<span class="hljs-comment"># Text generation</span>
response = client.text_generation(
 <span class="hljs-string">&quot;Write a short poem about the ocean.&quot;</span>,
 model=<span class="hljs-string">&quot;gpt2&quot;</span>, <span class="hljs-comment"># replace with a model you want to try</span>
)
<span class="hljs-built_in">print</span>(response)
<span class="hljs-comment"># Image generation (example)</span>
<span class="hljs-comment"># img_bytes = client.image_generation(</span>
<span class="hljs-comment"># prompt=&quot;a watercolor painting of a lighthouse at dawn&quot;,</span>
<span class="hljs-comment"># model=&quot;stabilityai/stable-diffusion-2&quot;,</span>
<span class="hljs-comment"># )</span>
<span class="hljs-comment"># with open(&quot;output.png&quot;, &quot;wb&quot;) as f:</span>
<span class="hljs-comment"># f.write(img_bytes)</span><!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1kqoya8">To prefer a specific provider, pass <code>provider=&quot;...&quot;</code> to your call (or when constructing the client). When in doubt, keep <code>provider=&quot;auto&quot;</code> to use the first available provider based on your preferences.</p></div> <h2 class="relative group"><a id="authentication" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#authentication"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Authentication</span></h2> <p data-svelte-h="svelte-uwz26h"><code>InferenceClient</code> reads your token from the <code>HF_TOKEN</code> environment variable or you can pass <code>token</code> explicitly:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> InferenceClient
client = InferenceClient(token=<span class="hljs-string">&quot;hf_xxx&quot;</span>)
<span class="hljs-built_in">print</span>(client.text_generation(<span class="hljs-string">&quot;Hello!&quot;</span>, model=<span class="hljs-string">&quot;gpt2&quot;</span>))<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="curl-example" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#curl-example"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>cURL example</span></h2> <p data-svelte-h="svelte-72macm">You can also call the Inference API directly with cURL:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->curl -X POST \
 -H <span class="hljs-string">&quot;Authorization: Bearer <span class="hljs-variable">$HF_TOKEN</span>&quot;</span> \
 -H <span class="hljs-string">&quot;Content-Type: application/json&quot;</span> \
 -d <span class="hljs-string">&#x27;{&quot;inputs&quot;: &quot;Write a haiku about the sea&quot;}&#x27;</span> \
 https://api-inference.huggingface.co/models/gpt2<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="your-first-api-call-text-to-image" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#your-first-api-call-text-to-image"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Your first API call (Text-to-Image)</span></h2> <p data-svelte-h="svelte-1jfako">Before coding, pick a model on the Hub with Inference Providers enabled and try the right-side widget. Then replicate the request in code.</p> <p data-svelte-h="svelte-1t6kqw0">Python:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> os
<span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> InferenceClient
client = InferenceClient(
 provider=<span class="hljs-string">&quot;auto&quot;</span>,
 api_key=os.environ[<span class="hljs-string">&quot;HF_TOKEN&quot;</span>],
)
<span class="hljs-comment"># Returns a PIL.Image</span>
image = client.text_to_image(
 <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 model=<span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
)
image.save(<span class="hljs-string">&quot;image.png&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1sc380f">TypeScript:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">InferenceClient</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&quot;@huggingface/inference&quot;</span>;
<span class="hljs-keyword">const</span> client = <span class="hljs-keyword">new</span> <span class="hljs-title class_">InferenceClient</span>(process.<span class="hljs-property">env</span>.<span class="hljs-property">HF_TOKEN</span>);
<span class="hljs-keyword">const</span> image = <span class="hljs-keyword">await</span> client.<span class="hljs-title function_">textToImage</span>({
 <span class="hljs-attr">provider</span>: <span class="hljs-string">&quot;auto&quot;</span>,
 <span class="hljs-attr">model</span>: <span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
 <span class="hljs-attr">inputs</span>: <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 <span class="hljs-attr">parameters</span>: { <span class="hljs-attr">num_inference_steps</span>: <span class="hljs-number">5</span> },
});
<span class="hljs-comment">// image is a Blob</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="streaming" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#streaming"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Streaming</span></h2> <p data-svelte-h="svelte-1h3fuab">For long generations, stream tokens as they arrive:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> InferenceClient
client = InferenceClient()
<span class="hljs-keyword">for</span> chunk <span class="hljs-keyword">in</span> client.text_generation(
 <span class="hljs-string">&quot;Explain transformers in 2 sentences.&quot;</span>,
 model=<span class="hljs-string">&quot;gpt2&quot;</span>,
 stream=<span class="hljs-literal">True</span>,
):
 <span class="hljs-built_in">print</span>(chunk, end=<span class="hljs-string">&quot;&quot;</span>, flush=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="provider-selection" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#provider-selection"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Provider selection</span></h2> <p data-svelte-h="svelte-n27pyw"><code>provider=&quot;auto&quot;</code> is the default and tries providers in your preference order with failover. You can also pin a specific provider.</p> <p data-svelte-h="svelte-1t6kqw0">Python:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> InferenceClient
client = InferenceClient()
<span class="hljs-comment"># Auto selection (default)</span>
img_auto = client.text_to_image(
 <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 model=<span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
 provider=<span class="hljs-string">&quot;auto&quot;</span>,
)
<span class="hljs-comment"># Explicit provider</span>
img_fal = client.text_to_image(
 <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 model=<span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
 provider=<span class="hljs-string">&quot;fal-ai&quot;</span>,
)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1sc380f">TypeScript:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">InferenceClient</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&quot;@huggingface/inference&quot;</span>;
<span class="hljs-keyword">const</span> client = <span class="hljs-keyword">new</span> <span class="hljs-title class_">InferenceClient</span>(process.<span class="hljs-property">env</span>.<span class="hljs-property">HF_TOKEN</span>);
<span class="hljs-keyword">const</span> imageAuto = <span class="hljs-keyword">await</span> client.<span class="hljs-title function_">textToImage</span>({
 <span class="hljs-attr">model</span>: <span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
 <span class="hljs-attr">inputs</span>: <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 <span class="hljs-attr">provider</span>: <span class="hljs-string">&quot;auto&quot;</span>,
 <span class="hljs-attr">parameters</span>: { <span class="hljs-attr">num_inference_steps</span>: <span class="hljs-number">5</span> },
});
<span class="hljs-keyword">const</span> imageFal = <span class="hljs-keyword">await</span> client.<span class="hljs-title function_">textToImage</span>({
 <span class="hljs-attr">model</span>: <span class="hljs-string">&quot;black-forest-labs/FLUX.1-schnell&quot;</span>,
 <span class="hljs-attr">inputs</span>: <span class="hljs-string">&quot;Astronaut riding a horse&quot;</span>,
 <span class="hljs-attr">provider</span>: <span class="hljs-string">&quot;fal-ai&quot;</span>,
 <span class="hljs-attr">parameters</span>: { <span class="hljs-attr">num_inference_steps</span>: <span class="hljs-number">5</span> },
});<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="error-handling-and-timeouts" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#error-handling-and-timeouts"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Error handling and timeouts</span></h2> <ul data-svelte-h="svelte-12ogqg9"><li>Set timeouts when creating the client (e.g., <code>InferenceClient(timeout=60)</code>).</li> <li>Catch HTTP errors (e.g., invalid model, rate limits) and retry when appropriate.</li></ul> <p data-svelte-h="svelte-1hqr58t">You’re ready to build an app with providers—let’s do that next.</p> <p data-svelte-h="svelte-1n0ekh8">Up next: build your first AI app using Providers (transcribe + summarize).</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/101-course/blob/main/chapters/en/chapter2/2.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_kib1ob = {
 assets: "/docs/101-course/pr_4/en",
 base: "/docs/101-course/pr_4/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/101-course/pr_4/en/_app/immutable/entry/start.b6742992.js"),
 import("/docs/101-course/pr_4/en/_app/immutable/entry/app.8b986792.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 11],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
34 kB
·
Xet hash:
4f1a33e51f54145cb2feff933ddf32959b4ad142ec86f498138b25301a4defbd

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.