inference-endpoints/pr_113/en/guides/test_endpoint.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Send Requests to Endpoints&quot;,&quot;local&quot;:&quot;send-requests-to-endpoints&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Use the UI to send requests&quot;,&quot;local&quot;:&quot;use-the-ui-to-send-requests&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Use cURL to send requests&quot;,&quot;local&quot;:&quot;use-curl-to-send-requests&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Use javascript library @huggingface/inference&quot;,&quot;local&quot;:&quot;use-javascript-library-huggingfaceinference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Custom handler&quot;,&quot;local&quot;:&quot;custom-handler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/inference-endpoints/pr_113/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/entry/start.d1c14968.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/scheduler.389d799c.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/singletons.16c9b508.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/paths.58d119e0.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/entry/app.18050d92.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/index.8f81d18f.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/nodes/0.ce016c16.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/nodes/18.a41e89d1.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/CodeBlock.c0898180.js">
		<link rel="modulepreload" href="/docs/inference-endpoints/pr_113/en/_app/immutable/chunks/getInferenceSnippets.8efa8e08.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Send Requests to Endpoints&quot;,&quot;local&quot;:&quot;send-requests-to-endpoints&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Use the UI to send requests&quot;,&quot;local&quot;:&quot;use-the-ui-to-send-requests&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Use cURL to send requests&quot;,&quot;local&quot;:&quot;use-curl-to-send-requests&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Use javascript library @huggingface/inference&quot;,&quot;local&quot;:&quot;use-javascript-library-huggingfaceinference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Custom handler&quot;,&quot;local&quot;:&quot;custom-handler&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="send-requests-to-endpoints" 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="#send-requests-to-endpoints"><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>Send Requests to Endpoints</span></h1> <p data-svelte-h="svelte-85u5h2">You can send requests to Inference Endpoints using the UI leveraging the Inference Widget or programmatically, e.g. with cURL, <code>@huggingface/inference</code>, <code>huggingface_hub</code> or any REST client. The Endpoint overview not only provides a interactive widget for you to test the Endpoint, but also generates code for <code>python</code>, <code>javascript</code> and <code>curl</code>. You can use this code to quickly get started with your Endpoint in your favorite programming language.</p> <p data-svelte-h="svelte-zcsaap">Below are also examples on how to use the <code>@huggingface/inference</code> library to call an inference endpoint.</p>  <h2 class="relative group"><a id="use-the-ui-to-send-requests" 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="#use-the-ui-to-send-requests"><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>Use the UI to send requests</span></h2> <p data-svelte-h="svelte-m5tjmz">The Endpoint overview provides access to the Inference Widget which can be used to send requests (see step 6 of <a href="/docs/inference-endpoints/guides/create_endpoint">Create an Endpoint</a>). This allows you to quickly test your Endpoint with different inputs and share it with team members.</p>  <h2 class="relative group"><a id="use-curl-to-send-requests" 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="#use-curl-to-send-requests"><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>Use cURL to send requests</span></h2> <p data-svelte-h="svelte-19dwlhh">The cURL command for the request above should look like this. You’ll need to provide your user token which can be found in your Hugging Face <a href="https://huggingface.co/settings/tokens" rel="nofollow">account settings</a>:</p> <p data-svelte-h="svelte-24u3dd">Example Request:</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 https://uu149rez6gw9ehej.eu-west-1.aws.endpoints.huggingface.cloud/distilbert-sentiment \
	-X POST \
	-d <span class="hljs-string">&#x27;{&quot;inputs&quot;: &quot;Deploying my first endpoint was an amazing experience.&quot;}&#x27;</span> \
	-H <span class="hljs-string">&quot;Authorization: Bearer &lt;Token&gt;&quot;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17axk1j">The Endpoints API offers the same API definitions as the <a href="https://huggingface.co/docs/api-inference/detailed_parameters" rel="nofollow">Inference API</a> and the <a href="https://huggingface.co/docs/sagemaker/reference#inference-toolkit-api" rel="nofollow">SageMaker Inference Toolkit</a>. All the request payloads are documented in the <a href="/docs/inference-endpoints/supported_tasks">Supported Tasks</a> section.</p> <p data-svelte-h="svelte-1dl9skp">This means for an NLP task, the payload is represented as the <code>inputs</code> key and additional pipeline parameters are included in the <code>parameters</code> key. You can provide any of the supported <code>kwargs</code> from <a href="https://huggingface.co/docs/transformers/main_classes/pipelines" rel="nofollow">pipelines</a> as parameters.
For image or audio tasks, you should send the data as a binary request with the corresponding mime type. Below is an example cURL for an audio payload:</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 --request POST \
  --url https://uu149rez6gw9ehej.eu-west-1.aws.endpoints.huggingface.cloud/wav2vec-asr \
  --header <span class="hljs-string">&#x27;Authorization: Bearer &lt;Token&gt;&#x27;</span> \
  --header <span class="hljs-string">&#x27;Content-Type: audio/x-flac&#x27;</span> \
  --data-binary <span class="hljs-string">&#x27;@sample1.flac&#x27;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-iadl06">To use your cURL command as code, use the <a href="https://curlconverter.com/" rel="nofollow">cURL Converter</a> tool to quickly get started with the programming language of your choice.</p>  <h2 class="relative group"><a id="use-javascript-library-huggingfaceinference" 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="#use-javascript-library-huggingfaceinference"><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>Use javascript library @huggingface/inference</span></h2> <p data-svelte-h="svelte-1uhxmqh">You can use the javascript library to call an inference endpoint:</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">const</span> inference = <span class="hljs-keyword">new</span> <span class="hljs-title class_">HfInference</span>(<span class="hljs-string">&#x27;hf_...&#x27;</span>) <span class="hljs-comment">// your user token</span>

<span class="hljs-keyword">const</span> gpt2 = inference.<span class="hljs-title function_">endpoint</span>(<span class="hljs-string">&#x27;https://xyz.eu-west-1.aws.endpoints.huggingface.cloud/gpt2-endpoint&#x27;</span>)
<span class="hljs-keyword">const</span> { generated_text } = <span class="hljs-keyword">await</span> gpt2.<span class="hljs-title function_">textGeneration</span>({ <span class="hljs-attr">inputs</span>: <span class="hljs-string">&#x27;The answer to the universe is&#x27;</span> })<!-- HTML_TAG_END --></pre></div>  <h3 class="relative group"><a id="custom-handler" 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="#custom-handler"><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>Custom handler</span></h3> <p data-svelte-h="svelte-1sne8k4"><code>@huggingface/inference</code> supports tasks from <a href="https://huggingface.co/tasks" rel="nofollow">https://huggingface.co/tasks</a>, and is typed accordingly.</p> <p data-svelte-h="svelte-143o5w7">If your model has additional inputs, or even custom inputs / outputs you can use the more generic <code>.request</code> / <code>streamingRequest</code>:</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">const</span> output = <span class="hljs-keyword">await</span> inference.<span class="hljs-title function_">request</span>({
  <span class="hljs-attr">inputs</span>: <span class="hljs-string">&quot;blablabla&quot;</span>,
  <span class="hljs-attr">parameters</span>: {
    <span class="hljs-attr">custom_parameter_1</span>: ...,
    ...
  }
});<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hf-endpoints-documentation/blob/main/docs/source/guides/test_endpoint.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_87vzq7 = {
						assets: "/docs/inference-endpoints/pr_113/en",
						base: "/docs/inference-endpoints/pr_113/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/inference-endpoints/pr_113/en/_app/immutable/entry/start.d1c14968.js"),
						import("/docs/inference-endpoints/pr_113/en/_app/immutable/entry/app.18050d92.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 18],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>