inference-providers/pr_1663/en/tasks/table-question-answering.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Table Question Answering&quot;,&quot;local&quot;:&quot;table-question-answering&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Recommended models&quot;,&quot;local&quot;:&quot;recommended-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Using the API&quot;,&quot;local&quot;:&quot;using-the-api&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;API specification&quot;,&quot;local&quot;:&quot;api-specification&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Request&quot;,&quot;local&quot;:&quot;request&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;Response&quot;,&quot;local&quot;:&quot;response&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3}],&quot;depth&quot;:2}">
		<link href="/docs/inference-providers/pr_1663/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/entry/start.d5f15666.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/scheduler.ddb4e551.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/singletons.0f5b782d.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/index.ce98237b.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/paths.b324c1e2.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/entry/app.68b4644d.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/index.e16e4efa.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/nodes/0.80863911.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/nodes/20.0fa87f69.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/Tip.20abb04f.js">
		<link rel="modulepreload" href="/docs/inference-providers/pr_1663/en/_app/immutable/chunks/index.e108c5ed.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Table Question Answering&quot;,&quot;local&quot;:&quot;table-question-answering&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Recommended models&quot;,&quot;local&quot;:&quot;recommended-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Using the API&quot;,&quot;local&quot;:&quot;using-the-api&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;API specification&quot;,&quot;local&quot;:&quot;api-specification&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Request&quot;,&quot;local&quot;:&quot;request&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;Response&quot;,&quot;local&quot;:&quot;response&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3}],&quot;depth&quot;:2}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h2 class="relative group"><a id="table-question-answering" 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="#table-question-answering"><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>Table Question Answering</span></h2> <p data-svelte-h="svelte-1h902ra">Table Question Answering (Table QA) is the answering a question about an information on a given table.</p>  <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-hnlsr0">For more details about the <code>table-question-answering</code> task, check out its <a href="https://huggingface.co/tasks/table-question-answering" rel="nofollow">dedicated page</a>! You will find examples and related materials.</p></div>  <h3 class="relative group"><a id="recommended-models" 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="#recommended-models"><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>Recommended models</span></h3> <ul data-svelte-h="svelte-1jox8hm"><li><a href="https://huggingface.co/microsoft/tapex-base" rel="nofollow">microsoft/tapex-base</a>: A table question answering model that is capable of neural SQL execution, i.e., employ TAPEX to execute a SQL query on a given table.</li> <li><a href="https://huggingface.co/google/tapas-base-finetuned-wtq" rel="nofollow">google/tapas-base-finetuned-wtq</a>: A robust table question answering model.</li></ul> <p data-svelte-h="svelte-1hakgjj">Explore all available models and find the one that suits you best <a href="https://huggingface.co/models?inference=warm&pipeline_tag=table-question-answering&sort=trending" rel="nofollow">here</a>.</p>  <h3 class="relative group"><a id="using-the-api" 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="#using-the-api"><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>Using the API</span></h3> <p data-svelte-h="svelte-1kehkb7">No snippet available for this task.</p>  <h3 class="relative group"><a id="api-specification" 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="#api-specification"><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>API specification</span></h3>  <h4 class="relative group"><a id="request" 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="#request"><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>Request</span></h4> <table data-svelte-h="svelte-11w5q36"><thead><tr><th align="left">Payload</th> <th align="left"></th> <th align="left"></th></tr></thead> <tbody><tr><td align="left"><strong>inputs*</strong></td> <td align="left"><em>object</em></td> <td align="left">One (table, question) pair to answer</td></tr> <tr><td align="left"><strong>        table*</strong></td> <td align="left"><em>object</em></td> <td align="left">The table to serve as context for the questions</td></tr> <tr><td align="left"><strong>        question*</strong></td> <td align="left"><em>string</em></td> <td align="left">The question to be answered about the table</td></tr> <tr><td align="left"><strong>parameters</strong></td> <td align="left"><em>object</em></td> <td align="left"></td></tr> <tr><td align="left"><strong>        padding</strong></td> <td align="left"><em>enum</em></td> <td align="left">Possible values: do_not_pad, longest, max_length.</td></tr> <tr><td align="left"><strong>        sequential</strong></td> <td align="left"><em>boolean</em></td> <td align="left">Whether to do inference sequentially or as a batch. Batching is faster, but models like SQA require the inference to be done sequentially to extract relations within sequences, given their conversational nature.</td></tr> <tr><td align="left"><strong>        truncation</strong></td> <td align="left"><em>boolean</em></td> <td align="left">Activates and controls truncation.</td></tr></tbody></table> <p data-svelte-h="svelte-xa4wks">Some options can be configured by passing headers to the Inference API. Here are the available headers:</p> <table data-svelte-h="svelte-2rfiu7"><thead><tr><th align="left">Headers</th> <th align="left"></th> <th align="left"></th></tr></thead> <tbody><tr><td align="left"><strong>authorization</strong></td> <td align="left"><em>string</em></td> <td align="left">Authentication header in the form <code>&#39;Bearer: hf_****&#39;</code> when <code>hf_****</code> is a personal user access token with Inference API permission. You can generate one from <a href="https://huggingface.co/settings/tokens" rel="nofollow">your settings page</a>.</td></tr> <tr><td align="left"><strong>x-use-cache</strong></td> <td align="left"><em>boolean, default to <code>true</code></em></td> <td align="left">There is a cache layer on the inference API to speed up requests we have already seen. Most models can use those results as they are deterministic (meaning the outputs will be the same anyway). However, if you use a nondeterministic model, you can set this parameter to prevent the caching mechanism from being used, resulting in a real new query. Read more about caching <a href="../parameters#caching%5D">here</a>.</td></tr> <tr><td align="left"><strong>x-wait-for-model</strong></td> <td align="left"><em>boolean, default to <code>false</code></em></td> <td align="left">If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error, as it will limit hanging in your application to known places. Read more about model availability <a href="../overview#eligibility%5D">here</a>.</td></tr></tbody></table> <p data-svelte-h="svelte-1ps9cb1">For more information about Inference API headers, check out the parameters <a href="../parameters">guide</a>.</p>  <h4 class="relative group"><a id="response" 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="#response"><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>Response</span></h4> <table data-svelte-h="svelte-1u8ol55"><thead><tr><th align="left">Body</th> <th align="left"></th> <th align="left"></th></tr></thead> <tbody><tr><td align="left"><strong>(array)</strong></td> <td align="left"><em>object[]</em></td> <td align="left">Output is an array of objects.</td></tr> <tr><td align="left"><strong>        answer</strong></td> <td align="left"><em>string</em></td> <td align="left">The answer of the question given the table. If there is an aggregator, the answer will be preceded by <code>AGGREGATOR &gt;</code>.</td></tr> <tr><td align="left"><strong>        coordinates</strong></td> <td align="left"><em>array[]</em></td> <td align="left">Coordinates of the cells of the answers.</td></tr> <tr><td align="left"><strong>        cells</strong></td> <td align="left"><em>string[]</em></td> <td align="left">List of strings made up of the answer cell values.</td></tr> <tr><td align="left"><strong>        aggregator</strong></td> <td align="left"><em>string</em></td> <td align="left">If the model has an aggregator, this returns the aggregator.</td></tr></tbody></table> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/inference-providers/tasks/table-question-answering.md" 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_1o5mypj = {
						assets: "/docs/inference-providers/pr_1663/en",
						base: "/docs/inference-providers/pr_1663/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/inference-providers/pr_1663/en/_app/immutable/entry/start.d5f15666.js"),
						import("/docs/inference-providers/pr_1663/en/_app/immutable/entry/app.68b4644d.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 20],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>