Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / datasets /pr_8021 /en /faiss_es.html

rtrm

29 days ago

download

raw

38.4 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Search index","local":"search-index","sections":[{"title":"FAISS","local":"faiss","sections":[],"depth":2},{"title":"Elasticsearch","local":"elasticsearch","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/datasets/pr_8021/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/entry/start.467c4c66.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/scheduler.d75c11ed.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/singletons.24e4ec1f.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/index.d12496d4.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/paths.409c1290.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/entry/app.3b2ba720.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/preload-helper.a99c0584.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/index.4ec9dfe9.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/nodes/0.5fda7065.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/nodes/19.66985e89.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.ee0f129e.js">
	<link rel="modulepreload" href="/docs/datasets/pr_8021/en/_app/immutable/chunks/CodeBlock.5919a092.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Search index","local":"search-index","sections":[{"title":"FAISS","local":"faiss","sections":[],"depth":2},{"title":"Elasticsearch","local":"elasticsearch","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="search-index" 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="#search-index"><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>Search index</span></h1> <p data-svelte-h="svelte-1n7ea75"><a href="https://github.com/facebookresearch/faiss" rel="nofollow">FAISS</a> and <a href="https://www.elastic.co/elasticsearch/" rel="nofollow">Elasticsearch</a> enables searching for examples in a dataset. This can be useful when you want to retrieve specific examples from a dataset that are relevant to your NLP task. For example, if you are working on an Open Domain Question Answering task, you may want to only return examples that are relevant to answering your question.</p> <p data-svelte-h="svelte-hdwpul">This guide will show you how to build an index for your dataset that will allow you to search it.</p> <h2 class="relative group"><a id="faiss" 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="#faiss"><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>FAISS</span></h2> <p data-svelte-h="svelte-se9cy2">FAISS retrieves documents based on the similarity of their vector representations. In this example, you will generate the vector representations with the <a href="https://huggingface.co/transformers/model_doc/dpr.html" rel="nofollow">DPR</a> model.</p> <ol data-svelte-h="svelte-x1ghuo"><li>Download the DPR model from 🤗 Transformers:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DPRContextEncoder, DPRContextEncoderTokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch
	<span class="hljs-meta">>>> </span>torch.set_grad_enabled(<span class="hljs-literal">False</span>)
	<span class="hljs-meta">>>> </span>ctx_encoder = DPRContextEncoder.from_pretrained(<span class="hljs-string">"facebook/dpr-ctx_encoder-single-nq-base"</span>)
	<span class="hljs-meta">>>> </span>ctx_tokenizer = DPRContextEncoderTokenizer.from_pretrained(<span class="hljs-string">"facebook/dpr-ctx_encoder-single-nq-base"</span>)<!-- HTML_TAG_END --></pre></div> <ol start="2" data-svelte-h="svelte-1teerx9"><li>Load your dataset and compute the vector representations:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>ds = load_dataset(<span class="hljs-string">'community-datasets/crime_and_punish'</span>, split=<span class="hljs-string">'train[:100]'</span>)
	<span class="hljs-meta">>>> </span>ds_with_embeddings = ds.<span class="hljs-built_in">map</span>(<span class="hljs-keyword">lambda</span> example: {<span class="hljs-string">'embeddings'</span>: ctx_encoder(**ctx_tokenizer(example[<span class="hljs-string">"line"</span>], return_tensors=<span class="hljs-string">"pt"</span>))[<span class="hljs-number">0</span>][<span class="hljs-number">0</span>].numpy()})<!-- HTML_TAG_END --></pre></div> <ol start="3" data-svelte-h="svelte-ym625v"><li>Create the index with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.add_faiss_index">Dataset.add_faiss_index()</a>:</li></ol> <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-meta">>>> </span>ds_with_embeddings.add_faiss_index(column=<span class="hljs-string">'embeddings'</span>)<!-- HTML_TAG_END --></pre></div> <ol start="4" data-svelte-h="svelte-1ast6iv"><li>Now you can query your dataset with the <code>embeddings</code> index. Load the DPR Question Encoder, and search for a question with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.get_nearest_examples">Dataset.get_nearest_examples()</a>:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DPRQuestionEncoder, DPRQuestionEncoderTokenizer
	<span class="hljs-meta">>>> </span>q_encoder = DPRQuestionEncoder.from_pretrained(<span class="hljs-string">"facebook/dpr-question_encoder-single-nq-base"</span>)
	<span class="hljs-meta">>>> </span>q_tokenizer = DPRQuestionEncoderTokenizer.from_pretrained(<span class="hljs-string">"facebook/dpr-question_encoder-single-nq-base"</span>)

	<span class="hljs-meta">>>> </span>question = <span class="hljs-string">"Is it serious ?"</span>
	<span class="hljs-meta">>>> </span>question_embedding = q_encoder(**q_tokenizer(question, return_tensors=<span class="hljs-string">"pt"</span>))[<span class="hljs-number">0</span>][<span class="hljs-number">0</span>].numpy()
	<span class="hljs-meta">>>> </span>scores, retrieved_examples = ds_with_embeddings.get_nearest_examples(<span class="hljs-string">'embeddings'</span>, question_embedding, k=<span class="hljs-number">10</span>)
	<span class="hljs-meta">>>> </span>retrieved_examples[<span class="hljs-string">"line"</span>][<span class="hljs-number">0</span>]
	<span class="hljs-string">'_that_ serious? It is not serious at all. It’s simply a fantasy to amuse\r\n'</span><!-- HTML_TAG_END --></pre></div> <ol start="5" data-svelte-h="svelte-64d8et"><li>You can access the index with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.get_index">Dataset.get_index()</a> and use it for special operations, e.g. query it using <code>range_search</code>:</li></ol> <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-meta">>>> </span>faiss_index = ds_with_embeddings.get_index(<span class="hljs-string">'embeddings'</span>).faiss_index
	<span class="hljs-meta">>>> </span>limits, distances, indices = faiss_index.range_search(x=question_embedding.reshape(<span class="hljs-number">1</span>, -<span class="hljs-number">1</span>), thresh=<span class="hljs-number">0.95</span>)<!-- HTML_TAG_END --></pre></div> <ol start="6" data-svelte-h="svelte-10f8mcs"><li>When you are done querying, save the index on disk with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.save_faiss_index">Dataset.save_faiss_index()</a>:</li></ol> <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-meta">>>> </span>ds_with_embeddings.save_faiss_index(<span class="hljs-string">'embeddings'</span>, <span class="hljs-string">'my_index.faiss'</span>)<!-- HTML_TAG_END --></pre></div> <ol start="7" data-svelte-h="svelte-pmavtd"><li>Reload it at a later time with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.load_faiss_index">Dataset.load_faiss_index()</a>:</li></ol> <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-meta">>>> </span>ds = load_dataset(<span class="hljs-string">'community-datasets/crime_and_punish'</span>, split=<span class="hljs-string">'train[:100]'</span>)
	<span class="hljs-meta">>>> </span>ds.load_faiss_index(<span class="hljs-string">'embeddings'</span>, <span class="hljs-string">'my_index.faiss'</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="elasticsearch" 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="#elasticsearch"><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>Elasticsearch</span></h2> <p data-svelte-h="svelte-8ul8ma">Unlike FAISS, Elasticsearch retrieves documents based on exact matches.</p> <p data-svelte-h="svelte-195ztu1">Start Elasticsearch on your machine, or see the <a href="https://www.elastic.co/guide/en/elasticsearch/reference/current/setup.html" rel="nofollow">Elasticsearch installation guide</a> if you don’t already have it installed.</p> <ol data-svelte-h="svelte-3fd7ny"><li>Load the dataset you want to index:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>squad = load_dataset(<span class="hljs-string">'rajpurkar/squad'</span>, split=<span class="hljs-string">'validation'</span>)<!-- HTML_TAG_END --></pre></div> <ol start="2" data-svelte-h="svelte-1v2mfzu"><li>Build the index with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.add_elasticsearch_index">Dataset.add_elasticsearch_index()</a>:</li></ol> <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-meta">>>> </span>squad.add_elasticsearch_index(<span class="hljs-string">"context"</span>, host=<span class="hljs-string">"localhost"</span>, port=<span class="hljs-string">"9200"</span>)<!-- HTML_TAG_END --></pre></div> <ol start="3" data-svelte-h="svelte-ez44t5"><li>Then you can query the <code>context</code> index with <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.get_nearest_examples">Dataset.get_nearest_examples()</a>:</li></ol> <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-meta">>>> </span>query = <span class="hljs-string">"machine"</span>
	<span class="hljs-meta">>>> </span>scores, retrieved_examples = squad.get_nearest_examples(<span class="hljs-string">"context"</span>, query, k=<span class="hljs-number">10</span>)
	<span class="hljs-meta">>>> </span>retrieved_examples[<span class="hljs-string">"title"</span>][<span class="hljs-number">0</span>]
	<span class="hljs-string">'Computational_complexity_theory'</span><!-- HTML_TAG_END --></pre></div> <ol start="4" data-svelte-h="svelte-1tchn11"><li>If you want to reuse the index, define the <code>es_index_name</code> parameter when you build the index:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>squad = load_dataset(<span class="hljs-string">'rajpurkar/squad'</span>, split=<span class="hljs-string">'validation'</span>)
	<span class="hljs-meta">>>> </span>squad.add_elasticsearch_index(<span class="hljs-string">"context"</span>, host=<span class="hljs-string">"localhost"</span>, port=<span class="hljs-string">"9200"</span>, es_index_name=<span class="hljs-string">"hf_squad_val_context"</span>)
	<span class="hljs-meta">>>> </span>squad.get_index(<span class="hljs-string">"context"</span>).es_index_name
	hf_squad_val_context<!-- HTML_TAG_END --></pre></div> <ol start="5" data-svelte-h="svelte-mhxyep"><li>Reload it later with the index name when you call <a href="/docs/datasets/pr_8021/en/package_reference/main_classes#datasets.Dataset.load_elasticsearch_index">Dataset.load_elasticsearch_index()</a>:</li></ol> <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-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
	<span class="hljs-meta">>>> </span>squad = load_dataset(<span class="hljs-string">'rajpurkar/squad'</span>, split=<span class="hljs-string">'validation'</span>)
	<span class="hljs-meta">>>> </span>squad.load_elasticsearch_index(<span class="hljs-string">"context"</span>, host=<span class="hljs-string">"localhost"</span>, port=<span class="hljs-string">"9200"</span>, es_index_name=<span class="hljs-string">"hf_squad_val_context"</span>)
	<span class="hljs-meta">>>> </span>query = <span class="hljs-string">"machine"</span>
	<span class="hljs-meta">>>> </span>scores, retrieved_examples = squad.get_nearest_examples(<span class="hljs-string">"context"</span>, query, k=<span class="hljs-number">10</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ajeg13">For more advanced Elasticsearch usage, you can specify your own configuration with custom settings:</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-meta">>>> </span><span class="hljs-keyword">import</span> elasticsearch <span class="hljs-keyword">as</span> es
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> elasticsearch.helpers
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> elasticsearch <span class="hljs-keyword">import</span> Elasticsearch
	<span class="hljs-meta">>>> </span>es_client = Elasticsearch([{<span class="hljs-string">"host"</span>: <span class="hljs-string">"localhost"</span>, <span class="hljs-string">"port"</span>: <span class="hljs-string">"9200"</span>}]) <span class="hljs-comment"># default client</span>
	<span class="hljs-meta">>>> </span>es_config = {
	<span class="hljs-meta">... </span> <span class="hljs-string">"settings"</span>: {
	<span class="hljs-meta">... </span> <span class="hljs-string">"number_of_shards"</span>: <span class="hljs-number">1</span>,
	<span class="hljs-meta">... </span> <span class="hljs-string">"analysis"</span>: {<span class="hljs-string">"analyzer"</span>: {<span class="hljs-string">"stop_standard"</span>: {<span class="hljs-string">"type"</span>: <span class="hljs-string">"standard"</span>, <span class="hljs-string">" stopwords"</span>: <span class="hljs-string">"_english_"</span>}}},
	<span class="hljs-meta">... </span> },
	<span class="hljs-meta">... </span> <span class="hljs-string">"mappings"</span>: {<span class="hljs-string">"properties"</span>: {<span class="hljs-string">"text"</span>: {<span class="hljs-string">"type"</span>: <span class="hljs-string">"text"</span>, <span class="hljs-string">"analyzer"</span>: <span class="hljs-string">"standard"</span>, <span class="hljs-string">"similarity"</span>: <span class="hljs-string">"BM25"</span>}}},
	<span class="hljs-meta">... </span>} <span class="hljs-comment"># default config</span>
	<span class="hljs-meta">>>> </span>es_index_name = <span class="hljs-string">"hf_squad_context"</span> <span class="hljs-comment"># name of the index in Elasticsearch</span>
	<span class="hljs-meta">>>> </span>squad.add_elasticsearch_index(<span class="hljs-string">"context"</span>, es_client=es_client, es_config=es_config, es_index_name=es_index_name)<!-- 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/datasets/blob/main/docs/source/faiss_es.mdx" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_1tcoqe3 = {
	assets: "/docs/datasets/pr_8021/en",
	base: "/docs/datasets/pr_8021/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/datasets/pr_8021/en/_app/immutable/entry/start.467c4c66.js"),
	import("/docs/datasets/pr_8021/en/_app/immutable/entry/app.3b2ba720.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 19],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 38.4 kB
Xet hash:: 6ce43a9bb0a8729c523a04d4222105c28fb0e87e1887ebd5a98d49940c7bc0f4

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