datasets/pr_8193/en/_app/immutable/nodes/20.dce2fe2b.js

import{s as ts,n as ss,o as as}from"../chunks/scheduler.d75c11ed.js";import{S as es,i as ls,e as p,s as l,c as m,h as ns,a as o,d as a,b as n,f as Kt,g as r,j as i,k as Ot,l as ps,m as e,n as d,t as h,o as c,p as g}from"../chunks/index.4ec9dfe9.js";import{C as os,H as A,E as is}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.d492929c.js";import{C as L}from"../chunks/CodeBlock.f741bf07.js";function ms($t){let u,K,P,O,f,tt,y,st,M,at,J,Rt="The Hugging Face Dataset Hub is home to a growing collection of datasets that span a variety of domains and tasks.",et,w,vt="It’s more than a cloud storage: the Dataset Hub is a platform that provides data versioning thanks to git, as well as a Dataset Viewer to explore the data, making it a great place to store AI-ready datasets.",lt,T,Ft="This guide shows how to import data from other cloud storage using the filesystems implementations from <code>fsspec</code>.",nt,j,pt,b,xt="Storage Buckets are a repo type on the Hugging Face Hub providing S3-like object storage, powered by the Xet storage backend. Unlike Git-based dataset repositories, buckets are non-versioned and mutable, designed for use cases where you need simple, fast storage such as logs, intermediate artifacts, or any large collection of files that doesn’t need version control.",ot,I,it,k,Yt=`Most cloud storage providers have a <code>fsspec</code> FileSystem implementation, which is useful to import data from any cloud provider with the same code.
This is especially useful to publish datasets on Hugging Face.`,mt,Z,Wt="Take a look at the following table for some example of supported cloud storage providers:",rt,G,Vt='<thead><tr><th>Storage provider</th> <th>Filesystem implementation</th></tr></thead> <tbody><tr><td>Amazon S3</td> <td><a href="https://s3fs.readthedocs.io/en/latest/" rel="nofollow">s3fs</a></td></tr> <tr><td>Google Cloud Storage</td> <td><a href="https://gcsfs.readthedocs.io/en/latest/" rel="nofollow">gcsfs</a></td></tr> <tr><td>Azure Blob/DataLake</td> <td><a href="https://github.com/fsspec/adlfs" rel="nofollow">adlfs</a></td></tr> <tr><td>Oracle Cloud Storage</td> <td><a href="https://ocifs.readthedocs.io/en/latest/" rel="nofollow">ocifs</a></td></tr></tbody>',dt,U,Nt="This guide will show you how to import data files from any cloud storage and save a dataset on Hugging Face.",ht,X,zt="Let’s say we want to publish a dataset on Hugging Face from Parquet files from a cloud storage.",ct,_,Qt="First, instantiate your cloud storage filesystem and list the files you’d like to import:",gt,B,ut,C,ft,$,Ht="Then you can create a dataset on Hugging Face and import the data files, using for example:",yt,R,Mt,v,St='Check out the <a href="https://huggingface.co/docs/huggingface_hub" rel="nofollow">huggingface_hub</a> documentation on files uploads <a href="https://huggingface.co/docs/huggingface_hub/en/guides/upload" rel="nofollow">here</a> if you’re looking for more upload options.',Jt,F,qt="Finally you can now load the dataset using 🤗 Datasets:",wt,x,Tt,Y,jt,W,Et='Alternatively if you wish not to publish a dataset but simply import raw data files in a Hugging Face <a href="https://huggingface.co/docs/hub/storage-buckets" rel="nofollow">Storage Bucket</a>, you can use:',bt,V,It,N,At='Check out the <a href="https://huggingface.co/docs/huggingface_hub" rel="nofollow">huggingface_hub</a> documentation on Storage Buckets <a href="https://huggingface.co/docs/hub/storage-buckets" rel="nofollow">here</a> if you’re looking for more upload options.',kt,z,Lt="Then later you can load the raw files using 🤗 Datasets, transform them and upload the final AI-ready datasets, e.g. in a streaming manner:",Zt,Q,Pt="If the files are in a format supported by 🤗 Datasets:",Gt,H,Ut,S,Dt="Otherwise you can use your own file parsing function:",Xt,q,_t,E,Bt,D,Ct;return f=new os({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),y=new A({props:{title:"Cloud storage",local:"cloud-storage",headingTag:"h1"}}),M=new A({props:{title:"Hugging Face Datasets",local:"hugging-face-datasets",headingTag:"h2"}}),j=new A({props:{title:"Hugging Face Storage Buckets",local:"hugging-face-storage-buckets",headingTag:"h2"}}),I=new A({props:{title:"Import data from a cloud storage",local:"import-data-from-a-cloud-storage",headingTag:"h2"}}),B=new L({props:{code:"aW1wb3J0JTIwZnNzcGVjJTBBZnMlMjAlM0QlMjBmc3NwZWMuZmlsZXN5c3RlbSglMjIuLi4lMjIpJTIwJTIwJTIzJTIwczMlMjAlMkYlMjBnY3MlMjAlMkYlMjBhYmZzJTIwJTJGJTIwYWRsJTIwJTJGJTIwb2NpJTIwJTJGJTIwLi4uJTBBZGF0YV9kaXIlMjAlM0QlMjAlMjJwYXRoJTJGdG8lMkZteSUyRmRhdGElMkYlMjIlMEFwYXR0ZXJuJTIwJTNEJTIwJTIyKi5wYXJxdWV0JTIyJTBBZGF0YV9maWxlcyUyMCUzRCUyMGZzLmdsb2IoZGF0YV9kaXIlMjAlMkIlMjBwYXR0ZXJuKQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> fsspec
<span class="hljs-meta">&gt;&gt;&gt; </span>fs = fsspec.filesystem(<span class="hljs-string">&quot;...&quot;</span>)  <span class="hljs-comment"># s3 / gcs / abfs / adl / oci / ...</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>data_dir = <span class="hljs-string">&quot;path/to/my/data/&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pattern = <span class="hljs-string">&quot;*.parquet&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>data_files = fs.glob(data_dir + pattern)
[<span class="hljs-string">&quot;path/to/my/data/0001.parquet&quot;</span>, <span class="hljs-string">&quot;path/to/my/data/0001.parquet&quot;</span>, ...]`,lang:"python",wrap:!1}}),C=new A({props:{title:"Publish a Dataset",local:"publish-a-dataset",headingTag:"h3"}}),R=new L({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> create_repo, upload_folder
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> tqdm.auto <span class="hljs-keyword">import</span> tqdm
<span class="hljs-meta">&gt;&gt;&gt; </span>destination_dataset = <span class="hljs-string">&quot;username/my-dataset&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>create_repo(destination_dataset, repo_type=<span class="hljs-string">&quot;dataset&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>batch_size = <span class="hljs-number">100</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> data_files <span class="hljs-keyword">in</span> batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
<span class="hljs-meta">... </span>    <span class="hljs-keyword">with</span> TemporaryDirectory() <span class="hljs-keyword">as</span> tmp_dir:
<span class="hljs-meta">... </span>        tmp_files = [os.path.join(tmp_dir, x[<span class="hljs-built_in">len</span>(data_dir):]) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> data_files]
<span class="hljs-meta">... </span>        fs.download(data_files, tmp_files)
<span class="hljs-meta">... </span>        upload_folder(
<span class="hljs-meta">... </span>            repo_id=destination_dataset,
<span class="hljs-meta">... </span>            folder_path=tmp_dir,
<span class="hljs-meta">... </span>            repo_type=<span class="hljs-string">&quot;dataset&quot;</span>,
<span class="hljs-meta">... </span>        )`,lang:"python",wrap:!1}}),x=new L({props:{code:"ZnJvbSUyMGRhdGFzZXRzJTIwaW1wb3J0JTIwbG9hZF9kYXRhc2V0JTBBZHMlMjAlM0QlMjBsb2FkX2RhdGFzZXQoJTIydXNlcm5hbWUlMkZteS1kYXRhc2V0JTIyKQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = load_dataset(<span class="hljs-string">&quot;username/my-dataset&quot;</span>)`,lang:"python",wrap:!1}}),Y=new A({props:{title:"Import raw data to Storage Buckets",local:"import-raw-data-to-storage-buckets",headingTag:"h3"}}),V=new L({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> create_bucket, sync_bucket
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> tqdm.auto <span class="hljs-keyword">import</span> tqdm
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> itertools <span class="hljs-keyword">import</span> batched
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> tempfile <span class="hljs-keyword">import</span> TemporaryDirectory
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> os
<span class="hljs-meta">&gt;&gt;&gt; </span>create_bucket(<span class="hljs-string">&quot;username/my-bucket&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>bucket_files_location = <span class="hljs-string">&quot;hf://buckets/username/my-bucket/path/to/raw/files&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>batch_size = <span class="hljs-number">100</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> data_files <span class="hljs-keyword">in</span> batched(tqdm(fs.glob(data_dir + pattern)), batch_size):
<span class="hljs-meta">... </span>    <span class="hljs-keyword">with</span> TemporaryDirectory() <span class="hljs-keyword">as</span> tmp_dir:
<span class="hljs-meta">... </span>        tmp_files = [os.path.join(tmp_dir, x[<span class="hljs-built_in">len</span>(data_dir):]) <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> data_files]
<span class="hljs-meta">... </span>        fs.download(data_files, tmp_files)
<span class="hljs-meta">... </span>        sync_bucket(tmp_dir, bucket_files_location)`,lang:"python",wrap:!1}}),H=new L({props:{code:"ZnJvbSUyMGRhdGFzZXRzJTIwaW1wb3J0JTIwbG9hZF9kYXRhc2V0JTBBZHMlMjAlM0QlMjBsb2FkX2RhdGFzZXQoYnVja2V0X2ZpbGVzX2xvY2F0aW9uJTJDJTIwc3RyZWFtaW5nJTNEVHJ1ZSklMEFkcyUyMCUzRCUyMGRzLm1hcCguLi4pLmZpbHRlciguLi4pJTBBZHMucHVzaF90b19odWIoJTIydXNlcm5hbWUlMkZteS1kYXRhc2V0JTIyJTJDJTIwbnVtX3Byb2MlM0Q0KSUwQSUyMyUyMGFuZCUyMGxhdGVyJTBBZHMlMjAlM0QlMjBsb2FkX2RhdGFzZXQoJTIydXNlcm5hbWUlMkZteS1kYXRhc2V0JTIyKQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = load_dataset(bucket_files_location, streaming=<span class="hljs-literal">True</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = ds.<span class="hljs-built_in">map</span>(...).<span class="hljs-built_in">filter</span>(...)
<span class="hljs-meta">&gt;&gt;&gt; </span>ds.push_to_hub(<span class="hljs-string">&quot;username/my-dataset&quot;</span>, num_proc=<span class="hljs-number">4</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># and later</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = load_dataset(<span class="hljs-string">&quot;username/my-dataset&quot;</span>)`,lang:"python",wrap:!1}}),q=new L({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> IterableDataset
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> hffs
<span class="hljs-meta">&gt;&gt;&gt; </span>data_files = hffs.find(bucket_files_location)
<span class="hljs-meta">&gt;&gt;&gt; </span>num_shards = <span class="hljs-number">1024</span>  <span class="hljs-comment"># For parallelism. PS: every shard should fit in RAM</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = IterableDataset.from_dict({<span class="hljs-string">&quot;data_file&quot;</span>: data_files}, num_shards=num_shards)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">parse_data_files</span>(<span class="hljs-params">data_files</span>):
<span class="hljs-meta">... </span>    ...
<span class="hljs-meta">... </span>    <span class="hljs-keyword">return</span> {<span class="hljs-string">&quot;col_1&quot;</span>: [...], <span class="hljs-string">&quot;col_2&quot;</span>: [...]}
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = ds.<span class="hljs-built_in">map</span>(parse_data_files, batched=<span class="hljs-literal">True</span>, input_column=[<span class="hljs-string">&quot;data_file&quot;</span>])
<span class="hljs-meta">&gt;&gt;&gt; </span>ds.push_to_hub(<span class="hljs-string">&quot;username/my-dataset&quot;</span>, num_proc=<span class="hljs-number">4</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># and later</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>ds = load_dataset(<span class="hljs-string">&quot;username/my-dataset&quot;</span>)`,lang:"python",wrap:!1}}),E=new is({props:{source:"https://github.com/huggingface/datasets/blob/main/docs/source/filesystems.mdx"}}),{c(){u=p("meta"),K=l(),P=p("p"),O=l(),m(f.$$.fragment),tt=l(),m(y.$$.fragment),st=l(),m(M.$$.fragment),at=l(),J=p("p"),J.textContent=Rt,et=l(),w=p("p"),w.textContent=vt,lt=l(),T=p("p"),T.innerHTML=Ft,nt=l(),m(j.$$.fragment),pt=l(),b=p("p"),b.textContent=xt,ot=l(),m(I.$$.fragment),it=l(),k=p("p"),k.innerHTML=Yt,mt=l(),Z=p("p"),Z.textContent=Wt,rt=l(),G=p("table"),G.innerHTML=Vt,dt=l(),U=p("p"),U.textContent=Nt,ht=l(),X=p("p"),X.textContent=zt,ct=l(),_=p("p"),_.textContent=Qt,gt=l(),m(B.$$.fragment),ut=l(),m(C.$$.fragment),ft=l(),$=p("p"),$.textContent=Ht,yt=l(),m(R.$$.fragment),Mt=l(),v=p("p"),v.innerHTML=St,Jt=l(),F=p("p"),F.textContent=qt,wt=l(),m(x.$$.fragment),Tt=l(),m(Y.$$.fragment),jt=l(),W=p("p"),W.innerHTML=Et,bt=l(),m(V.$$.fragment),It=l(),N=p("p"),N.innerHTML=At,kt=l(),z=p("p"),z.textContent=Lt,Zt=l(),Q=p("p"),Q.textContent=Pt,Gt=l(),m(H.$$.fragment),Ut=l(),S=p("p"),S.textContent=Dt,Xt=l(),m(q.$$.fragment),_t=l(),m(E.$$.fragment),Bt=l(),D=p("p"),this.h()},l(t){const s=ns("svelte-u9bgzb",document.head);u=o(s,"META",{name:!0,content:!0}),s.forEach(a),K=n(t),P=o(t,"P",{}),Kt(P).forEach(a),O=n(t),r(f.$$.fragment,t),tt=n(t),r(y.$$.fragment,t),st=n(t),r(M.$$.fragment,t),at=n(t),J=o(t,"P",{"data-svelte-h":!0}),i(J)!=="svelte-pwg4if"&&(J.textContent=Rt),et=n(t),w=o(t,"P",{"data-svelte-h":!0}),i(w)!=="svelte-le6063"&&(w.textContent=vt),lt=n(t),T=o(t,"P",{"data-svelte-h":!0}),i(T)!=="svelte-ei4lhv"&&(T.innerHTML=Ft),nt=n(t),r(j.$$.fragment,t),pt=n(t),b=o(t,"P",{"data-svelte-h":!0}),i(b)!=="svelte-1f2me8o"&&(b.textContent=xt),ot=n(t),r(I.$$.fragment,t),it=n(t),k=o(t,"P",{"data-svelte-h":!0}),i(k)!=="svelte-1uadmic"&&(k.innerHTML=Yt),mt=n(t),Z=o(t,"P",{"data-svelte-h":!0}),i(Z)!=="svelte-1enr8yq"&&(Z.textContent=Wt),rt=n(t),G=o(t,"TABLE",{"data-svelte-h":!0}),i(G)!=="svelte-40f5jy"&&(G.innerHTML=Vt),dt=n(t),U=o(t,"P",{"data-svelte-h":!0}),i(U)!=="svelte-tdsgr3"&&(U.textContent=Nt),ht=n(t),X=o(t,"P",{"data-svelte-h":!0}),i(X)!=="svelte-19vswnu"&&(X.textContent=zt),ct=n(t),_=o(t,"P",{"data-svelte-h":!0}),i(_)!=="svelte-1fbzvas"&&(_.textContent=Qt),gt=n(t),r(B.$$.fragment,t),ut=n(t),r(C.$$.fragment,t),ft=n(t),$=o(t,"P",{"data-svelte-h":!0}),i($)!=="svelte-br8k8v"&&($.textContent=Ht),yt=n(t),r(R.$$.fragment,t),Mt=n(t),v=o(t,"P",{"data-svelte-h":!0}),i(v)!=="svelte-drsgq7"&&(v.innerHTML=St),Jt=n(t),F=o(t,"P",{"data-svelte-h":!0}),i(F)!=="svelte-5gahax"&&(F.textContent=qt),wt=n(t),r(x.$$.fragment,t),Tt=n(t),r(Y.$$.fragment,t),jt=n(t),W=o(t,"P",{"data-svelte-h":!0}),i(W)!=="svelte-1afdv1v"&&(W.innerHTML=Et),bt=n(t),r(V.$$.fragment,t),It=n(t),N=o(t,"P",{"data-svelte-h":!0}),i(N)!=="svelte-1d7y2kh"&&(N.innerHTML=At),kt=n(t),z=o(t,"P",{"data-svelte-h":!0}),i(z)!=="svelte-r4lftr"&&(z.textContent=Lt),Zt=n(t),Q=o(t,"P",{"data-svelte-h":!0}),i(Q)!=="svelte-8p9hs7"&&(Q.textContent=Pt),Gt=n(t),r(H.$$.fragment,t),Ut=n(t),S=o(t,"P",{"data-svelte-h":!0}),i(S)!=="svelte-1imogd5"&&(S.textContent=Dt),Xt=n(t),r(q.$$.fragment,t),_t=n(t),r(E.$$.fragment,t),Bt=n(t),D=o(t,"P",{}),Kt(D).forEach(a),this.h()},h(){Ot(u,"name","hf:doc:metadata"),Ot(u,"content",rs)},m(t,s){ps(document.head,u),e(t,K,s),e(t,P,s),e(t,O,s),d(f,t,s),e(t,tt,s),d(y,t,s),e(t,st,s),d(M,t,s),e(t,at,s),e(t,J,s),e(t,et,s),e(t,w,s),e(t,lt,s),e(t,T,s),e(t,nt,s),d(j,t,s),e(t,pt,s),e(t,b,s),e(t,ot,s),d(I,t,s),e(t,it,s),e(t,k,s),e(t,mt,s),e(t,Z,s),e(t,rt,s),e(t,G,s),e(t,dt,s),e(t,U,s),e(t,ht,s),e(t,X,s),e(t,ct,s),e(t,_,s),e(t,gt,s),d(B,t,s),e(t,ut,s),d(C,t,s),e(t,ft,s),e(t,$,s),e(t,yt,s),d(R,t,s),e(t,Mt,s),e(t,v,s),e(t,Jt,s),e(t,F,s),e(t,wt,s),d(x,t,s),e(t,Tt,s),d(Y,t,s),e(t,jt,s),e(t,W,s),e(t,bt,s),d(V,t,s),e(t,It,s),e(t,N,s),e(t,kt,s),e(t,z,s),e(t,Zt,s),e(t,Q,s),e(t,Gt,s),d(H,t,s),e(t,Ut,s),e(t,S,s),e(t,Xt,s),d(q,t,s),e(t,_t,s),d(E,t,s),e(t,Bt,s),e(t,D,s),Ct=!0},p:ss,i(t){Ct||(h(f.$$.fragment,t),h(y.$$.fragment,t),h(M.$$.fragment,t),h(j.$$.fragment,t),h(I.$$.fragment,t),h(B.$$.fragment,t),h(C.$$.fragment,t),h(R.$$.fragment,t),h(x.$$.fragment,t),h(Y.$$.fragment,t),h(V.$$.fragment,t),h(H.$$.fragment,t),h(q.$$.fragment,t),h(E.$$.fragment,t),Ct=!0)},o(t){c(f.$$.fragment,t),c(y.$$.fragment,t),c(M.$$.fragment,t),c(j.$$.fragment,t),c(I.$$.fragment,t),c(B.$$.fragment,t),c(C.$$.fragment,t),c(R.$$.fragment,t),c(x.$$.fragment,t),c(Y.$$.fragment,t),c(V.$$.fragment,t),c(H.$$.fragment,t),c(q.$$.fragment,t),c(E.$$.fragment,t),Ct=!1},d(t){t&&(a(K),a(P),a(O),a(tt),a(st),a(at),a(J),a(et),a(w),a(lt),a(T),a(nt),a(pt),a(b),a(ot),a(it),a(k),a(mt),a(Z),a(rt),a(G),a(dt),a(U),a(ht),a(X),a(ct),a(_),a(gt),a(ut),a(ft),a($),a(yt),a(Mt),a(v),a(Jt),a(F),a(wt),a(Tt),a(jt),a(W),a(bt),a(It),a(N),a(kt),a(z),a(Zt),a(Q),a(Gt),a(Ut),a(S),a(Xt),a(_t),a(Bt),a(D)),a(u),g(f,t),g(y,t),g(M,t),g(j,t),g(I,t),g(B,t),g(C,t),g(R,t),g(x,t),g(Y,t),g(V,t),g(H,t),g(q,t),g(E,t)}}}const rs='{"title":"Cloud storage","local":"cloud-storage","sections":[{"title":"Hugging Face Datasets","local":"hugging-face-datasets","sections":[],"depth":2},{"title":"Hugging Face Storage Buckets","local":"hugging-face-storage-buckets","sections":[],"depth":2},{"title":"Import data from a cloud storage","local":"import-data-from-a-cloud-storage","sections":[{"title":"Publish a Dataset","local":"publish-a-dataset","sections":[],"depth":3},{"title":"Import raw data to Storage Buckets","local":"import-raw-data-to-storage-buckets","sections":[],"depth":3}],"depth":2}],"depth":1}';function ds($t){return as(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class fs extends es{constructor(u){super(),ls(this,u,ds,ms,ts,{})}}export{fs as component};