Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Hashing","local":"hashing","sections":[{"title":"Chunk Hashes","local":"chunk-hashes","sections":[{"title":"DATA_KEY","local":"datakey","sections":[],"depth":3}],"depth":2},{"title":"Xorb Hashes","local":"xorb-hashes","sections":[{"title":"INTERNAL_NODE_KEY","local":"internalnodekey","sections":[],"depth":3},{"title":"Example of data for internal node","local":"example-of-data-for-internal-node","sections":[],"depth":3},{"title":"Example Python code for the internal hash function","local":"example-python-code-for-the-internal-hash-function","sections":[],"depth":3}],"depth":2},{"title":"File Hashes","local":"file-hashes","sections":[],"depth":2},{"title":"Term Verification Hashes","local":"term-verification-hashes","sections":[{"title":"VERIFICATION_KEY","local":"verificationkey","sections":[],"depth":3},{"title":"Example Python code for the verification hash","local":"example-python-code-for-the-verification-hash","sections":[],"depth":3}],"depth":2},{"title":"Reference Files","local":"reference-files","sections":[{"title":"Chunk Hashes Sample","local":"chunk-hashes-sample","sections":[],"depth":3},{"title":"File Hash Sample","local":"file-hash-sample","sections":[],"depth":3},{"title":"Xorb Hash Sample","local":"xorb-hash-sample","sections":[],"depth":3},{"title":"Range Hash Sample","local":"range-hash-sample","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/xet/pr_2272/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/entry/start.7209fe0c.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/scheduler.de5597d1.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/singletons.800e7c38.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/paths.d1eab31c.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/entry/app.54268a84.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/preload-helper.1b7d12f9.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/index.f8bac2c1.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/nodes/0.097c0756.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/nodes/9.e762f09e.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.4e1a23d9.js"> | |
| <link rel="modulepreload" href="/docs/xet/pr_2272/en/_app/immutable/chunks/CodeBlock.d8c0c481.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Hashing","local":"hashing","sections":[{"title":"Chunk Hashes","local":"chunk-hashes","sections":[{"title":"DATA_KEY","local":"datakey","sections":[],"depth":3}],"depth":2},{"title":"Xorb Hashes","local":"xorb-hashes","sections":[{"title":"INTERNAL_NODE_KEY","local":"internalnodekey","sections":[],"depth":3},{"title":"Example of data for internal node","local":"example-of-data-for-internal-node","sections":[],"depth":3},{"title":"Example Python code for the internal hash function","local":"example-python-code-for-the-internal-hash-function","sections":[],"depth":3}],"depth":2},{"title":"File Hashes","local":"file-hashes","sections":[],"depth":2},{"title":"Term Verification Hashes","local":"term-verification-hashes","sections":[{"title":"VERIFICATION_KEY","local":"verificationkey","sections":[],"depth":3},{"title":"Example Python code for the verification hash","local":"example-python-code-for-the-verification-hash","sections":[],"depth":3}],"depth":2},{"title":"Reference Files","local":"reference-files","sections":[{"title":"Chunk Hashes Sample","local":"chunk-hashes-sample","sections":[],"depth":3},{"title":"File Hash Sample","local":"file-hash-sample","sections":[],"depth":3},{"title":"Xorb Hash Sample","local":"xorb-hash-sample","sections":[],"depth":3},{"title":"Range Hash Sample","local":"range-hash-sample","sections":[],"depth":3}],"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="hashing" 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="#hashing"><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>Hashing</span></h1> <ul data-svelte-h="svelte-1p4elgl"><li><a href="#chunk-hashes">Chunk hashes</a> - compute for each chunk from chunk data.</li> <li><a href="#xorb-hashes">Xorb Hashes</a> - compute for each xorb from its chunk hashes.</li> <li><a href="#file-hashes">File Hashes</a> - compute for each file from its chunk hashes.</li> <li><a href="#term-verification-hashes">Term Verification Hashes</a> - compute for each term in a reconstruction when serializing a shard from the chunk hashes in the xorb that is used in that term.</li></ul> <p data-svelte-h="svelte-qn784m">The Xet protocol utilizes a few different hashing types.</p> <p data-svelte-h="svelte-1dw5srm">All hashes referenced are 32 bytes (256 bits) long.</p> <h2 class="relative group"><a id="chunk-hashes" 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="#chunk-hashes"><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>Chunk Hashes</span></h2> <p data-svelte-h="svelte-1n4jnlt">After cutting a chunk of data, the chunk hash is computed via a blake3 keyed hash with the following key (DATA_KEY):</p> <h3 class="relative group"><a id="datakey" 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="#datakey"><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>DATA_KEY</span></h3> <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-punctuation">[</span> | |
| <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> <span class="hljs-number">151</span><span class="hljs-punctuation">,</span> <span class="hljs-number">245</span><span class="hljs-punctuation">,</span> <span class="hljs-number">119</span><span class="hljs-punctuation">,</span> <span class="hljs-number">91</span><span class="hljs-punctuation">,</span> <span class="hljs-number">149</span><span class="hljs-punctuation">,</span> <span class="hljs-number">80</span><span class="hljs-punctuation">,</span> <span class="hljs-number">222</span><span class="hljs-punctuation">,</span> <span class="hljs-number">49</span><span class="hljs-punctuation">,</span> <span class="hljs-number">53</span><span class="hljs-punctuation">,</span> <span class="hljs-number">203</span><span class="hljs-punctuation">,</span> <span class="hljs-number">172</span><span class="hljs-punctuation">,</span> <span class="hljs-number">165</span><span class="hljs-punctuation">,</span> <span class="hljs-number">151</span><span class="hljs-punctuation">,</span> <span class="hljs-number">24</span><span class="hljs-punctuation">,</span> <span class="hljs-number">28</span><span class="hljs-punctuation">,</span> <span class="hljs-number">157</span><span class="hljs-punctuation">,</span> <span class="hljs-number">228</span><span class="hljs-punctuation">,</span> <span class="hljs-number">33</span><span class="hljs-punctuation">,</span> <span class="hljs-number">16</span><span class="hljs-punctuation">,</span> <span class="hljs-number">155</span><span class="hljs-punctuation">,</span> <span class="hljs-number">235</span><span class="hljs-punctuation">,</span> <span class="hljs-number">43</span><span class="hljs-punctuation">,</span> <span class="hljs-number">88</span><span class="hljs-punctuation">,</span> <span class="hljs-number">180</span><span class="hljs-punctuation">,</span> <span class="hljs-number">208</span><span class="hljs-punctuation">,</span> <span class="hljs-number">176</span><span class="hljs-punctuation">,</span> <span class="hljs-number">75</span><span class="hljs-punctuation">,</span> <span class="hljs-number">147</span><span class="hljs-punctuation">,</span> <span class="hljs-number">173</span><span class="hljs-punctuation">,</span> <span class="hljs-number">242</span><span class="hljs-punctuation">,</span> <span class="hljs-number">41</span> | |
| <span class="hljs-punctuation">]</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-vblynd"><a href="https://github.com/huggingface/xet-core/blob/main/merklehash/src/data_hash.rs#L308-L311" rel="nofollow">reference implementation</a></p> <h2 class="relative group"><a id="xorb-hashes" 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="#xorb-hashes"><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>Xorb Hashes</span></h2> <p data-svelte-h="svelte-9sa3h0">Xorbs are composed of a series of chunks; given the series of chunks that make up a xorb, to compute the hash or xorb hash we will compute a MerkleHash using a <a href="https://en.wikipedia.org/wiki/Merkle_tree" rel="nofollow">Merkle Tree</a> data structure with custom hashing functions. | |
| <strong>The xorb hash will be the root node hash of the MerkleTree.</strong></p> <p data-svelte-h="svelte-1j8skhm">The leaf node hashes are the chunk hashes as described in the previous section.</p> <p data-svelte-h="svelte-170oeev">The hash function used to compute internal node hashes is as follows:</p> <ul data-svelte-h="svelte-120fvhk"><li>concatenate the hashes together such that for each chunk there is a line in order formatted like <code>{chunk_hash:x} : {size}\n</code> <ul><li>the hash first in lowercase hex format (64 hex characters e.g. <code>a3f91d6e8b47c20ff9d84a1c77dcb8e5a91e6fbf2b2d483af6d3c1e90ac57843</code>)</li> <li>a space, a colon, a space (<code>:</code>)</li> <li>the chunk length number e.g. 64000</li> <li>finally a newline <code>\n</code> character</li></ul></li> <li>Then take the bytes from this string and compute a blake3 keyed hash with the following key (INTERNAL_NODE_KEY)</li></ul> <p data-svelte-h="svelte-1itha2s"><a href="https://github.com/huggingface/xet-core/blob/main/merklehash/src/aggregated_hashes.rs#L103-L109" rel="nofollow">reference implementation</a></p> <h3 class="relative group"><a id="internalnodekey" 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="#internalnodekey"><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>INTERNAL_NODE_KEY</span></h3> <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-punctuation">[</span> | |
| <span class="hljs-number">1</span><span class="hljs-punctuation">,</span> <span class="hljs-number">126</span><span class="hljs-punctuation">,</span> <span class="hljs-number">197</span><span class="hljs-punctuation">,</span> <span class="hljs-number">199</span><span class="hljs-punctuation">,</span> <span class="hljs-number">165</span><span class="hljs-punctuation">,</span> <span class="hljs-number">71</span><span class="hljs-punctuation">,</span> <span class="hljs-number">41</span><span class="hljs-punctuation">,</span> <span class="hljs-number">150</span><span class="hljs-punctuation">,</span> <span class="hljs-number">253</span><span class="hljs-punctuation">,</span> <span class="hljs-number">148</span><span class="hljs-punctuation">,</span> <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> <span class="hljs-number">180</span><span class="hljs-punctuation">,</span> <span class="hljs-number">138</span><span class="hljs-punctuation">,</span> <span class="hljs-number">2</span><span class="hljs-punctuation">,</span> <span class="hljs-number">230</span><span class="hljs-punctuation">,</span> <span class="hljs-number">93</span><span class="hljs-punctuation">,</span> <span class="hljs-number">221</span><span class="hljs-punctuation">,</span> <span class="hljs-number">83</span><span class="hljs-punctuation">,</span> <span class="hljs-number">111</span><span class="hljs-punctuation">,</span> <span class="hljs-number">55</span><span class="hljs-punctuation">,</span> <span class="hljs-number">199</span><span class="hljs-punctuation">,</span> <span class="hljs-number">109</span><span class="hljs-punctuation">,</span> <span class="hljs-number">210</span><span class="hljs-punctuation">,</span> <span class="hljs-number">248</span><span class="hljs-punctuation">,</span> <span class="hljs-number">99</span><span class="hljs-punctuation">,</span> <span class="hljs-number">82</span><span class="hljs-punctuation">,</span> <span class="hljs-number">230</span><span class="hljs-punctuation">,</span> <span class="hljs-number">74</span><span class="hljs-punctuation">,</span> <span class="hljs-number">83</span><span class="hljs-punctuation">,</span> <span class="hljs-number">113</span><span class="hljs-punctuation">,</span> <span class="hljs-number">63</span> | |
| <span class="hljs-punctuation">]</span><!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="example-of-data-for-internal-node" 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="#example-of-data-for-internal-node"><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>Example of data for internal node</span></h3> <p data-svelte-h="svelte-1onbsm0">Consider that a node were 4 chunks with the following pairs of hashes and lengths:</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 -->hash,length (bytes) | |
| 1f6a2b8e9d3c4075a2e8c5fd4f0b763e6f3c1d7a9b2e6487de3f91ab7c6d5401,10000 | |
| 7c94fe2a38bdcf9b4d2a6f7e1e08ac35bc24a7903d6f5a0e7d1c2b93e5f748de,20000 | |
| cfd18a92e0743bb09e56dbf76ea2c34d99b5a0cf271f8d429b6cd148203df061,25000 | |
| e38d7c09a21b4cf8d0f92b3a85e6df19f7c20435e0b1c78a9d635f7b8c2e4da1,64000<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cux42q">Then to form the buffer to compute the internal node hash we will create this string (note the <code>\n</code> newline at the end):</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 -->"1f6a2b8e9d3c4075a2e8c5fd4f0b763e6f3c1d7a9b2e6487de3f91ab7c6d5401 : 10000 | |
| 7c94fe2a38bdcf9b4d2a6f7e1e08ac35bc24a7903d6f5a0e7d1c2b93e5f748de : 20000 | |
| cfd18a92e0743bb09e56dbf76ea2c34d99b5a0cf271f8d429b6cd148203df061 : 25000 | |
| e38d7c09a21b4cf8d0f92b3a85e6df19f7c20435e0b1c78a9d635f7b8c2e4da1 : 64000 | |
| "<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ycy69l">Then compute the blake3 keyed hash with INTERNAL_NODE_KEY to get the final hash.</p> <h3 class="relative group"><a id="example-python-code-for-the-internal-hash-function" 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="#example-python-code-for-the-internal-hash-function"><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>Example Python code for the internal hash function</span></h3> <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> blake3 <span class="hljs-keyword">import</span> blake3 | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">internal_hash_function</span>(<span class="hljs-params">node</span>): | |
| buffer = <span class="hljs-string">""</span> | |
| <span class="hljs-keyword">for</span> chunk <span class="hljs-keyword">in</span> node: | |
| size = <span class="hljs-built_in">len</span>(chunk) | |
| chunk_hash = compute_chunk_hash(chunk) | |
| buffer += <span class="hljs-string">f"<span class="hljs-subst">{chunk_hash:x}</span> : <span class="hljs-subst">{size}</span>\n"</span> | |
| blake3(<span class="hljs-built_in">bytes</span>(buffer), key=INTERNAL_NODE_KEY)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="file-hashes" 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="#file-hashes"><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>File Hashes</span></h2> <p data-svelte-h="svelte-1jtatff">After chunking a whole file, to compute the file hash, follow the same procedure used to compute the xorb hash and then take that final hash as data to compute a blake3 keyed hash with a key that is all 0’s.</p> <p data-svelte-h="svelte-hh3b8l">This means create a MerkleTree using the same hashing functions described in the previous section. | |
| Then take the root node’s hash and compute a blake3 keyed hash with the key being 32 0-value bytes.</p> <p data-svelte-h="svelte-1n540og"><a href="https://github.com/huggingface/xet-core/blob/main/merklehash/src/aggregated_hashes.rs#L123-L125" rel="nofollow">reference implementation</a></p> <h2 class="relative group"><a id="term-verification-hashes" 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="#term-verification-hashes"><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>Term Verification Hashes</span></h2> <p data-svelte-h="svelte-18d9rp">When uploading a shard, each term in each file info in the shard MUST have a matching FileVerificationEntry section that contains a hash.</p> <p data-svelte-h="svelte-18be7u7">To generate this hash, take the chunk hashes for the specific range of chunks that make up the term and:</p> <ol data-svelte-h="svelte-1nbfhlz"><li><p><strong>Concatenate the raw hash bytes</strong>: Take all the chunk hashes in the range (from <code>chunk_index_start</code> to <code>chunk_index_end</code> in the xorb specified in the term) and concatenate their raw 32-byte representations together in order.</p></li> <li><p><strong>Apply keyed hash</strong>: Compute a blake3 keyed hash of the concatenated bytes using the following verification key (VERIFICATION_KEY):</p></li></ol> <h3 class="relative group"><a id="verificationkey" 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="#verificationkey"><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>VERIFICATION_KEY</span></h3> <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-punctuation">[</span> | |
| <span class="hljs-number">127</span><span class="hljs-punctuation">,</span> <span class="hljs-number">24</span><span class="hljs-punctuation">,</span> <span class="hljs-number">87</span><span class="hljs-punctuation">,</span> <span class="hljs-number">214</span><span class="hljs-punctuation">,</span> <span class="hljs-number">206</span><span class="hljs-punctuation">,</span> <span class="hljs-number">86</span><span class="hljs-punctuation">,</span> <span class="hljs-number">237</span><span class="hljs-punctuation">,</span> <span class="hljs-number">102</span><span class="hljs-punctuation">,</span> <span class="hljs-number">18</span><span class="hljs-punctuation">,</span> <span class="hljs-number">127</span><span class="hljs-punctuation">,</span> <span class="hljs-number">249</span><span class="hljs-punctuation">,</span> <span class="hljs-number">19</span><span class="hljs-punctuation">,</span> <span class="hljs-number">231</span><span class="hljs-punctuation">,</span> <span class="hljs-number">165</span><span class="hljs-punctuation">,</span> <span class="hljs-number">195</span><span class="hljs-punctuation">,</span> <span class="hljs-number">243</span><span class="hljs-punctuation">,</span> <span class="hljs-number">164</span><span class="hljs-punctuation">,</span> <span class="hljs-number">205</span><span class="hljs-punctuation">,</span> <span class="hljs-number">38</span><span class="hljs-punctuation">,</span> <span class="hljs-number">213</span><span class="hljs-punctuation">,</span> <span class="hljs-number">181</span><span class="hljs-punctuation">,</span> <span class="hljs-number">219</span><span class="hljs-punctuation">,</span> <span class="hljs-number">73</span><span class="hljs-punctuation">,</span> <span class="hljs-number">230</span><span class="hljs-punctuation">,</span> <span class="hljs-number">65</span><span class="hljs-punctuation">,</span> <span class="hljs-number">36</span><span class="hljs-punctuation">,</span> <span class="hljs-number">152</span><span class="hljs-punctuation">,</span> <span class="hljs-number">127</span><span class="hljs-punctuation">,</span> <span class="hljs-number">40</span><span class="hljs-punctuation">,</span> <span class="hljs-number">251</span><span class="hljs-punctuation">,</span> <span class="hljs-number">148</span><span class="hljs-punctuation">,</span> <span class="hljs-number">195</span> | |
| <span class="hljs-punctuation">]</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1habaob">The result of the blake3 keyed hash is the verification hash that MUST be used in the FileVerificationEntry for the term.</p> <p data-svelte-h="svelte-1a87ss8"><a href="https://github.com/huggingface/xet-core/blob/main/mdb_shard/src/chunk_verification.rs#L4-L16" rel="nofollow">reference implementation</a></p> <h3 class="relative group"><a id="example-python-code-for-the-verification-hash" 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="#example-python-code-for-the-verification-hash"><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>Example Python code for the verification hash</span></h3> <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">def</span> <span class="hljs-title function_">verification_hash_function</span>(<span class="hljs-params">term</span>): | |
| buffer = <span class="hljs-built_in">bytes</span>() | |
| <span class="hljs-comment"># note chunk ranges are end exclusive</span> | |
| <span class="hljs-keyword">for</span> chunk_hash <span class="hljs-keyword">in</span> term.xorb.chunk_hashes[term.chunk_index_start : term.chunk_index_end]: | |
| buffer.extend(<span class="hljs-built_in">bytes</span>(chunk_hash)) | |
| <span class="hljs-keyword">return</span> blake3(buffer, key=VERIFICATION_KEY)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="reference-files" 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="#reference-files"><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>Reference Files</span></h2> <p data-svelte-h="svelte-106smfh">Reference files are provided in Hugging Face Dataset repository <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files" rel="nofollow">xet-team/xet-spec-reference-files</a>.</p> <p data-svelte-h="svelte-zalecs">In this repository there are a number of different samples implementors can use to verify hash computations.</p> <blockquote data-svelte-h="svelte-ccbbrv"><p>Note that all hashes are represented as strings. | |
| To get the raw value of these hashes you must invert the endianness of each byte octet in the hash string, reversing the procedure described in <a href="./api#converting-hashes-to-strings">api</a>.</p></blockquote> <h3 class="relative group"><a id="chunk-hashes-sample" 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="#chunk-hashes-sample"><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>Chunk Hashes Sample</span></h3> <p data-svelte-h="svelte-16y0ek8">There are 3 chunks files, for each file name, the first 64 characters are the string format of the chunk hash of the data in the file:</p> <ul data-svelte-h="svelte-1fxoa4s"><li><a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/b10aa1dc71c61661de92280c41a188aabc47981739b785724a099945d8dc5ce4.chunk" rel="nofollow">b10aa1dc71c61661de92280c41a188aabc47981739b785724a099945d8dc5ce4.chunk</a></li> <li><a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/26255591fa803b6baf25d88c315b8a6f5153d5bcfdf18ec5ef526264e0ccc907.chunk" rel="nofollow">26255591fa803b6baf25d88c315b8a6f5153d5bcfdf18ec5ef526264e0ccc907.chunk</a></li> <li><a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/099cb228194fe640e36a6c7d274ee5ed3a714ccd557a0951d9b6b43a7292b5d1.chunk" rel="nofollow">099cb228194fe640e36a6c7d274ee5ed3a714ccd557a0951d9b6b43a7292b5d1.chunk</a></li></ul> <h3 class="relative group"><a id="file-hash-sample" 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="#file-hash-sample"><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>File Hash Sample</span></h3> <p data-svelte-h="svelte-g3zk4y">The <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files" rel="nofollow">xet-team/xet-spec-reference-files</a> repository contains the original file | |
| <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv</a>.</p> <p data-svelte-h="svelte-fwmkut">When processed through the Xet upload protocol the chunks that are produced for this file are listed (formatted <code><hash> <length></code>) in the file | |
| <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv.chunks" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv.chunks</a>.</p> <p data-svelte-h="svelte-rac1s">Using these chunks to compute a file hash of the entire file the result is the hash stored in the file | |
| <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv.xet-file-hash" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv.xet-file-hash</a> or the raw value <code>118a53328412787fee04011dcf82fdc4acf3a4a1eddec341c910d30a306aaf97</code>.</p> <h3 class="relative group"><a id="xorb-hash-sample" 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="#xorb-hash-sample"><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>Xorb Hash Sample</span></h3> <p data-svelte-h="svelte-rn2oha">All of the chunks of <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv</a> can fit into 1 single xorb.</p> <p data-svelte-h="svelte-1hsvxc0">The xorb produced with all of the chunks in order for this file can be found serialized in file <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb" rel="nofollow">eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb</a>.</p> <p data-svelte-h="svelte-iyfjm7">The hash of this xorb is <code>eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632</code>, the value in <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv.xet-xorb-hash" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv.xet-xorb-hash</a>.</p> <p data-svelte-h="svelte-1r234cl">The chunks that make up this xorb are listed in a file <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb.chunks" rel="nofollow">eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb.chunks</a>; | |
| note this file is equivalent to <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv.chunks" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv.chunks</a>.</p> <h3 class="relative group"><a id="range-hash-sample" 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="#range-hash-sample"><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>Range Hash Sample</span></h3> <p data-svelte-h="svelte-1eepk7q">In the reconstruction of <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/Electric_Vehicle_Population_Data_20250917.csv" rel="nofollow">Electric_Vehicle_Population_Data_20250917.csv</a> | |
| with xorb <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb" rel="nofollow">eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632</a> there is 1 range that contains all 796 chunks.</p> <p data-svelte-h="svelte-e3x7l">The verification range hash for this range is the value in <a href="https://huggingface.co/datasets/xet-team/xet-spec-reference-files/blob/main/eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb.range-hash" rel="nofollow">eea25d6ee393ccae385820daed127b96ef0ea034dfb7cf6da3a950ce334b7632.xorb.range-hash</a> | |
| which is <code>d81c11b1fc9bc2a25587108c675bbfe65ca2e5d350b0cd92c58329fcc8444178</code>.</p> <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/xet/hashing.md" 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_1t7h0ns = { | |
| assets: "/docs/xet/pr_2272/en", | |
| base: "/docs/xet/pr_2272/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/xet/pr_2272/en/_app/immutable/entry/start.7209fe0c.js"), | |
| import("/docs/xet/pr_2272/en/_app/immutable/entry/app.54268a84.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 9], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 54.7 kB
- Xet hash:
- d1709a33d7150f542235c4d4ddd29da5f9a721db9e7bfe574eaf3aea66862145
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.