相关文章推荐
曾经爱过的猴子
·
罗马内战——罗马共和国的解体和帝制的建立_新 ...
·
4 月前
·
健壮的排球
·
(ibm)股票公司摘要_美股_新浪财经_新浪网
·
5 月前
·
温文尔雅的橙子
·
四月是你的谎言tv和oad的区别- 抖音
·
8 月前
·
忐忑的镜子
·
宝马高性能SUV中美价格对比,X4M竟然是香 ...
·
1 年前
·
胡子拉碴的牛肉面
·
生理学_百度百科
·
1 年前
·
小百科
›
Conduct a Vector Similarity Search Milvus documentation
vector
谦逊的红豆
10 月前
</noscript><div id="___gatsby"><div style="outline:none" tabindex="-1" id="gatsby-focus-wrapper"><header class="index-module--header--jlRI9 index-module--light--2gO8U docHeader index-module--posSticky--Wq9Vh"><div class="index-module--headerContainer--VF15S headerContainer"><div class="index-module--logoSection--4ogSS"><a hreflang="en" href="/"><img src="data:image/svg+xml;base64,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" alt="milvus-logo"/></a><style data-emotion="css 12i6tf2">.css-12i6tf2{margin:0;-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;border-width:0;border-style:solid;border-color:rgba(0, 0, 0, 0.12);border-bottom-width:thin;margin-left:16px;margin-right:16px;margin:0 13px;opacity:0.3;border:1px solid #d1d1d1;-webkit-transform:scaleX(0.5);-moz-transform:scaleX(0.5);-ms-transform:scaleX(0.5);transform:scaleX(0.5);}@media(max-width: 1024px){.css-12i6tf2{margin:0 10px;}}@media(max-width: 744px){.css-12i6tf2{margin:0 6px;}}</style><hr class="MuiDivider-root MuiDivider-middle css-12i6tf2"/><a href="https://lfaidata.foundation/projects/" target="_blank" rel="noopener noreferrer" style="display:inline-block;line-height:0"><span class="index-module--lfaiLogo--nxF7b"/></a></div><div class="index-module--desktopHeaderBar--2tgXR"><div class="index-module--leftSection--Qvvap"><ul class="index-module--menu--KGPVd"><li><a class="index-module--menuItem--hfVbG" hreflang="en" href="/docs">Docs</a></li><li><button class="index-module--menuItem--hfVbG">Tutorials</button></li><li><button class="index-module--menuItem--hfVbG">Tools</button></li><li><a class="index-module--menuItem--hfVbG" hreflang="en" href="/blog">Blog</a></li><li><a class="index-module--menuItem--hfVbG" hreflang="en" href="/community">Community</a></li></ul></div><div class="index-module--rightSection--s0szn"><div class="index-module--actionBar--78eap"><div class="index-module--gitBtnsWrapper--cbosR"><div class="index-module--gitBtnWrapper--4tD20 "><a href="https://github.com/milvus-io/milvus" class="index-module--link--3plah" target="_blank" rel="noopener noreferrer"><span class="index-module--iconWrapper--UDUtV"><svg width="20" height="20" viewbox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><g clip-path="url(#clip0_5149_4597)"><rect width="20" height="20" fill="white"/><path fill-rule="evenodd" clip-rule="evenodd" d="M10 1C5.0275 1 1 5.0275 1 10C1 13.9825 3.57625 17.3463 7.15375 18.5388C7.60375 18.6175 7.7725 18.3475 7.7725 18.1113C7.7725 17.8975 7.76125 17.1888 7.76125 16.435C5.5 16.8513 4.915 15.8837 4.735 15.3775C4.63375 15.1187 4.195 14.32 3.8125 14.1062C3.4975 13.9375 3.0475 13.5212 3.80125 13.51C4.51 13.4987 5.01625 14.1625 5.185 14.4325C5.995 15.7937 7.28875 15.4113 7.80625 15.175C7.885 14.59 8.12125 14.1962 8.38 13.9712C6.3775 13.7462 4.285 12.97 4.285 9.5275C4.285 8.54875 4.63375 7.73875 5.2075 7.10875C5.1175 6.88375 4.8025 5.96125 5.2975 4.72375C5.2975 4.72375 6.05125 4.4875 7.7725 5.64625C8.4925 5.44375 9.2575 5.3425 10.0225 5.3425C10.7875 5.3425 11.5525 5.44375 12.2725 5.64625C13.9938 4.47625 14.7475 4.72375 14.7475 4.72375C15.2425 5.96125 14.9275 6.88375 14.8375 7.10875C15.4113 7.73875 15.76 8.5375 15.76 9.5275C15.76 12.9812 13.6563 13.7462 11.6538 13.9712C11.98 14.2525 12.2613 14.7925 12.2613 15.6363C12.2613 16.84 12.25 17.8075 12.25 18.1113C12.25 18.3475 12.4188 18.6288 12.8688 18.5388C16.4238 17.3463 19 13.9712 19 10C19 5.0275 14.9725 1 10 1V1Z" fill="black"/></g><defs><clippath id="clip0_5149_4597"><rect width="20" height="20" fill="white"/></clippath></defs></svg></span><span class="index-module--iconText---em9M">Stars</span><span class="index-module--stat--1XQOz">0</span></a></div></div></div><a href="https://cloud.zilliz.com/signup" target="_blank" hreflang="en"><button class="index-module--startBtn--zExZn">Try Managed Milvus <span>FREE</span><svg width="20" height="20" viewbox="0 0 20 20" fill="none"><path d="M12 3.5L18.364 9.86396L12 16.2279" stroke="white" stroke-width="2"/><path d="M18 10H1" stroke="white" stroke-width="2"/></svg></button></a></div></div><button class="index-module--hamburg--+gAuq "><span class="index-module--top--noPo9"/><span class="index-module--middle--tLjx0"/><span class="index-module--bottom--NCTWD"/></button></div></header><div class="doc-temp-container"><section class="index-module--adjustableMenuContainer--cBhiP"><div class="index-module--floatContainer--Kegle" role="menu" tabindex="0"><div class="index-module--content--gmAWS" role="menu" tabindex="0"><aside class="left-nav leftNav-module--aside--IKoAH"><div class="DocSearchWrapper"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><svg width="20" height="20" class="DocSearch-Search-Icon" viewbox="0 0 20 20"><path d="M14.386 14.386l4.0877 4.0877-4.0877-4.0877c-2.9418 2.9419-7.7115 2.9419-10.6533 0-2.9419-2.9418-2.9419-7.7115 0-10.6533 2.9418-2.9419 7.7115-2.9419 10.6533 0 2.9419 2.9418 2.9419 7.7115 0 10.6533z" stroke="currentColor" fill="none" fill-rule="evenodd" stroke-linecap="round" stroke-linejoin="round"/></svg><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"/></button></div><div class="selector-container leftNav-module--selectorContainer--g-0+A"><a class="leftNav-module--homeBtn--s36RQ" hreflang="en" href="/docs">Home</a><style data-emotion="css tzsjye">.css-tzsjye{display:-webkit-inline-box;display:-webkit-inline-flex;display:-ms-inline-flexbox;display:inline-flex;-webkit-flex-direction:column;-ms-flex-direction:column;flex-direction:column;position:relative;min-width:0;padding:0;margin:0;border:0;vertical-align:top;width:100%;}</style><div class="MuiFormControl-root MuiFormControl-fullWidth selector leftNav-module--selector--Po3jV css-tzsjye"><style data-emotion="css-global 1prfaxn">@-webkit-keyframes mui-auto-fill{from{display:block;}}@keyframes mui-auto-fill{from{display:block;}}@-webkit-keyframes mui-auto-fill-cancel{from{display:block;}}@keyframes mui-auto-fill-cancel{from{display:block;}}</style><style data-emotion="css fvipm8">.css-fvipm8{font-family:"Roboto","Helvetica","Arial",sans-serif;font-weight:400;font-size:1rem;line-height:1.4375em;letter-spacing:0.00938em;color:rgba(0, 0, 0, 0.87);box-sizing:border-box;position:relative;cursor:text;display:-webkit-inline-box;display:-webkit-inline-flex;display:-ms-inline-flexbox;display:inline-flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;position:relative;border-radius:4px;}.css-fvipm8.Mui-disabled{color:rgba(0, 0, 0, 0.38);cursor:default;}.css-fvipm8:hover .MuiOutlinedInput-notchedOutline{border-color:rgba(0, 0, 0, 0.87);}@media (hover: none){.css-fvipm8:hover .MuiOutlinedInput-notchedOutline{border-color:rgba(0, 0, 0, 0.23);}}.css-fvipm8.Mui-focused .MuiOutlinedInput-notchedOutline{border-color:#1976d2;border-width:2px;}.css-fvipm8.Mui-error .MuiOutlinedInput-notchedOutline{border-color:#d32f2f;}.css-fvipm8.Mui-disabled .MuiOutlinedInput-notchedOutline{border-color:rgba(0, 0, 0, 0.26);}</style><div class="MuiInputBase-root MuiOutlinedInput-root MuiInputBase-colorPrimary MuiInputBase-formControl MuiInputBase-sizeSmall css-fvipm8"><style data-emotion="css 1o6z5ng">.css-1o6z5ng{font:inherit;letter-spacing:inherit;color:currentColor;padding:4px 0 5px;border:0;box-sizing:content-box;background:none;height:1.4375em;margin:0;-webkit-tap-highlight-color:transparent;display:block;min-width:0;width:100%;-webkit-animation-name:mui-auto-fill-cancel;animation-name:mui-auto-fill-cancel;-webkit-animation-duration:10ms;animation-duration:10ms;padding-top:1px;padding:8.5px 14px;}.css-1o6z5ng::-webkit-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-1o6z5ng::-moz-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-1o6z5ng:-ms-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-1o6z5ng::-ms-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-1o6z5ng:focus{outline:0;}.css-1o6z5ng:invalid{box-shadow:none;}.css-1o6z5ng::-webkit-search-decoration{-webkit-appearance:none;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng::-webkit-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng::-moz-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng:-ms-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng::-ms-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng:focus::-webkit-input-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng:focus::-moz-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng:focus:-ms-input-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-1o6z5ng:focus::-ms-input-placeholder{opacity:0.42;}.css-1o6z5ng.Mui-disabled{opacity:1;-webkit-text-fill-color:rgba(0, 0, 0, 0.38);}.css-1o6z5ng:-webkit-autofill{-webkit-animation-duration:5000s;animation-duration:5000s;-webkit-animation-name:mui-auto-fill;animation-name:mui-auto-fill;}.css-1o6z5ng:-webkit-autofill{border-radius:inherit;}</style><style data-emotion="css 182didf">.css-182didf{-moz-appearance:none;-webkit-appearance:none;-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;border-radius:4px;cursor:pointer;font:inherit;letter-spacing:inherit;color:currentColor;padding:4px 0 5px;border:0;box-sizing:content-box;background:none;height:1.4375em;margin:0;-webkit-tap-highlight-color:transparent;display:block;min-width:0;width:100%;-webkit-animation-name:mui-auto-fill-cancel;animation-name:mui-auto-fill-cancel;-webkit-animation-duration:10ms;animation-duration:10ms;padding-top:1px;padding:8.5px 14px;}.css-182didf:focus{border-radius:4px;}.css-182didf::-ms-expand{;}.css-182didf.Mui-disabled{cursor:default;}.css-182didf[multiple]{height:auto;}.css-182didf:not([multiple]) option,.css-182didf:not([multiple]) optgroup{background-color:#fff;}.css-182didf.css-182didf.css-182didf{padding-right:32px;}.css-182didf.MuiSelect-select{height:auto;min-height:1.4375em;text-overflow:ellipsis;white-space:nowrap;overflow:hidden;}.css-182didf::-webkit-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-182didf::-moz-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-182didf:-ms-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-182didf::-ms-input-placeholder{color:currentColor;opacity:0.42;-webkit-transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:opacity 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;}.css-182didf:focus{outline:0;}.css-182didf:invalid{box-shadow:none;}.css-182didf::-webkit-search-decoration{-webkit-appearance:none;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf::-webkit-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf::-moz-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf:-ms-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf::-ms-input-placeholder{opacity:0!important;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf:focus::-webkit-input-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf:focus::-moz-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf:focus:-ms-input-placeholder{opacity:0.42;}label[data-shrink=false]+.MuiInputBase-formControl .css-182didf:focus::-ms-input-placeholder{opacity:0.42;}.css-182didf.Mui-disabled{opacity:1;-webkit-text-fill-color:rgba(0, 0, 0, 0.38);}.css-182didf:-webkit-autofill{-webkit-animation-duration:5000s;animation-duration:5000s;-webkit-animation-name:mui-auto-fill;animation-name:mui-auto-fill;}.css-182didf:-webkit-autofill{border-radius:inherit;}</style><div tabindex="0" role="button" aria-expanded="false" aria-haspopup="listbox" aria-labelledby="version-select-label version-select" id="version-select" class="MuiSelect-select MuiSelect-outlined MuiInputBase-input MuiOutlinedInput-input MuiInputBase-inputSizeSmall css-182didf"><a aria-current="page" class="leftNav-module--selectorItem--h3-V8" hreflang="en" href="/docs/search.md">v2.3.x</a></div><style data-emotion="css 1k3x8v3">.css-1k3x8v3{bottom:0;left:0;opacity:0;pointer-events:none;width:100%;box-sizing:border-box;}</style><input value="v2.3.x" aria-hidden="true" tabindex="-1" class="MuiSelect-nativeInput css-1k3x8v3"/><style data-emotion="css bi4s6q">.css-bi4s6q{right:7px;top:calc(50% - .5em);pointer-events:none;color:rgba(0, 0, 0, 0.54);}.css-bi4s6q.Mui-disabled{color:rgba(0, 0, 0, 0.26);}</style><style data-emotion="css 1636szt">.css-1636szt{-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;width:1em;height:1em;display:inline-block;fill:currentColor;-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;-webkit-transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;font-size:1.5rem;right:7px;top:calc(50% - .5em);pointer-events:none;color:rgba(0, 0, 0, 0.54);}.css-1636szt.Mui-disabled{color:rgba(0, 0, 0, 0.26);}</style><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium MuiSelect-icon MuiSelect-iconOutlined css-1636szt" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ArrowDropDownIcon"><path d="M7 10l5 5 5-5z"/></svg><style data-emotion="css 19w1uun">.css-19w1uun{border-color:rgba(0, 0, 0, 0.23);}</style><style data-emotion="css igs3ac">.css-igs3ac{text-align:left;bottom:0;right:0;top:-5px;left:0;margin:0;padding:0 8px;pointer-events:none;border-radius:inherit;border-style:solid;border-width:1px;overflow:hidden;min-width:0%;border-color:rgba(0, 0, 0, 0.23);}</style><fieldset aria-hidden="true" class="MuiOutlinedInput-notchedOutline css-igs3ac"><style data-emotion="css ihdtdm">.css-ihdtdm{float:unset;width:auto;overflow:hidden;padding:0;line-height:11px;-webkit-transition:width 150ms cubic-bezier(0.0, 0, 0.2, 1) 0ms;transition:width 150ms cubic-bezier(0.0, 0, 0.2, 1) 0ms;}</style><legend class="css-ihdtdm"><span class="notranslate"></span></legend></fieldset></div></div></div><style data-emotion="css 12mehxg">.css-12mehxg{padding:0;margin:0;list-style:none;outline:0;}</style><ul role="tree" aria-multiselectable="false" class="MuiTreeView-root mv3-tree-view leftNav-module--tree--WFhiO css-12mehxg" tabindex="0"><style data-emotion="css 105mfs8">.css-105mfs8{list-style:none;margin:0;padding:0;outline:0;}</style><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><style data-emotion="css yuu8jj">.css-yuu8jj{padding:0 8px;width:100%;display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;cursor:pointer;-webkit-tap-highlight-color:transparent;}.css-yuu8jj:hover{background-color:rgba(0, 0, 0, 0.04);}@media (hover: none){.css-yuu8jj:hover{background-color:transparent;}}.css-yuu8jj.Mui-disabled{opacity:0.38;background-color:transparent;}.css-yuu8jj.Mui-focused{background-color:rgba(0, 0, 0, 0.12);}.css-yuu8jj.Mui-selected{background-color:rgba(25, 118, 210, 0.08);}.css-yuu8jj.Mui-selected:hover{background-color:rgba(25, 118, 210, 0.12);}@media (hover: none){.css-yuu8jj.Mui-selected:hover{background-color:rgba(25, 118, 210, 0.08);}}.css-yuu8jj.Mui-selected.Mui-focused{background-color:rgba(25, 118, 210, 0.2);}.css-yuu8jj .MuiTreeItem-iconContainer{margin-right:4px;width:15px;display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;-webkit-box-pack:center;-ms-flex-pack:center;-webkit-justify-content:center;justify-content:center;}.css-yuu8jj .MuiTreeItem-iconContainer svg{font-size:18px;}.css-yuu8jj .MuiTreeItem-label{width:100%;min-width:0;padding-left:4px;position:relative;font-family:"Roboto","Helvetica","Arial",sans-serif;font-weight:400;font-size:1rem;line-height:1.5;letter-spacing:0.00938em;}</style><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><style data-emotion="css vubbuv">.css-vubbuv{-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;width:1em;height:1em;display:inline-block;fill:currentColor;-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;-webkit-transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;font-size:1.5rem;}</style><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">About Milvus</div></div><style data-emotion="css 1jozaee">.css-1jozaee{margin:0;padding:0;margin-left:17px;}</style></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Get Started</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="true" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content Mui-expanded"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ExpandMoreIcon"><path d="M16.59 8.59 12 13.17 7.41 8.59 6 10l6 6 6-6z"/></svg></div><div class="MuiTreeItem-label">User Guide</div></div><style data-emotion="css 1xxsnna">.css-1xxsnna{height:auto;overflow:visible;-webkit-transition:height 300ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:height 300ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;margin:0;padding:0;margin-left:17px;}</style><ul class="MuiCollapse-root MuiCollapse-vertical MuiTreeItem-group MuiCollapse-entered css-1xxsnna" style="min-height:0px" role="group"><style data-emotion="css hboir5">.css-hboir5{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;width:100%;}</style><div class="MuiCollapse-wrapper MuiCollapse-vertical css-hboir5"><style data-emotion="css 8atqhb">.css-8atqhb{width:100%;}</style><div class="MuiCollapse-wrapperInner MuiCollapse-vertical css-8atqhb"><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a class="mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}" hreflang="en" href="/docs/manage_connection.md">Manage Milvus Connections</a></div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a class="mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}" hreflang="en" href="/docs/manage_databases.md">Manage Databases</a></div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Manage Collections</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Manage Partitions</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Manage Data</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Manage Indexes</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="true" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content Mui-expanded"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ExpandMoreIcon"><path d="M16.59 8.59 12 13.17 7.41 8.59 6 10l6 6 6-6z"/></svg></div><div class="MuiTreeItem-label">Search and Query</div></div><ul class="MuiCollapse-root MuiCollapse-vertical MuiTreeItem-group MuiCollapse-entered css-1xxsnna" style="min-height:0px" role="group"><div class="MuiCollapse-wrapper MuiCollapse-vertical css-hboir5"><div class="MuiCollapse-wrapperInner MuiCollapse-vertical css-8atqhb"><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-selected="true" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content Mui-selected"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a aria-current="page" class="mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}" hreflang="en" href="/docs/search.md">Search</a></div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a class="mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}" hreflang="en" href="/docs/query.md">Query</a></div></div></li></div></div></ul></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a target="_blank" href="https://milvus.io/bootcamp" rel="noopener noreferrer" class="CustomIconLink-module--link--P45EA mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}"><span><svg width="24" height="24" stroke-width="1.5" viewbox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M14 11.9976C14 9.5059 11.683 7 8.85714 7C8.52241 7 7.41904 7.00001 7.14286 7.00001C4.30254 7.00001 2 9.23752 2 11.9976C2 14.376 3.70973 16.3664 6 16.8714C6.36756 16.9525 6.75006 16.9952 7.14286 16.9952" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round"/><path d="M10 11.9976C10 14.4893 12.317 16.9952 15.1429 16.9952C15.4776 16.9952 16.581 16.9952 16.8571 16.9952C19.6975 16.9952 22 14.7577 22 11.9976C22 9.6192 20.2903 7.62884 18 7.12383C17.6324 7.04278 17.2499 6.99999 16.8571 6.99999" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round"/></svg></span>Bootcamp</a></div></div></li></div></div></ul></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Administration Guide</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Integrations</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"/><div class="MuiTreeItem-label"><a class="mv3-item-link ()=>{const menuTree=document.querySelector('.mv3-tree-view');window.sessionStorage.setItem(SCROLL_TOP,menuTree.scrollTop);}" hreflang="en" href="/docs/benchmark.md">Benchmarks</a></div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Tools</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Reference</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">Example Applications</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">FAQs</div></div></li><li class="MuiTreeItem-root leftNav-module--treeItem---MapO css-105mfs8" role="treeitem" aria-expanded="false" tabindex="-1"><div class="css-yuu8jj MuiTreeItem-content"><div class="MuiTreeItem-iconContainer"><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="ChevronRightIcon"><path d="M10 6 8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"/></svg></div><div class="MuiTreeItem-label">API reference</div></div></li></ul></aside></div><button class="index-module--lineWrapper--yJc44"><span class="index-module--dragLine--7RgkJ"/><span class="index-module--iconWrapper--uuia1" role="menu" tabindex="0"><style data-emotion="css vubbuv">.css-vubbuv{-webkit-user-select:none;-moz-user-select:none;-ms-user-select:none;user-select:none;width:1em;height:1em;display:inline-block;fill:currentColor;-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;-webkit-transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;transition:fill 200ms cubic-bezier(0.4, 0, 0.2, 1) 0ms;font-size:1.5rem;}</style><svg class="MuiSvgIcon-root MuiSvgIcon-fontSizeMedium css-vubbuv" focusable="false" aria-hidden="true" viewbox="0 0 24 24" data-testid="KeyboardArrowRightIcon"><path d="M8.59 16.59 13.17 12 8.59 7.41 10 6l6 6-6 6-1.41-1.41z"/></svg></span></button></div></section><div class="doc-right-container"><div class="doc-content-container"><div class="doc-post-wrapper doc-style"><div class="doc-post-content"><div class="tab-wrapper"><a href="search.md" class="active ">Vector Similarity Search</a><a href="hybridsearch.md" class="">Hybrid Search</a><a href="within_range.md" class="">Range Search</a></div> <h1 id="Conduct-a-Vector-Similarity-Search" style="position:relative;">Conduct a Vector Similarity Search<a href="#Conduct-a-Vector-Similarity-Search" aria-label="Conduct a Vector Similarity Search permalink" class="icon-wrapper after"><svg aria-hidden="true" focusable="false" height="20" version="1.1" viewbox="0 0 16 16" width="16"><path fill="#0093c6" fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"/></svg></a></h1> <p>This topic describes how to search entities with Milvus.</p> <p>A vector similarity search in Milvus calculates the distance between query vector(s) and vectors in the collection with specified similarity metrics, and returns the most similar results. You can perform a <a href="hybridsearch.md">hybrid search</a> by specifying a <a href="boolean.md">boolean expression</a> that filters the scalar field or the primary key field.</p> <p>The following example shows how to perform a vector similarity search on a 2000-row dataset of book ID (primary key), word count (scalar field), and book introduction (vector field), simulating the situation that you search for certain books based on their vectorized introductions. Milvus will return the most similar results according to the query vector and search parameters you have defined.</p> <h2 id="Load-collection" style="position:relative;">Load collection<a href="#Load-collection" aria-label="Load collection permalink" class="icon-wrapper after"><svg aria-hidden="true" focusable="false" height="20" version="1.1" viewbox="0 0 16 16" width="16"><path fill="#0093c6" fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"/></svg></a></h2> <p>All search and query operations within Milvus are executed in memory. Load the collection to memory before conducting a vector similarity search.</p> <a href="#python">Python </a> <a href="#javascript">Node.js</a> <pre><code class="language-python">from pymilvus import Collection collection = Collection("book") # Get an existing collection. collection.load() <pre><code class="language-javascript">await milvusClient.loadCollection({ collection_name: "book", <pre><code class="language-go">err := milvusClient.LoadCollection( context.Background(), // ctx "book", // CollectionName false // async if err != nil { log.Fatal("failed to load collection:", err.Error()) <pre><code class="language-java">milvusClient.loadCollection( LoadCollectionParam.newBuilder() .withCollectionName("book") .build() <pre><code class="language-shell">load -c book <pre><code class="language-curl">curl -X 'POST' \ 'http://localhost:9091/api/v1/collection/load' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "collection_name": "book" <h2 id="Prepare-search-parameters" style="position:relative;">Prepare search parameters<a href="#Prepare-search-parameters" aria-label="Prepare search parameters permalink" class="icon-wrapper after"><svg aria-hidden="true" focusable="false" height="20" version="1.1" viewbox="0 0 16 16" width="16"><path fill="#0093c6" fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"/></svg></a></h2> <p>Prepare the parameters that suit your search scenario. The following example defines that the search will calculate the distance with Euclidean distance, and retrieve vectors from ten closest clusters built by the IVF_FLAT index.</p> <a href="#python">Python </a> <a href="#javascript">Node.js</a> <pre><code class="language-python">search_params = { "metric_type": "L2", "offset": 0, "ignore_growing": False, "params": {"nprobe": 10} <pre><code class="language-javascript">const searchParams = { params: { nprobe: 1024 } <pre><code class="language-go">sp, _ := entity.NewIndexIvfFlatSearchParam( // NewIndex*SearchParam func 10, // searchParam opt := client.SearchQueryOptionFunc(func(option *client.SearchQueryOption) { option.Limit = 3 option.Offset = 0 option.ConsistencyLevel = entity.ClStrong option.IgnoreGrowing = false <pre><code class="language-java">final Integer SEARCH_K = 2; // TopK final String SEARCH_PARAM = "{\"nprobe\":10, \"offset\":0}"; // Params <pre><code class="language-shell">search Collection name (book): book The vectors of search data(the length of data is number of query (nq), the dim of every vector in data must be equal to vector field’s of collection. You can also import a csv file without headers): [[0.1, 0.2]] The vector field used to search of collection (book_intro): book_intro Metric type: L2 Search parameter nprobe's value: 10 The max number of returned record, also known as topk: 10 The boolean expression used to filter attribute []: The names of partitions to search (split by "," if multiple) ['_default'] []: timeout []: Guarantee Timestamp(It instructs Milvus to see all operations performed before a provided timestamp. If no such timestamp is provided, then Milvus will search all operations performed to date) [0]: Travel Timestamp(Specify a timestamp in a search to get results based on a data view) [0]: <pre><code class="language-curl"># Search entities based on a given vector. curl --request POST \ --url '${MILVUS_HOST}:${MILVUS_PORT}/v1/vector/search' \ --header 'Authorization: Bearer <TOKEN>' \ --header 'accept: application/json' \ --header 'content-type: application/json' -d '{ "collectionName": "collection1", "vector": [0.0128121, 0.029119, .... , 0.09121] # Search entities and return specific fields. curl --request POST \ --url '${MILVUS_HOST}:${MILVUS_PORT}/v1/vector/search' \ --header 'Authorization: Bearer <TOKEN>' \ --header 'accept: application/json' \ --header 'content-type: application/json' -d '{ "collectionName": "collection1", "outputFields": ["id", "name", "feature", "distance"], "vector": [0.0128121, 0.029119, .... , 0.09121], "filter": "id in (1, 2, 3)", "limit": 100, "offset": 0 <p>Output:</p> "code": 200, "data": {} <td><code>metric_type</code></td> <td>Method used to measure the distance between vectors during search. It should be the same as the one specified for the index-building process. See <a href="metric.md">Simlarity Metrics</a> for more information.</td> <td><code>offset</code></td> <td>Number of entities to skip during the search. The sum of this value and <code>limit</code> of the <code>search</code> method should be less than <code>16384</code>. For example, if you want the 9th and 10th nearest neighbors to the query vector, set <code>limit</code> to <code>2</code> and <code>offset</code> to <code>8</code>.</td> <td><code>ignore_growing</code></td> <td>Whether to ignore growing segments during similarity searches. The value defaults to <code>False</code>, indicating that searches involve growing segments.</td> <td><code>params</code></td> <td>Search parameter(s) specific to the specified index type. See <a href="index.md">Vector Index</a> for more information. Possible options are as follows: <ul> <li><code>nprobe</code> Indicates the number of cluster units to search. This parameter is available only when <code>index_type</code> is set to <code>IVF_FLAT</code>, <code>IVF_SQ8</code>, or <code>IVF_PQ</code>. The value should be less than <code>nlist</code> specified for the index-building process.</li> <li><code>ef</code> Indicates the search scope. This parameter is available only when <code>index_type</code> is set to <code>HNSW</code>. The value should be within the range from <code>top_k</code> to <code>32768</code>.</li> <li><code>radius</code> Indicates the angle where the vector with the least similarity resides.</li> <li><code>range_filter</code> Indicates the filter used to filter vector field values whose similarity to the query vector falls into a specific range.</li> <td><code>params</code></td> <td>Search parameter(s) specific to the index. See <a href="index.md">Vector Index</a> for more information. Possible options are as follows:<ul> <li><code>nprobe</code> Indicates the number of cluster units to search. This parameter is available only when <code>index_type</code> is set to <code>IVF_FLAT</code>, <code>IVF_SQ8</code>, or <code>IVF_PQ</code>. The value should be less than <code>nlist</code> specified for the index-building process.</li> <li><code>ef</code> Indicates the search scope. This parameter is available only when <code>index_type</code> is set to <code>HNSW</code>. The value should be within the range from <code>top_k</code> to <code>32768</code>.</li> <td><code>NewIndex*SearchParam func</code></td> <td>Function to create <code>entity.SearchParam</code> according to different index types.</td> <td>For floating point vectors: <li><code>NewIndexFlatSearchParam()</code> (FLAT)</li> <li><code>NewIndexIvfFlatSearchParam(nprobe int)</code> (IVF_FLAT)</li> <li><code>NewIndexIvfSQ8SearchParam(nprobe int)</code> (IVF_SQ8)</li> <li><code>NewIndexIvfPQSearchParam(nprobe int)</code> (RNSG)</li> <li><code>NewIndexHNSWSearchParam(ef int)</code> (HNSW)</li> For binary vectors: <li><code>NewIndexBinFlatSearchParam(nprobe int)</code> (BIN_FLAT)</li> <li><code>NewIndexBinIvfFlatSearchParam(nprobe int)</code> (BIN_IVF_FLAT)</li> <td>Search parameter(s) specific to the index returned by the preceding functions.</td> <td>See <a href="index.md">Vector Index</a> for more information. </td> <td>Options for ANN searches.</td> <li><code>Limit</code> Indicates the number of entities to return.</li> <li><code>Offset</code> Indicates the number of entities to skip during the search. The sum of this parameter and <code>Limit</code> should be less than <code>16384</code>. For example, if you want the 9th and 10th nearest neighbors to the query vector, set <code>limit</code> to <code>2</code> and <code>offset</code> to <code>8</code>.</li> <li><code>ConsistencyLevel</code> Indicates the consistency level applied during the search.</li> <li><code>Ignore Growing</code> Indicates whether to ignore growing segments during similarity searches. The value defaults to <code>False</code>, indicating that searches involve growing segments. </li> <td><code>SEARCH_PARAM</code></td> <td>Search parameter(s) specific to the index.</td> <td>See <a href="index.md">Vector Index</a> for more information. Possible options are as follows:<ul> <li><code>nprobe</code> Indicates the number of cluster units to search. This parameter is available only when <code>index_type</code> is set to <code>IVF_FLAT</code>, <code>IVF_SQ8</code>, or <code>IVF_PQ</code>. The value should be less than <code>nlist</code> specified for the index-building process.</li> <li><code>ef</code> Indicates the search scope. This parameter is available only when <code>index_type</code> is set to <code>HNSW</code>. The value should be within the range from <code>top_k</code> to <code>32768</code>.</li> <li><code>metric_type</code> Indicates the metric type used in the search. It should be the same as the one specified when you index the collection.</li> <li><code>limit</code> Indicates the number of entities to return starting from the last skippped entity.</li> <li><code>offset</code> Indicates the number of entities to skip during the search. The sum of this value and <code>topK</code> of the <code>withTopK()</code> method should be less than <code>16384</code>. For example, if you want the 9th and 10th nearest neighbors to the query vector, set <code>topK</code> to <code>2</code> and <code>offset</code> to <code>8</code>.</li> <td><code>limit</code></td> <td>The maximum number of entities to return.<br/>The sum of this parameter value and <code>offset</code> should be less than <code>1024</code>.<br/>The value defaults to <code>100</code>.<br/>The value ranges from <code>1</code> to <code>100</code></td> <td><code>offset</code></td> <td>The number of entities to skip in the search results.<br/>The sum of this parameter value and <code>limit</code> should not be greater than <code>1024</code>.<br/>The maximum value is <code>1024</code>. For example, if you want the 9th and 10th nearest neighbors to the query vector, set <code>limit</code> to <code>2</code> and <code>offset</code> to <code>8</code>.</td> <td><code>outputFields</code></td> <td>An array of fields to return along with the search results.</td> <td><code>vector</code></td> <td>The query vector in the form of a list of floating numbers.</td> <h2 id="Conduct-a-vector-search" style="position:relative;">Conduct a vector search<a href="#Conduct-a-vector-search" aria-label="Conduct a vector search permalink" class="icon-wrapper after"><svg aria-hidden="true" focusable="false" height="20" version="1.1" viewbox="0 0 16 16" width="16"><path fill="#0093c6" fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"/></svg></a></h2> <p>Search vectors with Milvus. To search in a specific <a href="glossary.md#Partition">partition</a>, specify the list of partition names.</p> <p>Milvus supports setting consistency level specifically for a search. The example in this topic sets the consistency level as <code>Strong</code>. You can also set the consistency level as <code>Bounded</code>, <code>Session</code> or <code>Eventually</code>. See <a href="consistency.md">Consistency</a> for more information about the four consistency levels in Milvus.</p> <p>When conducting vector searches using GPU-enabled Milvus, the number of returned entities should meet the following requirements:</p> <li><strong>GPU_IVF_FLAT</strong>: The number of returned entities should be less than 256.</li> <li><strong>GPU_IVF_PQ</strong>: The number of returned entities should be less than 1024.</li> <p>For details, refer to <a href="index.md">In-memory Index</a></p> <a href="#python">Python </a> <a href="#javascript">Node.js</a> <pre><code class="language-python">results = collection.search( data=[[0.1, 0.2]], anns_field="book_intro", # the sum of `offset` in `param` and `limit` # should be less than 16384. param=search_params, limit=10, expr=None, # set the names of the fields you want to # retrieve from the search result. output_fields=['title'], consistency_level="Strong" # get the IDs of all returned hits results[0].ids # get the distances to the query vector from all returned hits results[0].distances # get the value of an output field specified in the search request. hit = results[0][0] hit.entity.get('title') <pre><code class="language-javascript">const results = await milvusClient.search({ collection_name: "book", vector: [0.1, 0.2], filter: null, // the sum of `limit` and `offset` should be less than 16384. limit: 10, offset: 2, metric_type: MetricType.L2, param: searchParams, consistency_level: ConsistencyLevelEnum.Strong, <pre><code class="language-go">searchResult, err := milvusClient.Search( context.Background(), // ctx "book", // CollectionName []string{}, // partitionNames "", // expr []string{"book_id"}, // outputFields []entity.Vector{entity.FloatVector([]float32{0.1, 0.2})}, // vectors "book_intro", // vectorField entity.L2, // metricType 10, // topK sp, // sp if err != nil { log.Fatal("fail to search collection:", err.Error()) <pre><code class="language-java">List<String> search_output_fields = Arrays.asList("book_id"); List<List<Float>> search_vectors = Arrays.asList(Arrays.asList(0.1f, 0.2f)); SearchParam searchParam = SearchParam.newBuilder() .withCollectionName("book") .withConsistencyLevel(ConsistencyLevelEnum.STRONG) .withMetricType(MetricType.L2) .withOutFields(search_output_fields) .withTopK(SEARCH_K) .withVectors(search_vectors) .withVectorFieldName("book_intro") .withParams(SEARCH_PARAM) .build(); R<SearchResults> respSearch = milvusClient.search(searchParam); <pre><code class="language-shell"># Follow the previous step. <pre><code class="language-curl"># Follow the previous step. <td><code>limit</code></td> <td>Number of the results to return. The sum of this value and <code>offset</code> in <code>param</code> should be less than 16384.</td> <td>Boolean expression used to filter attribute. See <a href="boolean.md">Boolean Expression Rules</a> for more information.</td> <td><code>output_fields</code> (optional)</td> <td>Name of the field to return. Milvus supports returning the vector field.</td> <td><code>consistency_level</code> (optional)</td> <td>Consistency level of the search.</td> <td><code>vector</code> / <code>vectors</code></td> <td>Vectors to search with. Note that you should provide a list of floats if you choose to use <code>vector</code>. Otherwise, you should provide a list of float lists.</td> <td><code>vector_type</code></td> <td>Pre-check of binary or float vectors. <code>100</code> for binary vectors and <code>101</code> for float vectors.</td> <td><code>limit</code> (optional)</td> <td>Number of the results to return. The sum of this value and <code>offset</code> should be less than 16384.</td> <td><code>offset</code> (optional)</td> <td>Number of entities to skip. The sum of this value and <code>limit</code> should be less than 16384. For example, if you want the 9th and 10th nearest neighbors to the query vector, set <code>limit</code> to <code>2</code> and <code>offset</code> to <code>8</code>.</td> <td><code>filter</code> (optional)</td> <td>Boolean expression used to filter attribute. See <a href="boolean.md">Boolean Expression Rules</a> for more information.</td> <td><code>output_fields</code> (optional)</td> <td>Name of the field to return. Milvus supports returning the vector field.</td> <td><code>partitionNames</code></td> <td>List of names of the partitions to load. All partitions will be searched if it is left empty.</td> <td>Boolean expression used to filter attribute.</td> <td>See <a href="boolean.md">Boolean Expression Rules</a> for more information.</td> <td><code>output_fields</code></td> <td>Name of the field to return. Milvus supports returning the vector field.</td> <td><code>vectors</code></td> <td>Vectors to search with.</td> <td><code>vectorField</code></td> <td>Name of the field to search on.</td> <td><code>metricType</code></td> <td>Metric type used for search.</td> <td>This parameter must be set identical to the metric type used for index building.</td> <td>Number of the results to return. The sum of this value and that of <code>offset</code> in <code>WithOffset</code> of <code>opts</code> should be less than 16384.</td> <td><code>entity.SearchParam<code> specific to the index.</code></code></td> <td><code>MetricType</code></td> <td>Metric type used for search.</td> <td>This parameter must be set identical to the metric type used for index building.</td> <td><code>OutFields</code></td> <td>Name of the field to return.</td> <td><code>Vectors</code></td> <td>Vectors to search with.</td> <td><code>VectorFieldName</code></td> <td>Name of the field to search on.</td> <td>Boolean expression used to filter attribute.</td> <td>See <a href="boolean.md">Boolean Expression Rules</a> for more information.</td> <td><code>ConsistencyLevel</code></td> <td>The consistency level used in the query.</td> <td><code>STRONG</code>, <code>BOUNDED</code>, and<code>EVENTUALLY</code>.</td> <p>Check the primary key values of the most similar vectors and their distances.</p> <a href="#python">Python </a> <a href="#javascript">Node.js</a> <pre><code class="language-python">results[0].ids results[0].distances <pre><code class="language-javascript">console.log(results.results) <pre><code class="language-go">fmt.Printf("%#v\n", searchResult) for _, sr := range searchResult { fmt.Println(sr.IDs) fmt.Println(sr.Scores) <pre><code class="language-java">SearchResultsWrapper wrapperSearch = new SearchResultsWrapper(respSearch.getData().getResults()); System.out.println(wrapperSearch.getIDScore(0)); System.out.println(wrapperSearch.getFieldData("book_id", 0)); <pre><code class="language-shell"># Milvus CLI automatically returns the primary key values of the most similar vectors and their distances. <p>Release the collection loaded in Milvus to reduce memory consumption when the search is completed.</p> <a href="#python">Python </a> <a href="#javascript">Node.js</a> <pre><code class="language-python">collection.release() <pre><code class="language-javascript">await milvusClient.releaseCollection({ collection_name: "book",}); <pre><code class="language-go">err := milvusClient.ReleaseCollection( context.Background(), // ctx "book", // CollectionName if err != nil { log.Fatal("failed to release collection:", err.Error()) <pre><code class="language-java">milvusClient.releaseCollection( ReleaseCollectionParam.newBuilder() .withCollectionName("book") .build()); <pre><code class="language-shell">release -c book <pre><code class="language-curl">curl -X 'DELETE' \ 'http://localhost:9091/api/v1/collection/load' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "collection_name": "book" <h2 id="Limits" style="position:relative;">Limits<a href="#Limits" aria-label="Limits permalink" class="icon-wrapper after"><svg aria-hidden="true" focusable="false" height="20" version="1.1" viewbox="0 0 16 16" width="16"><path fill="#0093c6" fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"/></svg></a></h2> <th>Feature</th> <th>Maximum limit</th>
推荐文章
曾经爱过的猴子
·
罗马内战——罗马共和国的解体和帝制的建立_新浪军事_新浪网
4 月前
健壮的排球
·
(ibm)股票公司摘要_美股_新浪财经_新浪网
5 月前
温文尔雅的橙子
·
四月是你的谎言tv和oad的区别- 抖音
8 月前
忐忑的镜子
·
宝马高性能SUV中美价格对比,X4M竟然是香饽饽?-手机新浪汽车
1 年前
胡子拉碴的牛肉面
·
生理学_百度百科
1 年前