Spaces:
Running
Running
| <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head> | |
| <meta charset="utf-8"> | |
| <meta name="generator" content="quarto-1.6.40"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes"> | |
| <title>Simple RAG – Open-Source AI Cookbook</title> | |
| <style> | |
| code{white-space: pre-wrap;} | |
| span.smallcaps{font-variant: small-caps;} | |
| div.columns{display: flex; gap: min(4vw, 1.5em);} | |
| div.column{flex: auto; overflow-x: auto;} | |
| div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;} | |
| ul.task-list{list-style: none;} | |
| ul.task-list li input[type="checkbox"] { | |
| width: 0.8em; | |
| margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */ | |
| vertical-align: middle; | |
| } | |
| /* CSS for syntax highlighting */ | |
| pre > code.sourceCode { white-space: pre; position: relative; } | |
| pre > code.sourceCode > span { line-height: 1.25; } | |
| pre > code.sourceCode > span:empty { height: 1.2em; } | |
| .sourceCode { overflow: visible; } | |
| code.sourceCode > span { color: inherit; text-decoration: inherit; } | |
| div.sourceCode { margin: 1em 0; } | |
| pre.sourceCode { margin: 0; } | |
| @media screen { | |
| div.sourceCode { overflow: auto; } | |
| } | |
| @media print { | |
| pre > code.sourceCode { white-space: pre-wrap; } | |
| pre > code.sourceCode > span { display: inline-block; text-indent: -5em; padding-left: 5em; } | |
| } | |
| pre.numberSource code | |
| { counter-reset: source-line 0; } | |
| pre.numberSource code > span | |
| { position: relative; left: -4em; counter-increment: source-line; } | |
| pre.numberSource code > span > a:first-child::before | |
| { content: counter(source-line); | |
| position: relative; left: -1em; text-align: right; vertical-align: baseline; | |
| border: none; display: inline-block; | |
| -webkit-touch-callout: none; -webkit-user-select: none; | |
| -khtml-user-select: none; -moz-user-select: none; | |
| -ms-user-select: none; user-select: none; | |
| padding: 0 4px; width: 4em; | |
| } | |
| pre.numberSource { margin-left: 3em; padding-left: 4px; } | |
| div.sourceCode | |
| { } | |
| @media screen { | |
| pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; } | |
| } | |
| </style> | |
| <script src="../site_libs/quarto-nav/quarto-nav.js"></script> | |
| <script src="../site_libs/quarto-nav/headroom.min.js"></script> | |
| <script src="../site_libs/clipboard/clipboard.min.js"></script> | |
| <script src="../site_libs/quarto-search/autocomplete.umd.js"></script> | |
| <script src="../site_libs/quarto-search/fuse.min.js"></script> | |
| <script src="../site_libs/quarto-search/quarto-search.js"></script> | |
| <meta name="quarto:offset" content="../"> | |
| <script src="../site_libs/quarto-html/quarto.js"></script> | |
| <script src="../site_libs/quarto-html/popper.min.js"></script> | |
| <script src="../site_libs/quarto-html/tippy.umd.min.js"></script> | |
| <script src="../site_libs/quarto-html/anchor.min.js"></script> | |
| <link href="../site_libs/quarto-html/tippy.css" rel="stylesheet"> | |
| <link href="../site_libs/quarto-html/quarto-syntax-highlighting-549806ee2085284f45b00abea8c6df48.css" rel="stylesheet" id="quarto-text-highlighting-styles"> | |
| <script src="../site_libs/bootstrap/bootstrap.min.js"></script> | |
| <link href="../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet"> | |
| <link href="../site_libs/bootstrap/bootstrap-2be10d9e998f81ff6e49e26833438aa5.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light"> | |
| <script id="quarto-search-options" type="application/json">{ | |
| "location": "sidebar", | |
| "copy-button": false, | |
| "collapse-after": 3, | |
| "panel-placement": "start", | |
| "type": "textbox", | |
| "limit": 50, | |
| "keyboard-shortcut": [ | |
| "f", | |
| "/", | |
| "s" | |
| ], | |
| "show-item-context": false, | |
| "language": { | |
| "search-no-results-text": "No results", | |
| "search-matching-documents-text": "matching documents", | |
| "search-copy-link-title": "Copy link to search", | |
| "search-hide-matches-text": "Hide additional matches", | |
| "search-more-match-text": "more match in this document", | |
| "search-more-matches-text": "more matches in this document", | |
| "search-clear-button-title": "Clear", | |
| "search-text-placeholder": "", | |
| "search-detached-cancel-button-title": "Cancel", | |
| "search-submit-button-title": "Submit", | |
| "search-label": "Search" | |
| } | |
| }</script> | |
| <link rel="stylesheet" href="../styles.css"> | |
| </head> | |
| <body class="nav-sidebar docked"> | |
| <div id="quarto-search-results"></div> | |
| <header id="quarto-header" class="headroom fixed-top"> | |
| <nav class="quarto-secondary-nav"> | |
| <div class="container-fluid d-flex"> | |
| <button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }"> | |
| <i class="bi bi-layout-text-sidebar-reverse"></i> | |
| </button> | |
| <nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item">Open-Source AI Cookbook</li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Techniques</a></li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Zephyr & LangChain</a></li></ol></nav> | |
| <a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }"> | |
| </a> | |
| <button type="button" class="btn quarto-search-button" aria-label="Search" onclick="window.quartoOpenSearch();"> | |
| <i class="bi bi-search"></i> | |
| </button> | |
| </div> | |
| </nav> | |
| </header> | |
| <!-- content --> | |
| <div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article"> | |
| <!-- sidebar --> | |
| <nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto"> | |
| <div class="pt-lg-2 mt-2 text-left sidebar-header"> | |
| <div class="sidebar-title mb-0 py-0"> | |
| <a href="../">Open-Source AI Cookbook</a> | |
| </div> | |
| </div> | |
| <div class="mt-2 flex-shrink-0 align-items-center"> | |
| <div class="sidebar-search"> | |
| <div id="quarto-search" class="" title="Search"></div> | |
| </div> | |
| </div> | |
| <div class="sidebar-menu-container"> | |
| <ul class="list-unstyled mt-1"> | |
| <li class="sidebar-item sidebar-item-section"> | |
| <div class="sidebar-item-container"> | |
| <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true"> | |
| <span class="menu-text">About</span></a> | |
| <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section"> | |
| <i class="bi bi-chevron-right ms-2"></i> | |
| </a> | |
| </div> | |
| <ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show"> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../index.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">About Quarto</span></a> | |
| </div> | |
| </li> | |
| </ul> | |
| </li> | |
| <li class="sidebar-item sidebar-item-section"> | |
| <div class="sidebar-item-container"> | |
| <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true"> | |
| <span class="menu-text">Open-Source AI Cookbook</span></a> | |
| <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section"> | |
| <i class="bi bi-chevron-right ms-2"></i> | |
| </a> | |
| </div> | |
| <ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show"> | |
| <li class="sidebar-item sidebar-item-section"> | |
| <div class="sidebar-item-container"> | |
| <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true"> | |
| <span class="menu-text">RAG Techniques</span></a> | |
| <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section"> | |
| <i class="bi bi-chevron-right ms-2"></i> | |
| </a> | |
| </div> | |
| <ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth2 show"> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/rag_zephyr_langchain.html" class="sidebar-item-text sidebar-link active"> | |
| <span class="menu-text">RAG Zephyr & LangChain</span></a> | |
| </div> | |
| </li> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/advanced_rag.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">Advanced RAG</span></a> | |
| </div> | |
| </li> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/rag_evaluation.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">RAG Evaluation</span></a> | |
| </div> | |
| </li> | |
| </ul> | |
| </li> | |
| <li class="sidebar-item sidebar-item-section"> | |
| <div class="sidebar-item-container"> | |
| <a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true"> | |
| <span class="menu-text">Additional Techniques</span></a> | |
| <a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true" aria-label="Toggle section"> | |
| <i class="bi bi-chevron-right ms-2"></i> | |
| </a> | |
| </div> | |
| <ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth2 show"> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/automatic_embedding.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">Automatic Embedding</span></a> | |
| </div> | |
| </li> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/faiss.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">FAISS for Efficient Search</span></a> | |
| </div> | |
| </li> | |
| <li class="sidebar-item"> | |
| <div class="sidebar-item-container"> | |
| <a href="../notebooks/single_gpu.html" class="sidebar-item-text sidebar-link"> | |
| <span class="menu-text">Single GPU Optimization</span></a> | |
| </div> | |
| </li> | |
| </ul> | |
| </li> | |
| </ul> | |
| </li> | |
| </ul> | |
| </div> | |
| </nav> | |
| <div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div> | |
| <!-- margin-sidebar --> | |
| <div id="quarto-margin-sidebar" class="sidebar margin-sidebar"> | |
| <nav id="TOC" role="doc-toc" class="toc-active"> | |
| <h2 id="toc-title">On this page</h2> | |
| <ul> | |
| <li><a href="#prepare-the-data" id="toc-prepare-the-data" class="nav-link active" data-scroll-target="#prepare-the-data">Prepare the data</a></li> | |
| <li><a href="#create-the-embeddings-retriever" id="toc-create-the-embeddings-retriever" class="nav-link" data-scroll-target="#create-the-embeddings-retriever">Create the embeddings + retriever</a></li> | |
| <li><a href="#load-quantized-model" id="toc-load-quantized-model" class="nav-link" data-scroll-target="#load-quantized-model">Load quantized model</a></li> | |
| <li><a href="#setup-the-llm-chain" id="toc-setup-the-llm-chain" class="nav-link" data-scroll-target="#setup-the-llm-chain">Setup the LLM chain</a></li> | |
| <li><a href="#compare-the-results" id="toc-compare-the-results" class="nav-link" data-scroll-target="#compare-the-results">Compare the results</a></li> | |
| </ul> | |
| </nav> | |
| </div> | |
| <!-- main --> | |
| <main class="content" id="quarto-document-content"> | |
| <header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item">Open-Source AI Cookbook</li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Techniques</a></li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Zephyr & LangChain</a></li></ol></nav> | |
| <div class="quarto-title"> | |
| <h1 class="title">Simple RAG</h1> | |
| </div> | |
| <div class="quarto-title-meta"> | |
| </div> | |
| </header> | |
| <div id="78116675" class="cell" data-execution_count="1"> | |
| <div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="op">-</span>q torch transformers accelerate bitsandbytes transformers sentence<span class="op">-</span>transformers faiss<span class="op">-</span>gpu</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <div id="be6b2c06" class="cell" data-execution_count="2"> | |
| <div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="op">-</span>q langchain</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <div class="callout callout-style-default callout-note callout-titled"> | |
| <div class="callout-header d-flex align-content-center"> | |
| <div class="callout-icon-container"> | |
| <i class="callout-icon"></i> | |
| </div> | |
| <div class="callout-title-container flex-fill"> | |
| Note | |
| </div> | |
| </div> | |
| <div class="callout-body-container callout-body"> | |
| <p>If running in Google Colab, you may need to run this cell to make sure you’re using UTF-8 locale to install LangChain</p> | |
| <div id="4dc3a73a" class="cell" data-execution_count="3"> | |
| <div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> locale</span> | |
| <span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a>locale.getpreferredencoding <span class="op">=</span> <span class="kw">lambda</span>: <span class="st">"UTF-8"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| </div> | |
| </div> | |
| <section id="prepare-the-data" class="level2"> | |
| <h2 class="anchored" data-anchor-id="prepare-the-data">Prepare the data</h2> | |
| <p>In this example, we’ll load all of the issues (both open and closed) from <a href="https://github.com/huggingface/peft">PEFT library’s repo</a>.</p> | |
| <p>First, you need to acquire a <a href="https://github.com/settings/tokens?type=beta">GitHub personal access token</a> to access the GitHub API.</p> | |
| <div id="99d8d506" class="cell" data-execution_count="4"> | |
| <div class="sourceCode cell-code" id="annotated-cell-3"><pre class="sourceCode python code-annotation-code code-with-copy code-annotated"><code class="sourceCode python"><span id="annotated-cell-3-1"><a href="#annotated-cell-3-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> getpass <span class="im">import</span> getpass</span> | |
| <span id="annotated-cell-3-2"><a href="#annotated-cell-3-2" aria-hidden="true" tabindex="-1"></a></span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-3" data-target-annotation="1">1</button><span id="annotated-cell-3-3" class="code-annotation-target"><a href="#annotated-cell-3-3" aria-hidden="true" tabindex="-1"></a>ACCESS_TOKEN <span class="op">=</span> getpass(<span class="st">"YOUR_GITHUB_PERSONAL_TOKEN"</span>)</span><div class="code-annotation-gutter-bg"></div><div class="code-annotation-gutter"></div></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| <div class="cell-annotation"> | |
| <dl class="code-annotation-container-hidden code-annotation-container-grid"> | |
| <dt data-target-cell="annotated-cell-3" data-target-annotation="1">1</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-3" data-code-lines="3" data-code-annotation="1">You can also use an environment variable to store your token.</span> | |
| </dd> | |
| </dl> | |
| </div> | |
| </div> | |
| <p>Next, we’ll load all of the issues in the <a href="https://github.com/huggingface/peft">huggingface/peft</a> repo: - By default, pull requests are considered issues as well, here we chose to exclude them from data with by setting <code>include_prs=False</code> - Setting <code>state = "all"</code> means we will load both open and closed issues.</p> | |
| <div id="4aba18cd" class="cell" data-execution_count="5"> | |
| <div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.document_loaders <span class="im">import</span> GitHubIssuesLoader</span> | |
| <span id="cb4-2"><a href="#cb4-2" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb4-3"><a href="#cb4-3" aria-hidden="true" tabindex="-1"></a>loader <span class="op">=</span> GitHubIssuesLoader(</span> | |
| <span id="cb4-4"><a href="#cb4-4" aria-hidden="true" tabindex="-1"></a> repo<span class="op">=</span><span class="st">"huggingface/peft"</span>,</span> | |
| <span id="cb4-5"><a href="#cb4-5" aria-hidden="true" tabindex="-1"></a> access_token<span class="op">=</span>ACCESS_TOKEN,</span> | |
| <span id="cb4-6"><a href="#cb4-6" aria-hidden="true" tabindex="-1"></a> include_prs<span class="op">=</span><span class="va">False</span>,</span> | |
| <span id="cb4-7"><a href="#cb4-7" aria-hidden="true" tabindex="-1"></a> state<span class="op">=</span><span class="st">"all"</span></span> | |
| <span id="cb4-8"><a href="#cb4-8" aria-hidden="true" tabindex="-1"></a>)</span> | |
| <span id="cb4-9"><a href="#cb4-9" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb4-10"><a href="#cb4-10" aria-hidden="true" tabindex="-1"></a>docs <span class="op">=</span> loader.load()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <p>The content of individual GitHub issues may be longer than what an embedding model can take as input. If we want to embed all of the available content, we need to chunk the documents into appropriately sized pieces.</p> | |
| <p>The most common and straightforward approach to chunking is to define a fixed size of chunks and whether there should be any overlap between them. Keeping some overlap between chunks allows us to preserve some semantic context between the chunks.</p> | |
| <p>Other approaches are typically more involved and take into account the documents’ structure and context. For example, one may want to split a document based on sentences or paragraphs, or create chunks based on the</p> | |
| <p>The fixed-size chunking, however, works well for most common cases, so that is what we’ll do here.</p> | |
| <div id="1ee02e26" class="cell" data-execution_count="6"> | |
| <div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.text_splitter <span class="im">import</span> CharacterTextSplitter</span> | |
| <span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a>splitter <span class="op">=</span> CharacterTextSplitter(chunk_size<span class="op">=</span><span class="dv">512</span>, chunk_overlap<span class="op">=</span><span class="dv">30</span>)</span> | |
| <span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a>chunked_docs <span class="op">=</span> splitter.split_documents(docs)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| </section> | |
| <section id="create-the-embeddings-retriever" class="level2"> | |
| <h2 class="anchored" data-anchor-id="create-the-embeddings-retriever">Create the embeddings + retriever</h2> | |
| <p>Now that the docs are all of the appropriate size, we can create a database with their embeddings.</p> | |
| <p>To create document chunk embeddings we’ll use the <code>HuggingFaceEmbeddings</code> and the <a href="https://huggingface.co/BAAI/bge-base-en-v1.5"><code>BAAI/bge-base-en-v1.5</code></a> embeddings model. To create the vector database, we’ll use <code>FAISS</code>, a library developed by Facebook AI. This library offers efficient similarity search and clustering of dense vectors, which is what we need here. FAISS is currently one of the most used libraries for NN search in massive datasets.</p> | |
| <div class="callout callout-style-default callout-tip callout-titled"> | |
| <div class="callout-header d-flex align-content-center"> | |
| <div class="callout-icon-container"> | |
| <i class="callout-icon"></i> | |
| </div> | |
| <div class="callout-title-container flex-fill"> | |
| Tip | |
| </div> | |
| </div> | |
| <div class="callout-body-container callout-body"> | |
| <p>There are many other embeddings models available on the Hub, and you can keep an eye on the best performing ones by checking the <a href="https://huggingface.co/spaces/mteb/leaderboard">Massive Text Embedding Benchmark (MTEB) Leaderboard</a>.</p> | |
| </div> | |
| </div> | |
| <p>We’ll access both the embeddings model and FAISS via LangChain API.</p> | |
| <div id="3342a691" class="cell" data-execution_count="7"> | |
| <div class="sourceCode cell-code" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.vectorstores <span class="im">import</span> FAISS</span> | |
| <span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.embeddings <span class="im">import</span> HuggingFaceEmbeddings</span> | |
| <span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a>db <span class="op">=</span> FAISS.from_documents(chunked_docs,</span> | |
| <span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a> HuggingFaceEmbeddings(model_name<span class="op">=</span><span class="st">'BAAI/bge-base-en-v1.5'</span>))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <p>We need a way to return(retrieve) the documents given an unstructured query. For that, we’ll use the <code>as_retriever</code> method using the <code>db</code> as a backbone: - <code>search_type="similarity"</code> means we want to perform similarity search between the query and documents - <code>search_kwargs={'k': 4}</code> instructs the retriever to return top 4 results.</p> | |
| <div id="28bd25f2" class="cell" data-execution_count="8"> | |
| <div class="sourceCode cell-code" id="annotated-cell-7"><pre class="sourceCode python code-annotation-code code-with-copy code-annotated"><code class="sourceCode python"><span id="annotated-cell-7-1"><a href="#annotated-cell-7-1" aria-hidden="true" tabindex="-1"></a>retriever <span class="op">=</span> db.as_retriever(</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-7" data-target-annotation="1">1</button><span id="annotated-cell-7-2" class="code-annotation-target"><a href="#annotated-cell-7-2" aria-hidden="true" tabindex="-1"></a> search_type<span class="op">=</span><span class="st">"similarity"</span>,</span> | |
| <span id="annotated-cell-7-3"><a href="#annotated-cell-7-3" aria-hidden="true" tabindex="-1"></a> search_kwargs<span class="op">=</span>{<span class="st">'k'</span>: <span class="dv">4</span>}</span> | |
| <span id="annotated-cell-7-4"><a href="#annotated-cell-7-4" aria-hidden="true" tabindex="-1"></a>)</span><div class="code-annotation-gutter-bg"></div><div class="code-annotation-gutter"></div></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| <div class="cell-annotation"> | |
| <dl class="code-annotation-container-hidden code-annotation-container-grid"> | |
| <dt data-target-cell="annotated-cell-7" data-target-annotation="1">1</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-7" data-code-lines="2,3" data-code-annotation="1">The ideal search type is context dependent, and you should experiment to find the best one for your data.</span> | |
| </dd> | |
| </dl> | |
| </div> | |
| </div> | |
| <p>The vector database and retriever are now set up, next we need to set up the next piece of the chain - the model.</p> | |
| </section> | |
| <section id="load-quantized-model" class="level2"> | |
| <h2 class="anchored" data-anchor-id="load-quantized-model">Load quantized model</h2> | |
| <p>For this example, we chose <a href="https://huggingface.co/HuggingFaceH4/zephyr-7b-beta"><code>HuggingFaceH4/zephyr-7b-beta</code></a>, a small but powerful model. To make inference faster, we will load the quantized version of the model:</p> | |
| <div class="callout callout-style-default callout-tip callout-titled"> | |
| <div class="callout-header d-flex align-content-center"> | |
| <div class="callout-icon-container"> | |
| <i class="callout-icon"></i> | |
| </div> | |
| <div class="callout-title-container flex-fill"> | |
| Tip | |
| </div> | |
| </div> | |
| <div class="callout-body-container callout-body"> | |
| <p>With many models being released every week, you may want to substitute this model to the latest and greatest. The best way to keep track of open source LLMs is to check the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">Open-source LLM leaderboard</a>.</p> | |
| </div> | |
| </div> | |
| <div id="e5288d87" class="cell" data-execution_count="9"> | |
| <div class="sourceCode cell-code" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> torch</span> | |
| <span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> transformers <span class="im">import</span> AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig</span> | |
| <span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb7-4"><a href="#cb7-4" aria-hidden="true" tabindex="-1"></a>model_name <span class="op">=</span> <span class="st">'HuggingFaceH4/zephyr-7b-beta'</span></span> | |
| <span id="cb7-5"><a href="#cb7-5" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb7-6"><a href="#cb7-6" aria-hidden="true" tabindex="-1"></a>bnb_config <span class="op">=</span> BitsAndBytesConfig(</span> | |
| <span id="cb7-7"><a href="#cb7-7" aria-hidden="true" tabindex="-1"></a> load_in_4bit<span class="op">=</span><span class="va">True</span>,</span> | |
| <span id="cb7-8"><a href="#cb7-8" aria-hidden="true" tabindex="-1"></a> bnb_4bit_use_double_quant<span class="op">=</span><span class="va">True</span>,</span> | |
| <span id="cb7-9"><a href="#cb7-9" aria-hidden="true" tabindex="-1"></a> bnb_4bit_quant_type<span class="op">=</span><span class="st">"nf4"</span>,</span> | |
| <span id="cb7-10"><a href="#cb7-10" aria-hidden="true" tabindex="-1"></a> bnb_4bit_compute_dtype<span class="op">=</span>torch.bfloat16</span> | |
| <span id="cb7-11"><a href="#cb7-11" aria-hidden="true" tabindex="-1"></a>)</span> | |
| <span id="cb7-12"><a href="#cb7-12" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb7-13"><a href="#cb7-13" aria-hidden="true" tabindex="-1"></a>model <span class="op">=</span> AutoModelForCausalLM.from_pretrained(model_name, quantization_config<span class="op">=</span>bnb_config)</span> | |
| <span id="cb7-14"><a href="#cb7-14" aria-hidden="true" tabindex="-1"></a>tokenizer <span class="op">=</span> AutoTokenizer.from_pretrained(model_name)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| </section> | |
| <section id="setup-the-llm-chain" class="level2"> | |
| <h2 class="anchored" data-anchor-id="setup-the-llm-chain">Setup the LLM chain</h2> | |
| <p>Finally, we have all the pieces we need to set up the LLM chain.</p> | |
| <p>First, create a text_generation pipeline using the loaded model and its tokenizer.</p> | |
| <p>Next, create a prompt template - this should follow the format of the model, so if you substitute the model checkpoint, make sure to use the appropriate formatting.</p> | |
| <div id="389798fe" class="cell" data-execution_count="10"> | |
| <div class="sourceCode cell-code" id="annotated-cell-9"><pre class="sourceCode python code-annotation-code code-with-copy code-annotated"><code class="sourceCode python"><span id="annotated-cell-9-1"><a href="#annotated-cell-9-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.llms <span class="im">import</span> HuggingFacePipeline</span> | |
| <span id="annotated-cell-9-2"><a href="#annotated-cell-9-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.prompts <span class="im">import</span> PromptTemplate</span> | |
| <span id="annotated-cell-9-3"><a href="#annotated-cell-9-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> transformers <span class="im">import</span> pipeline</span> | |
| <span id="annotated-cell-9-4"><a href="#annotated-cell-9-4" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_core.output_parsers <span class="im">import</span> StrOutputParser</span> | |
| <span id="annotated-cell-9-5"><a href="#annotated-cell-9-5" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-6"><a href="#annotated-cell-9-6" aria-hidden="true" tabindex="-1"></a>text_generation_pipeline <span class="op">=</span> pipeline(</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="1">1</button><span id="annotated-cell-9-7" class="code-annotation-target"><a href="#annotated-cell-9-7" aria-hidden="true" tabindex="-1"></a> model<span class="op">=</span>model,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="2">2</button><span id="annotated-cell-9-8" class="code-annotation-target"><a href="#annotated-cell-9-8" aria-hidden="true" tabindex="-1"></a> tokenizer<span class="op">=</span>tokenizer,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="3">3</button><span id="annotated-cell-9-9" class="code-annotation-target"><a href="#annotated-cell-9-9" aria-hidden="true" tabindex="-1"></a> task<span class="op">=</span><span class="st">"text-generation"</span>,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="4">4</button><span id="annotated-cell-9-10" class="code-annotation-target"><a href="#annotated-cell-9-10" aria-hidden="true" tabindex="-1"></a> temperature<span class="op">=</span><span class="fl">0.2</span>,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="5">5</button><span id="annotated-cell-9-11" class="code-annotation-target"><a href="#annotated-cell-9-11" aria-hidden="true" tabindex="-1"></a> do_sample<span class="op">=</span><span class="va">True</span>,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="6">6</button><span id="annotated-cell-9-12" class="code-annotation-target"><a href="#annotated-cell-9-12" aria-hidden="true" tabindex="-1"></a> repetition_penalty<span class="op">=</span><span class="fl">1.1</span>,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="7">7</button><span id="annotated-cell-9-13" class="code-annotation-target"><a href="#annotated-cell-9-13" aria-hidden="true" tabindex="-1"></a> return_full_text<span class="op">=</span><span class="va">True</span>,</span> | |
| <button class="code-annotation-anchor" data-target-cell="annotated-cell-9" data-target-annotation="8">8</button><span id="annotated-cell-9-14" class="code-annotation-target"><a href="#annotated-cell-9-14" aria-hidden="true" tabindex="-1"></a> max_new_tokens<span class="op">=</span><span class="dv">400</span>,</span> | |
| <span id="annotated-cell-9-15"><a href="#annotated-cell-9-15" aria-hidden="true" tabindex="-1"></a>)</span> | |
| <span id="annotated-cell-9-16"><a href="#annotated-cell-9-16" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-17"><a href="#annotated-cell-9-17" aria-hidden="true" tabindex="-1"></a>llm <span class="op">=</span> HuggingFacePipeline(pipeline<span class="op">=</span>text_generation_pipeline)</span> | |
| <span id="annotated-cell-9-18"><a href="#annotated-cell-9-18" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-19"><a href="#annotated-cell-9-19" aria-hidden="true" tabindex="-1"></a>prompt_template <span class="op">=</span> <span class="st">"""</span></span> | |
| <span id="annotated-cell-9-20"><a href="#annotated-cell-9-20" aria-hidden="true" tabindex="-1"></a><span class="st"><|system|></span></span> | |
| <span id="annotated-cell-9-21"><a href="#annotated-cell-9-21" aria-hidden="true" tabindex="-1"></a><span class="st">Answer the question based on your knowledge. Use the following context to help:</span></span> | |
| <span id="annotated-cell-9-22"><a href="#annotated-cell-9-22" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-23"><a href="#annotated-cell-9-23" aria-hidden="true" tabindex="-1"></a><span class="sc">{context}</span></span> | |
| <span id="annotated-cell-9-24"><a href="#annotated-cell-9-24" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-25"><a href="#annotated-cell-9-25" aria-hidden="true" tabindex="-1"></a><span class="st"></s></span></span> | |
| <span id="annotated-cell-9-26"><a href="#annotated-cell-9-26" aria-hidden="true" tabindex="-1"></a><span class="st"><|user|></span></span> | |
| <span id="annotated-cell-9-27"><a href="#annotated-cell-9-27" aria-hidden="true" tabindex="-1"></a><span class="sc">{question}</span></span> | |
| <span id="annotated-cell-9-28"><a href="#annotated-cell-9-28" aria-hidden="true" tabindex="-1"></a><span class="st"></s></span></span> | |
| <span id="annotated-cell-9-29"><a href="#annotated-cell-9-29" aria-hidden="true" tabindex="-1"></a><span class="st"><|assistant|></span></span> | |
| <span id="annotated-cell-9-30"><a href="#annotated-cell-9-30" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-31"><a href="#annotated-cell-9-31" aria-hidden="true" tabindex="-1"></a><span class="st"> """</span></span> | |
| <span id="annotated-cell-9-32"><a href="#annotated-cell-9-32" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-33"><a href="#annotated-cell-9-33" aria-hidden="true" tabindex="-1"></a>prompt <span class="op">=</span> PromptTemplate(</span> | |
| <span id="annotated-cell-9-34"><a href="#annotated-cell-9-34" aria-hidden="true" tabindex="-1"></a> input_variables<span class="op">=</span>[<span class="st">"context"</span>, <span class="st">"question"</span>],</span> | |
| <span id="annotated-cell-9-35"><a href="#annotated-cell-9-35" aria-hidden="true" tabindex="-1"></a> template<span class="op">=</span>prompt_template,</span> | |
| <span id="annotated-cell-9-36"><a href="#annotated-cell-9-36" aria-hidden="true" tabindex="-1"></a>)</span> | |
| <span id="annotated-cell-9-37"><a href="#annotated-cell-9-37" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="annotated-cell-9-38"><a href="#annotated-cell-9-38" aria-hidden="true" tabindex="-1"></a>llm_chain <span class="op">=</span> prompt <span class="op">|</span> llm <span class="op">|</span> StrOutputParser()</span><div class="code-annotation-gutter-bg"></div><div class="code-annotation-gutter"></div></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| <div class="cell-annotation"> | |
| <dl class="code-annotation-container-hidden code-annotation-container-grid"> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="1">1</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="7" data-code-annotation="1">The pre-trained model for text generation.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="2">2</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="8" data-code-annotation="2">Tokenizer to preprocess input text and postprocess generated output.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="3">3</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="9" data-code-annotation="3">Specifies the task as text generation.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="4">4</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="10" data-code-annotation="4">Controls the randomness in the output generation. Lower values make the output more deterministic.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="5">5</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="11" data-code-annotation="5">Enables sampling to introduce randomness in the output generation.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="6">6</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="12" data-code-annotation="6">Penalizes repetition in the output to encourage diversity.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="7">7</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="13" data-code-annotation="7">Returns the full generated text including the input prompt.</span> | |
| </dd> | |
| <dt data-target-cell="annotated-cell-9" data-target-annotation="8">8</dt> | |
| <dd> | |
| <span data-code-cell="annotated-cell-9" data-code-lines="14" data-code-annotation="8">Limits the maximum number of new tokens generated.</span> | |
| </dd> | |
| </dl> | |
| </div> | |
| </div> | |
| <p>Note: <em>You can also use <code>tokenizer.apply_chat_template</code> to convert a list of messages (as dicts: <code>{'role': 'user', 'content': '(...)'}</code>) into a string with the appropriate chat format.</em></p> | |
| <p>Finally, we need to combine the <code>llm_chain</code> with the retriever to create a RAG chain. We pass the original question through to the final generation step, as well as the retrieved context docs:</p> | |
| <div id="2ad1978e" class="cell" data-execution_count="11"> | |
| <div class="sourceCode cell-code" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_core.runnables <span class="im">import</span> RunnablePassthrough</span> | |
| <span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a>retriever <span class="op">=</span> db.as_retriever()</span> | |
| <span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a></span> | |
| <span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a>rag_chain <span class="op">=</span> (</span> | |
| <span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a> {<span class="st">"context"</span>: retriever, <span class="st">"question"</span>: RunnablePassthrough()}</span> | |
| <span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a> <span class="op">|</span> llm_chain</span> | |
| <span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| </section> | |
| <section id="compare-the-results" class="level2"> | |
| <h2 class="anchored" data-anchor-id="compare-the-results">Compare the results</h2> | |
| <p>Let’s see the difference RAG makes in generating answers to the library-specific questions.</p> | |
| <div id="aa570a95" class="cell" data-execution_count="12"> | |
| <div class="sourceCode cell-code" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>question <span class="op">=</span> <span class="st">"How do you combine multiple adapters?"</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <p>First, let’s see what kind of answer we can get with just the model itself, no context added:</p> | |
| <div id="3c1688aa" class="cell" data-execution_count="13"> | |
| <div class="sourceCode cell-code" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>llm_chain.invoke({<span class="st">"context"</span>:<span class="st">""</span>, <span class="st">"question"</span>: question})</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <p>As you can see, the model interpreted the question as one about physical computer adapters, while in the context of PEFT, “adapters” refer to LoRA adapters. Let’s see if adding context from GitHub issues helps the model give a more relevant answer:</p> | |
| <div id="57388c24" class="cell" data-execution_count="14"> | |
| <div class="sourceCode cell-code" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>rag_chain.invoke(question)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div> | |
| </div> | |
| <p>As we can see, the added context, really helps the exact same model, provide a much more relevant and informed answer to the library-specific question.</p> | |
| <p>Notably, combining multiple adapters for inference has been added to the library, and one can find this information in the documentation, so for the next iteration of this RAG it may be worth including documentation embeddings.</p> | |
| </section> | |
| </main> <!-- /main --> | |
| <script id="quarto-html-after-body" type="application/javascript"> | |
| window.document.addEventListener("DOMContentLoaded", function (event) { | |
| const toggleBodyColorMode = (bsSheetEl) => { | |
| const mode = bsSheetEl.getAttribute("data-mode"); | |
| const bodyEl = window.document.querySelector("body"); | |
| if (mode === "dark") { | |
| bodyEl.classList.add("quarto-dark"); | |
| bodyEl.classList.remove("quarto-light"); | |
| } else { | |
| bodyEl.classList.add("quarto-light"); | |
| bodyEl.classList.remove("quarto-dark"); | |
| } | |
| } | |
| const toggleBodyColorPrimary = () => { | |
| const bsSheetEl = window.document.querySelector("link#quarto-bootstrap"); | |
| if (bsSheetEl) { | |
| toggleBodyColorMode(bsSheetEl); | |
| } | |
| } | |
| toggleBodyColorPrimary(); | |
| const icon = ""; | |
| const anchorJS = new window.AnchorJS(); | |
| anchorJS.options = { | |
| placement: 'right', | |
| icon: icon | |
| }; | |
| anchorJS.add('.anchored'); | |
| const isCodeAnnotation = (el) => { | |
| for (const clz of el.classList) { | |
| if (clz.startsWith('code-annotation-')) { | |
| return true; | |
| } | |
| } | |
| return false; | |
| } | |
| const onCopySuccess = function(e) { | |
| // button target | |
| const button = e.trigger; | |
| // don't keep focus | |
| button.blur(); | |
| // flash "checked" | |
| button.classList.add('code-copy-button-checked'); | |
| var currentTitle = button.getAttribute("title"); | |
| button.setAttribute("title", "Copied!"); | |
| let tooltip; | |
| if (window.bootstrap) { | |
| button.setAttribute("data-bs-toggle", "tooltip"); | |
| button.setAttribute("data-bs-placement", "left"); | |
| button.setAttribute("data-bs-title", "Copied!"); | |
| tooltip = new bootstrap.Tooltip(button, | |
| { trigger: "manual", | |
| customClass: "code-copy-button-tooltip", | |
| offset: [0, -8]}); | |
| tooltip.show(); | |
| } | |
| setTimeout(function() { | |
| if (tooltip) { | |
| tooltip.hide(); | |
| button.removeAttribute("data-bs-title"); | |
| button.removeAttribute("data-bs-toggle"); | |
| button.removeAttribute("data-bs-placement"); | |
| } | |
| button.setAttribute("title", currentTitle); | |
| button.classList.remove('code-copy-button-checked'); | |
| }, 1000); | |
| // clear code selection | |
| e.clearSelection(); | |
| } | |
| const getTextToCopy = function(trigger) { | |
| const codeEl = trigger.previousElementSibling.cloneNode(true); | |
| for (const childEl of codeEl.children) { | |
| if (isCodeAnnotation(childEl)) { | |
| childEl.remove(); | |
| } | |
| } | |
| return codeEl.innerText; | |
| } | |
| const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', { | |
| text: getTextToCopy | |
| }); | |
| clipboard.on('success', onCopySuccess); | |
| if (window.document.getElementById('quarto-embedded-source-code-modal')) { | |
| const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', { | |
| text: getTextToCopy, | |
| container: window.document.getElementById('quarto-embedded-source-code-modal') | |
| }); | |
| clipboardModal.on('success', onCopySuccess); | |
| } | |
| var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//); | |
| var mailtoRegex = new RegExp(/^mailto:/); | |
| var filterRegex = new RegExp('/' + window.location.host + '/'); | |
| var isInternal = (href) => { | |
| return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href); | |
| } | |
| // Inspect non-navigation links and adorn them if external | |
| var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)'); | |
| for (var i=0; i<links.length; i++) { | |
| const link = links[i]; | |
| if (!isInternal(link.href)) { | |
| // undo the damage that might have been done by quarto-nav.js in the case of | |
| // links that we want to consider external | |
| if (link.dataset.originalHref !== undefined) { | |
| link.href = link.dataset.originalHref; | |
| } | |
| } | |
| } | |
| function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) { | |
| const config = { | |
| allowHTML: true, | |
| maxWidth: 500, | |
| delay: 100, | |
| arrow: false, | |
| appendTo: function(el) { | |
| return el.parentElement; | |
| }, | |
| interactive: true, | |
| interactiveBorder: 10, | |
| theme: 'quarto', | |
| placement: 'bottom-start', | |
| }; | |
| if (contentFn) { | |
| config.content = contentFn; | |
| } | |
| if (onTriggerFn) { | |
| config.onTrigger = onTriggerFn; | |
| } | |
| if (onUntriggerFn) { | |
| config.onUntrigger = onUntriggerFn; | |
| } | |
| window.tippy(el, config); | |
| } | |
| const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]'); | |
| for (var i=0; i<noterefs.length; i++) { | |
| const ref = noterefs[i]; | |
| tippyHover(ref, function() { | |
| // use id or data attribute instead here | |
| let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href'); | |
| try { href = new URL(href).hash; } catch {} | |
| const id = href.replace(/^#\/?/, ""); | |
| const note = window.document.getElementById(id); | |
| if (note) { | |
| return note.innerHTML; | |
| } else { | |
| return ""; | |
| } | |
| }); | |
| } | |
| const xrefs = window.document.querySelectorAll('a.quarto-xref'); | |
| const processXRef = (id, note) => { | |
| // Strip column container classes | |
| const stripColumnClz = (el) => { | |
| el.classList.remove("page-full", "page-columns"); | |
| if (el.children) { | |
| for (const child of el.children) { | |
| stripColumnClz(child); | |
| } | |
| } | |
| } | |
| stripColumnClz(note) | |
| if (id === null || id.startsWith('sec-')) { | |
| // Special case sections, only their first couple elements | |
| const container = document.createElement("div"); | |
| if (note.children && note.children.length > 2) { | |
| container.appendChild(note.children[0].cloneNode(true)); | |
| for (let i = 1; i < note.children.length; i++) { | |
| const child = note.children[i]; | |
| if (child.tagName === "P" && child.innerText === "") { | |
| continue; | |
| } else { | |
| container.appendChild(child.cloneNode(true)); | |
| break; | |
| } | |
| } | |
| if (window.Quarto?.typesetMath) { | |
| window.Quarto.typesetMath(container); | |
| } | |
| return container.innerHTML | |
| } else { | |
| if (window.Quarto?.typesetMath) { | |
| window.Quarto.typesetMath(note); | |
| } | |
| return note.innerHTML; | |
| } | |
| } else { | |
| // Remove any anchor links if they are present | |
| const anchorLink = note.querySelector('a.anchorjs-link'); | |
| if (anchorLink) { | |
| anchorLink.remove(); | |
| } | |
| if (window.Quarto?.typesetMath) { | |
| window.Quarto.typesetMath(note); | |
| } | |
| if (note.classList.contains("callout")) { | |
| return note.outerHTML; | |
| } else { | |
| return note.innerHTML; | |
| } | |
| } | |
| } | |
| for (var i=0; i<xrefs.length; i++) { | |
| const xref = xrefs[i]; | |
| tippyHover(xref, undefined, function(instance) { | |
| instance.disable(); | |
| let url = xref.getAttribute('href'); | |
| let hash = undefined; | |
| if (url.startsWith('#')) { | |
| hash = url; | |
| } else { | |
| try { hash = new URL(url).hash; } catch {} | |
| } | |
| if (hash) { | |
| const id = hash.replace(/^#\/?/, ""); | |
| const note = window.document.getElementById(id); | |
| if (note !== null) { | |
| try { | |
| const html = processXRef(id, note.cloneNode(true)); | |
| instance.setContent(html); | |
| } finally { | |
| instance.enable(); | |
| instance.show(); | |
| } | |
| } else { | |
| // See if we can fetch this | |
| fetch(url.split('#')[0]) | |
| .then(res => res.text()) | |
| .then(html => { | |
| const parser = new DOMParser(); | |
| const htmlDoc = parser.parseFromString(html, "text/html"); | |
| const note = htmlDoc.getElementById(id); | |
| if (note !== null) { | |
| const html = processXRef(id, note); | |
| instance.setContent(html); | |
| } | |
| }).finally(() => { | |
| instance.enable(); | |
| instance.show(); | |
| }); | |
| } | |
| } else { | |
| // See if we can fetch a full url (with no hash to target) | |
| // This is a special case and we should probably do some content thinning / targeting | |
| fetch(url) | |
| .then(res => res.text()) | |
| .then(html => { | |
| const parser = new DOMParser(); | |
| const htmlDoc = parser.parseFromString(html, "text/html"); | |
| const note = htmlDoc.querySelector('main.content'); | |
| if (note !== null) { | |
| // This should only happen for chapter cross references | |
| // (since there is no id in the URL) | |
| // remove the first header | |
| if (note.children.length > 0 && note.children[0].tagName === "HEADER") { | |
| note.children[0].remove(); | |
| } | |
| const html = processXRef(null, note); | |
| instance.setContent(html); | |
| } | |
| }).finally(() => { | |
| instance.enable(); | |
| instance.show(); | |
| }); | |
| } | |
| }, function(instance) { | |
| }); | |
| } | |
| let selectedAnnoteEl; | |
| const selectorForAnnotation = ( cell, annotation) => { | |
| let cellAttr = 'data-code-cell="' + cell + '"'; | |
| let lineAttr = 'data-code-annotation="' + annotation + '"'; | |
| const selector = 'span[' + cellAttr + '][' + lineAttr + ']'; | |
| return selector; | |
| } | |
| const selectCodeLines = (annoteEl) => { | |
| const doc = window.document; | |
| const targetCell = annoteEl.getAttribute("data-target-cell"); | |
| const targetAnnotation = annoteEl.getAttribute("data-target-annotation"); | |
| const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation)); | |
| const lines = annoteSpan.getAttribute("data-code-lines").split(","); | |
| const lineIds = lines.map((line) => { | |
| return targetCell + "-" + line; | |
| }) | |
| let top = null; | |
| let height = null; | |
| let parent = null; | |
| if (lineIds.length > 0) { | |
| //compute the position of the single el (top and bottom and make a div) | |
| const el = window.document.getElementById(lineIds[0]); | |
| top = el.offsetTop; | |
| height = el.offsetHeight; | |
| parent = el.parentElement.parentElement; | |
| if (lineIds.length > 1) { | |
| const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]); | |
| const bottom = lastEl.offsetTop + lastEl.offsetHeight; | |
| height = bottom - top; | |
| } | |
| if (top !== null && height !== null && parent !== null) { | |
| // cook up a div (if necessary) and position it | |
| let div = window.document.getElementById("code-annotation-line-highlight"); | |
| if (div === null) { | |
| div = window.document.createElement("div"); | |
| div.setAttribute("id", "code-annotation-line-highlight"); | |
| div.style.position = 'absolute'; | |
| parent.appendChild(div); | |
| } | |
| div.style.top = top - 2 + "px"; | |
| div.style.height = height + 4 + "px"; | |
| div.style.left = 0; | |
| let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter"); | |
| if (gutterDiv === null) { | |
| gutterDiv = window.document.createElement("div"); | |
| gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter"); | |
| gutterDiv.style.position = 'absolute'; | |
| const codeCell = window.document.getElementById(targetCell); | |
| const gutter = codeCell.querySelector('.code-annotation-gutter'); | |
| gutter.appendChild(gutterDiv); | |
| } | |
| gutterDiv.style.top = top - 2 + "px"; | |
| gutterDiv.style.height = height + 4 + "px"; | |
| } | |
| selectedAnnoteEl = annoteEl; | |
| } | |
| }; | |
| const unselectCodeLines = () => { | |
| const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"]; | |
| elementsIds.forEach((elId) => { | |
| const div = window.document.getElementById(elId); | |
| if (div) { | |
| div.remove(); | |
| } | |
| }); | |
| selectedAnnoteEl = undefined; | |
| }; | |
| // Handle positioning of the toggle | |
| window.addEventListener( | |
| "resize", | |
| throttle(() => { | |
| elRect = undefined; | |
| if (selectedAnnoteEl) { | |
| selectCodeLines(selectedAnnoteEl); | |
| } | |
| }, 10) | |
| ); | |
| function throttle(fn, ms) { | |
| let throttle = false; | |
| let timer; | |
| return (...args) => { | |
| if(!throttle) { // first call gets through | |
| fn.apply(this, args); | |
| throttle = true; | |
| } else { // all the others get throttled | |
| if(timer) clearTimeout(timer); // cancel #2 | |
| timer = setTimeout(() => { | |
| fn.apply(this, args); | |
| timer = throttle = false; | |
| }, ms); | |
| } | |
| }; | |
| } | |
| const annoteTargets = window.document.querySelectorAll('.code-annotation-anchor'); | |
| for (let i=0; i<annoteTargets.length; i++) { | |
| const annoteTarget = annoteTargets[i]; | |
| const targetCell = annoteTarget.getAttribute("data-target-cell"); | |
| const targetAnnotation = annoteTarget.getAttribute("data-target-annotation"); | |
| const contentFn = () => { | |
| const content = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation)); | |
| if (content) { | |
| const tipContent = content.cloneNode(true); | |
| tipContent.classList.add("code-annotation-tip-content"); | |
| return tipContent.outerHTML; | |
| } | |
| } | |
| const config = { | |
| allowHTML: true, | |
| content: contentFn, | |
| onShow: (instance) => { | |
| selectCodeLines(instance.reference); | |
| instance.reference.classList.add('code-annotation-active'); | |
| window.tippy.hideAll(); | |
| }, | |
| onHide: (instance) => { | |
| unselectCodeLines(); | |
| instance.reference.classList.remove('code-annotation-active'); | |
| }, | |
| maxWidth: 300, | |
| delay: [50, 0], | |
| duration: [200, 0], | |
| offset: [5, 10], | |
| arrow: true, | |
| appendTo: function(el) { | |
| return el.parentElement.parentElement.parentElement; | |
| }, | |
| interactive: true, | |
| interactiveBorder: 10, | |
| theme: 'quarto', | |
| placement: 'right', | |
| popperOptions: { | |
| modifiers: [ | |
| { | |
| name: 'flip', | |
| options: { | |
| flipVariations: false, // true by default | |
| allowedAutoPlacements: ['right'], | |
| fallbackPlacements: ['right', 'top', 'top-start', 'top-end', 'bottom', 'bottom-start', 'bottom-end', 'left'], | |
| }, | |
| }, | |
| { | |
| name: 'preventOverflow', | |
| options: { | |
| mainAxis: false, | |
| altAxis: false | |
| } | |
| } | |
| ] | |
| } | |
| }; | |
| window.tippy(annoteTarget, config); | |
| } | |
| const findCites = (el) => { | |
| const parentEl = el.parentElement; | |
| if (parentEl) { | |
| const cites = parentEl.dataset.cites; | |
| if (cites) { | |
| return { | |
| el, | |
| cites: cites.split(' ') | |
| }; | |
| } else { | |
| return findCites(el.parentElement) | |
| } | |
| } else { | |
| return undefined; | |
| } | |
| }; | |
| var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]'); | |
| for (var i=0; i<bibliorefs.length; i++) { | |
| const ref = bibliorefs[i]; | |
| const citeInfo = findCites(ref); | |
| if (citeInfo) { | |
| tippyHover(citeInfo.el, function() { | |
| var popup = window.document.createElement('div'); | |
| citeInfo.cites.forEach(function(cite) { | |
| var citeDiv = window.document.createElement('div'); | |
| citeDiv.classList.add('hanging-indent'); | |
| citeDiv.classList.add('csl-entry'); | |
| var biblioDiv = window.document.getElementById('ref-' + cite); | |
| if (biblioDiv) { | |
| citeDiv.innerHTML = biblioDiv.innerHTML; | |
| } | |
| popup.appendChild(citeDiv); | |
| }); | |
| return popup.innerHTML; | |
| }); | |
| } | |
| } | |
| }); | |
| </script> | |
| </div> <!-- /content --> | |
| </body></html> |