| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>apache_beam.ml.transforms.embeddings.huggingface module — Apache Beam 2.56.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script> |
| <script type="text/javascript" src="_static/jquery.js"></script> |
| <script type="text/javascript" src="_static/underscore.js"></script> |
| <script type="text/javascript" src="_static/doctools.js"></script> |
| <script type="text/javascript" src="_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.ml.transforms.embeddings.tensorflow_hub module" href="apache_beam.ml.transforms.embeddings.tensorflow_hub.html" /> |
| <link rel="prev" title="apache_beam.ml.transforms.embeddings package" href="apache_beam.ml.transforms.embeddings.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 2.56.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.ml.html#subpackages">Subpackages</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.gcp.html">apache_beam.ml.gcp package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.inference.html">apache_beam.ml.inference package</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.ml.transforms.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="apache_beam.ml.transforms.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="index.html">Docs</a> »</li> |
| |
| <li><a href="apache_beam.ml.html">apache_beam.ml package</a> »</li> |
| |
| <li><a href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a> »</li> |
| |
| <li><a href="apache_beam.ml.transforms.embeddings.html">apache_beam.ml.transforms.embeddings package</a> »</li> |
| |
| <li>apache_beam.ml.transforms.embeddings.huggingface module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.ml.transforms.embeddings.huggingface.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="module-apache_beam.ml.transforms.embeddings.huggingface"> |
| <span id="apache-beam-ml-transforms-embeddings-huggingface-module"></span><h1>apache_beam.ml.transforms.embeddings.huggingface module<a class="headerlink" href="#module-apache_beam.ml.transforms.embeddings.huggingface" title="Permalink to this headline">¶</a></h1> |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.embeddings.huggingface.</code><code class="descname">SentenceTransformerEmbeddings</code><span class="sig-paren">(</span><em>model_name: str, columns: List[str], max_seq_length: Optional[int] = None, **kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#SentenceTransformerEmbeddings"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.ml.transforms.base.html#apache_beam.ml.transforms.base.EmbeddingsManager" title="apache_beam.ml.transforms.base.EmbeddingsManager"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.ml.transforms.base.EmbeddingsManager</span></code></a></p> |
| <p>Embedding config for sentence-transformers. This config can be used with |
| MLTransform to embed text data. Models are loaded using the RunInference |
| PTransform with the help of ModelHandler.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>model_name</strong> – Name of the model to use. The model should be hosted on |
| HuggingFace Hub or compatible with sentence_transformers.</li> |
| <li><strong>columns</strong> – List of columns to be embedded.</li> |
| <li><strong>max_seq_length</strong> – Max sequence length to use for the model if applicable.</li> |
| <li><strong>min_batch_size</strong> – The minimum batch size to be used for inference.</li> |
| <li><strong>max_batch_size</strong> – The maximum batch size to be used for inference.</li> |
| <li><strong>large_model</strong> – Whether to share the model across processes.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings.get_model_handler"> |
| <code class="descname">get_model_handler</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#SentenceTransformerEmbeddings.get_model_handler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings.get_model_handler" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings.get_ptransform_for_processing"> |
| <code class="descname">get_ptransform_for_processing</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span> → apache_beam.transforms.ptransform.PTransform<a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#SentenceTransformerEmbeddings.get_ptransform_for_processing"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.SentenceTransformerEmbeddings.get_ptransform_for_processing" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.embeddings.huggingface.</code><code class="descname">InferenceAPIEmbeddings</code><span class="sig-paren">(</span><em>hf_token: Optional[str], columns: List[str], model_name: Optional[str] = None, api_url: Optional[str] = None, **kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#InferenceAPIEmbeddings"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.ml.transforms.base.html#apache_beam.ml.transforms.base.EmbeddingsManager" title="apache_beam.ml.transforms.base.EmbeddingsManager"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.ml.transforms.base.EmbeddingsManager</span></code></a></p> |
| <p>Feature extraction using HuggingFace’s Inference API. |
| Intended to be used for feature-extraction. For other tasks, please |
| refer to <a class="reference external" href="https://huggingface.co/inference-api">https://huggingface.co/inference-api</a>.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>hf_token</strong> – HuggingFace token.</li> |
| <li><strong>columns</strong> – List of columns to be embedded.</li> |
| <li><strong>model_name</strong> – Model name used for feature extraction.</li> |
| <li><strong>api_url</strong> – API url for feature extraction. If specified, model_name will be |
| ignored. If none, the default url for feature extraction |
| will be used.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_token"> |
| <code class="descname">get_token</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#InferenceAPIEmbeddings.get_token"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_token" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.api_url"> |
| <code class="descname">api_url</code><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.api_url" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.authorization_token"> |
| <code class="descname">authorization_token</code><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.authorization_token" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_model_handler"> |
| <code class="descname">get_model_handler</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#InferenceAPIEmbeddings.get_model_handler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_model_handler" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_ptransform_for_processing"> |
| <code class="descname">get_ptransform_for_processing</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span> → apache_beam.transforms.ptransform.PTransform<a class="reference internal" href="_modules/apache_beam/ml/transforms/embeddings/huggingface.html#InferenceAPIEmbeddings.get_ptransform_for_processing"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.embeddings.huggingface.InferenceAPIEmbeddings.get_ptransform_for_processing" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="apache_beam.ml.transforms.embeddings.tensorflow_hub.html" class="btn btn-neutral float-right" title="apache_beam.ml.transforms.embeddings.tensorflow_hub module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.ml.transforms.embeddings.html" class="btn btn-neutral float-left" title="apache_beam.ml.transforms.embeddings package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |