| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="./"> |
| <head> |
| <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.ml.rag.chunking.langchain module — Apache Beam 2.67.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="_static/jquery.js?v=5d32c60e"></script> |
| <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="_static/documentation_options.js?v=959b4fbe"></script> |
| <script src="_static/doctools.js?v=9a2dae69"></script> |
| <script src="_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="_static/js/theme.js"></script> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.ml.rag.embeddings package" href="apache_beam.ml.rag.embeddings.html" /> |
| <link rel="prev" title="apache_beam.ml.rag.chunking.base module" href="apache_beam.ml.rag.chunking.base.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 role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="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="Navigation menu"> |
| <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.anomaly.html">apache_beam.ml.anomaly package</a></li> |
| <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.rag.html">apache_beam.ml.rag package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.ml.rag.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="apache_beam.ml.rag.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.ts.html">apache_beam.ml.ts package</a></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="Mobile navigation menu" > |
| <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="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.rag.html">apache_beam.ml.rag package</a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.rag.chunking.html">apache_beam.ml.rag.chunking package</a></li> |
| <li class="breadcrumb-item active">apache_beam.ml.rag.chunking.langchain module</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="_sources/apache_beam.ml.rag.chunking.langchain.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"> |
| |
| <section id="module-apache_beam.ml.rag.chunking.langchain"> |
| <span id="apache-beam-ml-rag-chunking-langchain-module"></span><h1>apache_beam.ml.rag.chunking.langchain module<a class="headerlink" href="#module-apache_beam.ml.rag.chunking.langchain" title="Link to this heading"></a></h1> |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.rag.chunking.langchain.LangChainChunker"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.rag.chunking.langchain.</span></span><span class="sig-name descname"><span class="pre">LangChainChunker</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">text_splitter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">document_field</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_fields</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.List" title="(in Python v3.13)"><span class="pre">List</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_id_fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Callable" title="(in Python v3.13)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="apache_beam.ml.rag.types.html#apache_beam.ml.rag.types.Chunk" title="apache_beam.ml.rag.types.Chunk"><span class="pre">Chunk</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/rag/chunking/langchain.html#LangChainChunker"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.rag.chunking.langchain.LangChainChunker" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.ml.rag.chunking.base.html#apache_beam.ml.rag.chunking.base.ChunkingTransformProvider" title="apache_beam.ml.rag.chunking.base.ChunkingTransformProvider"><code class="xref py py-class docutils literal notranslate"><span class="pre">ChunkingTransformProvider</span></code></a></p> |
| <p>A ChunkingTransformProvider that uses LangChain text splitters.</p> |
| <p>This provider integrates LangChain’s text splitting capabilities into |
| Beam’s MLTransform framework. It supports various text splitting strategies |
| through LangChain’s TextSplitter interface, including recursive character |
| splitting and other methods.</p> |
| <p>The provider: |
| - Takes documents with text content and metadata |
| - Splits text using configured LangChain splitter |
| - Preserves document metadata in resulting chunks |
| - Assigns unique IDs to chunks (configurable via chunk_id_fn)</p> |
| <dl> |
| <dt>Example usage:</dt><dd><p><a href="#id1"><span class="problematic" id="id2">``</span></a><a href="#id3"><span class="problematic" id="id4">`</span></a>python |
| from langchain.text_splitter import RecursiveCharacterTextSplitter</p> |
| <dl class="simple"> |
| <dt>splitter = RecursiveCharacterTextSplitter(</dt><dd><p>chunk_size=100, |
| chunk_overlap=20</p> |
| </dd> |
| </dl> |
| <p>)</p> |
| <p>chunker = LangChainChunker(text_splitter=splitter)</p> |
| <dl class="simple"> |
| <dt>with beam.Pipeline() as p:</dt><dd><dl class="simple"> |
| <dt>chunks = (</dt><dd><p>p |
| | beam.Create([{‘text’: ‘long document…’, ‘source’: ‘doc.txt’}]) |
| | MLTransform(…).with_transform(chunker))</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| <p><a href="#id5"><span class="problematic" id="id6">``</span></a><a href="#id7"><span class="problematic" id="id8">`</span></a></p> |
| </dd> |
| </dl> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>text_splitter</strong> – A LangChain TextSplitter instance that defines how |
| documents are split into chunks.</p></li> |
| <li><p><strong>metadata_fields</strong> – List of field names to copy from input documents to |
| chunk metadata. These fields will be preserved in each chunk created |
| from the document.</p></li> |
| <li><p><strong>chunk_id_fn</strong> – Optional function that take a Chunk and return str to |
| generate chunk IDs. If not provided, random UUIDs will be used.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.rag.chunking.langchain.LangChainChunker.get_splitter_transform"> |
| <span class="sig-name descname"><span class="pre">get_splitter_transform</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="apache_beam.transforms.ptransform.html#apache_beam.transforms.ptransform.PTransform" title="apache_beam.transforms.ptransform.PTransform"><span class="pre">PTransform</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="apache_beam.pvalue.html#apache_beam.pvalue.PCollection" title="apache_beam.pvalue.PCollection"><span class="pre">PCollection</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Dict" title="(in Python v3.13)"><span class="pre">Dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.13)"><span class="pre">Any</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="apache_beam.pvalue.html#apache_beam.pvalue.PCollection" title="apache_beam.pvalue.PCollection"><span class="pre">PCollection</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="apache_beam.ml.rag.types.html#apache_beam.ml.rag.types.Chunk" title="apache_beam.ml.rag.types.Chunk"><span class="pre">Chunk</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/rag/chunking/langchain.html#LangChainChunker.get_splitter_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.rag.chunking.langchain.LangChainChunker.get_splitter_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="apache_beam.ml.rag.chunking.base.html" class="btn btn-neutral float-left" title="apache_beam.ml.rag.chunking.base module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="apache_beam.ml.rag.embeddings.html" class="btn btn-neutral float-right" title="apache_beam.ml.rag.embeddings package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |
