TextUnit

A lightweight vector database for text retrieval in R with embedded
machine learning models and no external API (Application Programming
Interface) keys. Supports dense and hybrid search, optional HNSW
(Hierarchical Navigable Small World) approximate nearest-neighbor indexing,
faceted filters with ACL (Access Control List) metadata, command-line
tools, and a local dashboard built with 'shiny'. The HNSW method is
described by Malkov and Yashunin (2018) <doi:10.1109/TPAMI.2018.2889473>.

Kwadwo Daddy Nyame Owusu Boakye

VectrixDB

Lightweight Vector Database with Embedded Machine Learning
Models

TextUnit function

<p><div class="r6-fields"></div></p><dl>
<dt><code>id</code></dt>
<dd><p>Unique identifier</p></dd><p></p><p>
<dt><code>text</code></dt>
<dd><p>Text content</p></dd></p><p>
<dt><code>document_id</code></dt>
<dd><p>Source document</p></dd></p><p>
<dt><code>chunk_index</code></dt>
<dd><p>Index in document</p></dd></p><p>
<dt><code>start_char</code></dt>
<dd><p>Start position</p></dd></p><p>
<dt><code>end_char</code></dt>
<dd><p>End position</p></dd></p><p>
<dt><code>metadata</code></dt>
<dd><p>Additional metadata</p></dd></p><p>
</p></dl><p></p>

Public fields


<div class="section" id="public-methods">
<h3>Public methods</h3><p></p><p><ul>
<li><p><a href="/link/TextUnit%24new()?package=VectrixDB&version=1.1.2" data-mini-rdoc="VectrixDB::TextUnit$new()"><code>TextUnit$new()</code></a></p></li>
<li><p><a href="/link/TextUnit%24clone()?package=VectrixDB&version=1.1.2" data-mini-rdoc="VectrixDB::TextUnit$clone()"><code>TextUnit$clone()</code></a></p></li>
</ul></p><p></p></div><p><hr>
<a id="method-TextUnit-new"></a></p><div class="section" id="method-new-">
<h3>Method <code>new()</code></h3>
<p>Create a new TextUnit</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>TextUnit$new(
  id,
  text,
  document_id = NULL,
  chunk_index = 0,
  start_char = 0,
  end_char = 0,
  metadata = NULL
)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>id</code></dt>
<dd><p>Unique ID</p></dd></dl></div></p><p>
<dt><code>text</code></dt>
<dd><p>Content</p></dd></p><p>
<dt><code>document_id</code></dt>
<dd><p>Source doc</p></dd></p><p>
<dt><code>chunk_index</code></dt>
<dd><p>Index</p></dd></p><p>
<dt><code>start_char</code></dt>
<dd><p>Start</p></dd></p><p>
<dt><code>end_char</code></dt>
<dd><p>End</p></dd></p><p>
<dt><code>metadata</code></dt>
<dd><p>Metadata</p></dd></p><p>
</p><p></p>
<p></p><p></p><p><hr>
<a id="method-TextUnit-clone"></a></p><div class="section" id="method-clone-">
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>TextUnit$clone(deep = FALSE)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd></dl></div></p><p>
</p><p></p>
<p></p><p>
</p>

Methods

Text Unit — TextUnit

<p><div class="r6-fields"></p><dl>
<dt><code>id</code></dt>
<dd><p>Unique identifier</p></dd>


<dt><code>text</code></dt>
<dd><p>Text content</p></dd>


<dt><code>document_id</code></dt>
<dd><p>Source document</p></dd>


<dt><code>chunk_index</code></dt>
<dd><p>Index in document</p></dd>


<dt><code>start_char</code></dt>
<dd><p>Start position</p></dd>


<dt><code>end_char</code></dt>
<dd><p>End position</p></dd>


<dt><code>metadata</code></dt>
<dd><p>Additional metadata</p></dd>


</dl><p></div></p>


<div class='section' id='public-methods'>
<h3>Public methods</h3>

<ul>
<li><p><a href='#method-TextUnit-new'><code>TextUnit$new()</code></a></p></li>
<li><p><a href='#method-TextUnit-clone'><code>TextUnit$clone()</code></a></p></li>
</ul>

</div><p><hr>
<a id="method-TextUnit-new"></a></p><div class='section' id='method-new-'>
<h3>Method <code>new()</code></h3>
<p>Create a new TextUnit</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>TextUnit$new(
  id,
  text,
  document_id = NULL,
  chunk_index = 0,
  start_char = 0,
  end_char = 0,
  metadata = NULL
)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>id</code></dt>
<dd><p>Unique ID</p></dd>


<dt><code>text</code></dt>
<dd><p>Content</p></dd>


<dt><code>document_id</code></dt>
<dd><p>Source doc</p></dd>


<dt><code>chunk_index</code></dt>
<dd><p>Index</p></dd>


<dt><code>start_char</code></dt>
<dd><p>Start</p></dd>


<dt><code>end_char</code></dt>
<dd><p>End</p></dd>


<dt><code>metadata</code></dt>
<dd><p>Metadata</p></dd>


</dl><p></div></p>
</div>

</div><p><hr>
<a id="method-TextUnit-clone"></a></p><div class='section' id='method-clone-'>
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>TextUnit$clone(deep = FALSE)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd>


</dl><p></div></p>
</div>

</div>


TextUnit: Text Unit

Description

Arguments

Public fields

Methods

Public methods

Method `new()`

Usage

Arguments

Method `clone()`

Usage

Arguments

Description

Arguments

Public fields

Methods

Public methods

Method new()

Usage

Arguments

Method clone()

Usage

Arguments

Method `new()`

Method `clone()`