GeminiProcessor

<p>Gemini API Processor</p>
<p>Gemini API Processor</p>

Automated cell type annotation for single-cell RNA sequencing data
using consensus predictions from multiple large language models. Integrates
with Seurat objects and provides uncertainty quantification for annotations.
Supports various LLM providers including OpenAI, Anthropic, and Google.
For details see Yang et al. (2025) <doi:10.1101/2025.04.10.647852>.

Chen Yang

mLLMCelltype

Cell Type Annotation Using Large Language Models

GeminiProcessor function

<p><code>mLLMCelltype::BaseAPIProcessor</code> -&gt; <code>GeminiProcessor</code></p>

Super class


<div class="section" id="public-methods">
<h3>Public methods</h3><p></p><p><ul>
<li><p><a href="/link/GeminiProcessor%24new()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$new()"><code>GeminiProcessor$new()</code></a></p></li>
<li><p><a href="/link/GeminiProcessor%24get_default_api_url()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$get_default_api_url()"><code>GeminiProcessor$get_default_api_url()</code></a></p></li>
<li><p><a href="/link/GeminiProcessor%24get_api_url_for_model()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$get_api_url_for_model()"><code>GeminiProcessor$get_api_url_for_model()</code></a></p></li>
<li><p><a href="/link/GeminiProcessor%24make_api_call()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$make_api_call()"><code>GeminiProcessor$make_api_call()</code></a></p></li>
<li><p><a href="/link/GeminiProcessor%24extract_response_content()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$extract_response_content()"><code>GeminiProcessor$extract_response_content()</code></a></p></li>
<li><p><a href="/link/GeminiProcessor%24clone()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::GeminiProcessor$clone()"><code>GeminiProcessor$clone()</code></a></p></li>
</ul></p><p></p></div><p><details open><summary>Inherited methods</summary>
<ul>
<li><span class="pkg-link" data-pkg="mLLMCelltype" data-topic="BaseAPIProcessor" data-id="get_api_url"><a href="/link/mLLMCelltype%3A%3ABaseAPIProcessor%24get_api_url()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::mLLMCelltype::BaseAPIProcessor$get_api_url()"><code>mLLMCelltype::BaseAPIProcessor$get_api_url()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mLLMCelltype" data-topic="BaseAPIProcessor" data-id="process_request"><a href="/link/mLLMCelltype%3A%3ABaseAPIProcessor%24process_request()?package=mLLMCelltype&version=2.0.0" data-mini-rdoc="mLLMCelltype::mLLMCelltype::BaseAPIProcessor$process_request()"><code>mLLMCelltype::BaseAPIProcessor$process_request()</code></a></span></li>
</ul>
</details></p><p><hr>
<a id="method-GeminiProcessor-new"></a></p><div class="section" id="method-new-">
<h3>Method <code>new()</code></h3>
<p>Initialize Gemini processor</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$new(base_url = NULL)</code></pre><p></p></div><p></p>
</div><p></p><p>
</p><p><hr>
<a id="method-GeminiProcessor-get_default_api_url"></a></p><div class="section" id="method-get-default-api-url-">
<h3>Method <code>get_default_api_url()</code></h3>
<p>Get default Gemini API URL template</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$get_default_api_url()</code></pre><p></p></div><p></p>
</div><p></p><p>
</p><p><hr>
<a id="method-GeminiProcessor-get_api_url_for_model"></a></p><div class="section" id="method-get-api-url-for-model-">
<h3>Method <code>get_api_url_for_model()</code></h3>
<p>Get API URL for specific model</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$get_api_url_for_model(model)</code></pre><p></p></div><p></p>
</div><p></p><p>
</p><p><hr>
<a id="method-GeminiProcessor-make_api_call"></a></p><div class="section" id="method-make-api-call-">
<h3>Method <code>make_api_call()</code></h3>
<p>Make API call to Gemini</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$make_api_call(chunk_content, model, api_key)</code></pre><p></p></div><p></p>
</div><p></p><p>
</p><p><hr>
<a id="method-GeminiProcessor-extract_response_content"></a></p><div class="section" id="method-extract-response-content-">
<h3>Method <code>extract_response_content()</code></h3>
<p>Extract response content from Gemini API response</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$extract_response_content(response, model)</code></pre><p></p></div><p></p>
</div><p></p><p>
</p><p><hr>
<a id="method-GeminiProcessor-clone"></a></p><div class="section" id="method-clone-">
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>GeminiProcessor$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

Gemini API Processor — GeminiProcessor


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

<ul>
<li><p><a href='#method-GeminiProcessor-new'><code>GeminiProcessor$new()</code></a></p></li>
<li><p><a href='#method-GeminiProcessor-get_default_api_url'><code>GeminiProcessor$get_default_api_url()</code></a></p></li>
<li><p><a href='#method-GeminiProcessor-get_api_url_for_model'><code>GeminiProcessor$get_api_url_for_model()</code></a></p></li>
<li><p><a href='#method-GeminiProcessor-make_api_call'><code>GeminiProcessor$make_api_call()</code></a></p></li>
<li><p><a href='#method-GeminiProcessor-extract_response_content'><code>GeminiProcessor$extract_response_content()</code></a></p></li>
<li><p><a href='#method-GeminiProcessor-clone'><code>GeminiProcessor$clone()</code></a></p></li>
</ul>

</div><p><details open><summary>Inherited methods</summary>
<ul>
<li><span class="pkg-link" data-pkg="mLLMCelltype" data-topic="BaseAPIProcessor" data-id="get_api_url"><a href='../../mLLMCelltype/html/BaseAPIProcessor.html#method-BaseAPIProcessor-get_api_url'><code>mLLMCelltype::BaseAPIProcessor$get_api_url()</code></a></span></li>
<li><span class="pkg-link" data-pkg="mLLMCelltype" data-topic="BaseAPIProcessor" data-id="process_request"><a href='../../mLLMCelltype/html/BaseAPIProcessor.html#method-BaseAPIProcessor-process_request'><code>mLLMCelltype::BaseAPIProcessor$process_request()</code></a></span></li>
</ul>
</details>

<hr>
<a id="method-GeminiProcessor-new"></a></p><div class='section' id='method-new-'>
<h3>Method <code>new()</code></h3>
<p>Initialize Gemini processor</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>GeminiProcessor$new(base_url = NULL)</code></pre><p></div></p>
</div>


</div><p><hr>
<a id="method-GeminiProcessor-get_default_api_url"></a></p><div class='section' id='method-get-default-api-url-'>
<h3>Method <code>get_default_api_url()</code></h3>
<p>Get default Gemini API URL template</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>GeminiProcessor$get_default_api_url()</code></pre><p></div></p>
</div>


</div><p><hr>
<a id="method-GeminiProcessor-get_api_url_for_model"></a></p><div class='section' id='method-get-api-url-for-model-'>
<h3>Method <code>get_api_url_for_model()</code></h3>
<p>Get API URL for specific model</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>GeminiProcessor$get_api_url_for_model(model)</code></pre><p></div></p>
</div>


</div><p><hr>
<a id="method-GeminiProcessor-make_api_call"></a></p><div class='section' id='method-make-api-call-'>
<h3>Method <code>make_api_call()</code></h3>
<p>Make API call to Gemini</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>GeminiProcessor$make_api_call(chunk_content, model, api_key)</code></pre><p></div></p>
</div>


</div><p><hr>
<a id="method-GeminiProcessor-extract_response_content"></a></p><div class='section' id='method-extract-response-content-'>
<h3>Method <code>extract_response_content()</code></h3>
<p>Extract response content from Gemini API response</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>GeminiProcessor$extract_response_content(response, model)</code></pre><p></div></p>
</div>


</div><p><hr>
<a id="method-GeminiProcessor-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>GeminiProcessor$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>


GeminiProcessor: Gemini API Processor

Description

Arguments

Super class

Methods

Public methods

Method `new()`

Usage

Method `get_default_api_url()`

Usage

Method `get_api_url_for_model()`

Usage

Method `make_api_call()`

Usage

Method `extract_response_content()`

Usage

Method `clone()`

Usage

Arguments

Details

Description

Arguments

Super class

Methods

Public methods

Method new()

Usage

Method get_default_api_url()

Usage

Method get_api_url_for_model()

Usage

Method make_api_call()

Usage

Method extract_response_content()

Usage

Method clone()

Usage

Arguments

Details

Method `new()`

Method `get_default_api_url()`

Method `get_api_url_for_model()`

Method `make_api_call()`

Method `extract_response_content()`

Method `clone()`