<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Stages on Lucille</title><link>https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/</link><description>Recent content in Stages on Lucille</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 06 Jun 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/index.xml" rel="self" type="application/rss+xml"/><item><title>PromptOllama</title><link>https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/prompt_ollama/</link><pubDate>Fri, 06 Jun 2025 00:00:00 +0000</pubDate><guid>https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/prompt_ollama/</guid><description>&lt;p&gt;What if you could just, actually, put an LLM on everything?&lt;/p&gt;
&lt;h3 id="ollama"&gt;Ollama&lt;/h3&gt;
&lt;p&gt;Ollama allows you to run a variety of Large Language Models (LLMs) with minimal setup. You can also create custom models
using Modelfiles and system prompts.&lt;/p&gt;
&lt;p&gt;The &lt;code&gt;PromptOllama&lt;/code&gt; Stage allows you to connect to a running instance of Ollama Server, which communicates with an LLM through a simple API.
The Stage sends part (or all) of a Document to the LLM for generic enrichment. You&amp;rsquo;ll want to create a custom model (with a Modelfile)
or provide a System Prompt in the Stage Config that is tailored to your pipeline.&lt;/p&gt;</description></item><item><title>QueryOpensearch</title><link>https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/query_opensearch/</link><pubDate>Fri, 06 Jun 2025 00:00:00 +0000</pubDate><guid>https://kmwtechnology.github.io/lucille/docs-0.5.10/architecture/components/stages/query_opensearch/</guid><description>&lt;h3 id="opensearch-templates"&gt;OpenSearch Templates&lt;/h3&gt;
&lt;p&gt;You can use templates in OpenSearch to repeatedly run a certain query using different parameters. For example,
if we have an index full of parks, and we want to search for a certain park, we might use a template like this:&lt;/p&gt;
&lt;div class="highlight"&gt;&lt;pre tabindex="0" style="background-color:#f8f8f8;-moz-tab-size:4;-o-tab-size:4;tab-size:4;-webkit-text-size-adjust:none;"&gt;&lt;code class="language-json" data-lang="json"&gt;&lt;span style="display:flex;"&gt;&lt;span&gt;&lt;span style="color:#000;font-weight:bold"&gt;{&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#204a87;font-weight:bold"&gt;&amp;#34;source&amp;#34;&lt;/span&gt;&lt;span style="color:#000;font-weight:bold"&gt;:&lt;/span&gt; &lt;span style="color:#000;font-weight:bold"&gt;{&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#204a87;font-weight:bold"&gt;&amp;#34;query&amp;#34;&lt;/span&gt;&lt;span style="color:#000;font-weight:bold"&gt;:&lt;/span&gt; &lt;span style="color:#000;font-weight:bold"&gt;{&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#204a87;font-weight:bold"&gt;&amp;#34;match_phrase&amp;#34;&lt;/span&gt;&lt;span style="color:#000;font-weight:bold"&gt;:&lt;/span&gt; &lt;span style="color:#000;font-weight:bold"&gt;{&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#204a87;font-weight:bold"&gt;&amp;#34;park_name&amp;#34;&lt;/span&gt;&lt;span style="color:#000;font-weight:bold"&gt;:&lt;/span&gt; &lt;span style="color:#4e9a06"&gt;&amp;#34;{{park_to_search}}&amp;#34;&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#000;font-weight:bold"&gt;}&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#000;font-weight:bold"&gt;}&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt; &lt;span style="color:#000;font-weight:bold"&gt;}&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;span style="display:flex;"&gt;&lt;span&gt;&lt;span style="color:#000;font-weight:bold"&gt;}&lt;/span&gt;
&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;In Opensearch, you could then call this template (providing it &lt;code&gt;park_to_search&lt;/code&gt;) instead of writing out the full query each time you want to search.&lt;/p&gt;</description></item></channel></rss>