mirror of
https://github.com/memohai/Memoh.git
synced 2026-04-27 07:16:19 +09:00
sheepbox8646
2 lines
5.3 KiB
JavaScript
2 lines
5.3 KiB
JavaScript
import{_ as t,o,c as r,ag as a}from"./chunks/framework.ePeAWSvT.js";const u=JSON.parse('{"title":"Bot Memory Management","description":"","frontmatter":{},"headers":[],"relativePath":"getting-started/memory.md","filePath":"getting-started/memory.md","lastUpdated":1772873936000}'),i={name:"getting-started/memory.md"};function n(s,e,m,l,c,h){return o(),r("div",null,[...e[0]||(e[0]=[a('<h1 id="bot-memory-management" tabindex="-1">Bot Memory Management <a class="header-anchor" href="#bot-memory-management" aria-label="Permalink to "Bot Memory Management""></a></h1><p>Memoh's structured long-term memory system allows bots to remember information across multiple conversations, providing contextually relevant and personalized interactions.</p><h2 id="prerequisites" tabindex="-1">Prerequisites <a class="header-anchor" href="#prerequisites" aria-label="Permalink to "Prerequisites""></a></h2><p>Before using the <strong>Memory</strong> tab, make sure your bot already has a <strong>Memory Provider</strong> configured.</p><ol><li>Create a provider from the <a href="/memory-providers/builtin.html">Built-in Memory Provider</a> guide.</li><li>Open your bot's <strong>Settings</strong> tab.</li><li>Select the provider in the <strong>Memory Provider</strong> field.</li><li>Click <strong>Save</strong>.</li></ol><p>Without a memory provider, the bot will not have an active memory backend configuration.</p><hr><h2 id="concept-semantic-search" tabindex="-1">Concept: Semantic Search <a class="header-anchor" href="#concept-semantic-search" aria-label="Permalink to "Concept: Semantic Search""></a></h2><p>With the built-in memory provider, memories are stored in Memoh's memory system and retrieved through semantic search. When a user asks a question, Memoh finds the most relevant memories and includes them in the bot's runtime context.</p><hr><h2 id="operations" tabindex="-1">Operations <a class="header-anchor" href="#operations" aria-label="Permalink to "Operations""></a></h2><p>Manage your bot's memories from the <strong>Memory</strong> tab in the Bot Detail page.</p><h3 id="_1-creating-memories" tabindex="-1">1. Creating Memories <a class="header-anchor" href="#_1-creating-memories" aria-label="Permalink to "1. Creating Memories""></a></h3><ul><li><strong>New Memory</strong>: Manually enter a memory's content in the provided textarea.</li><li><strong>From Conversation</strong>: Select specific messages from the bot's conversation history to extract into memory.</li></ul><h3 id="_2-searching-and-managing" tabindex="-1">2. Searching and Managing <a class="header-anchor" href="#_2-searching-and-managing" aria-label="Permalink to "2. Searching and Managing""></a></h3><ul><li><strong>Search</strong>: Filter memories by ID or text content.</li><li><strong>Edit</strong>: Modify existing memory entries directly in the list.</li><li><strong>Delete</strong>: Remove memories that are no longer needed.</li></ul><hr><h2 id="memory-compression-compact" tabindex="-1">Memory Compression (Compact) <a class="header-anchor" href="#memory-compression-compact" aria-label="Permalink to "Memory Compression (Compact)""></a></h2><p>Over time, memories can accumulate and become redundant. The <strong>Compact</strong> feature helps optimize the memory pool.</p><ul><li><strong>Ratio</strong>: Set the compression ratio (for example <code>0.8</code>, <code>0.5</code>, or <code>0.3</code>) to determine how much information is retained.</li><li><strong>Decay Days</strong>: Optionally specify a time window to compact only memories older than a certain number of days.</li></ul><hr><h2 id="visualization-vector-manifold" tabindex="-1">Visualization: Vector Manifold <a class="header-anchor" href="#visualization-vector-manifold" aria-label="Permalink to "Visualization: Vector Manifold""></a></h2><p>The Memory tab includes visual tools to help you understand how the memory system is performing:</p><h3 id="top-k-bucket-chart" tabindex="-1">Top-K Bucket Chart <a class="header-anchor" href="#top-k-bucket-chart" aria-label="Permalink to "Top-K Bucket Chart""></a></h3><p>Shows the distribution of relevant memories retrieved for the most recent queries.</p><h3 id="cdf-curve-cumulative-distribution-function" tabindex="-1">CDF Curve (Cumulative Distribution Function) <a class="header-anchor" href="#cdf-curve-cumulative-distribution-function" aria-label="Permalink to "CDF Curve (Cumulative Distribution Function)""></a></h3><p>Visualizes the scoring threshold of retrieved memories, helping you fine-tune how much relevant information the bot should consider.</p><hr><h2 id="bot-interaction" tabindex="-1">Bot Interaction <a class="header-anchor" href="#bot-interaction" aria-label="Permalink to "Bot Interaction""></a></h2><ul><li>The bot automatically searches and retrieves memories during chat.</li><li>The assigned <strong>Memory Provider</strong> controls the memory backend used by the bot.</li><li>For the built-in provider, you can optionally configure a <strong>Memory Model</strong> and an <strong>Embedding Model</strong> inside the provider settings.</li><li>Memories provide the long-term knowledge that makes each bot unique to its owner.</li></ul>',30)])])}const g=t(i,[["render",n]]);export{u as __pageData,g as default};
|