423 lines
21 KiB
HTML
423 lines
21 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
<title>Troubleshooting — Nexus One AI Portal</title>
|
||
<link rel="stylesheet" href="style.css?v=4">
|
||
</head>
|
||
<body>
|
||
|
||
<header class="topnav">
|
||
<a href="index.html" class="brand">Nexus One <span>AI</span></a>
|
||
<nav>
|
||
<a href="index.html">Home</a>
|
||
<a href="quickstart.html">Quick Start</a>
|
||
<a href="prompts.html">Prompt Library</a>
|
||
<a href="usecases.html">Use Cases</a>
|
||
<div class="nav-dropdown">
|
||
<button class="nav-drop-btn active">Help ▾</button>
|
||
<div class="nav-drop-menu">
|
||
<span class="nav-drop-cat">LEARN /</span>
|
||
<a href="quickstart.html">Quick Start</a>
|
||
<a href="models.html">Models</a>
|
||
<span class="nav-drop-cat">SUPPORT /</span>
|
||
<a href="troubleshooting.html" class="active">Troubleshoot</a>
|
||
<a href="faq.html">FAQ</a>
|
||
<span class="nav-drop-cat">MORE /</span>
|
||
<a href="glossary.html">Glossary</a>
|
||
<a href="whats-new.html">What's New</a>
|
||
</div>
|
||
</div>
|
||
<div class="nav-dropdown">
|
||
<button class="nav-drop-btn">Admin ▾</button>
|
||
<div class="nav-drop-menu nav-drop-menu-wide">
|
||
<span class="nav-drop-cat">DOCS /</span>
|
||
<a href="security.html">Security & Privacy</a>
|
||
<a href="admin.html">Admin Guide</a>
|
||
<span class="nav-drop-cat">MONITOR /</span>
|
||
<a href="dashboard.html">Dashboard</a>
|
||
<a href="analytics.html">Usage Analytics</a>
|
||
<a href="audit.html">Audit Log</a>
|
||
<a href="feedback.html">Feedback & Ratings</a>
|
||
<span class="nav-drop-cat">MANAGE /</span>
|
||
<a href="users.html">Users</a>
|
||
<a href="teams.html">Teams</a>
|
||
<a href="models-admin.html">Model Manager</a>
|
||
<a href="training.html">Training</a>
|
||
<a href="knowledge.html">Knowledge Base</a>
|
||
<span class="nav-drop-cat">TOOLS /</span>
|
||
<a href="apikeys.html">API Keys</a>
|
||
<a href="benchmark.html">Benchmarking</a>
|
||
<a href="model-compare.html">Model Compare</a>
|
||
<a href="api-playground.html">API Playground</a>
|
||
<a href="guardrails.html">Guardrails</a>
|
||
<a href="rag-quality.html">RAG Quality</a>
|
||
<a href="router.html">Model Router</a>
|
||
<a href="connectors.html">Connectors</a>
|
||
<span class="nav-drop-cat">SYSTEM /</span>
|
||
<a href="console.html">Console</a>
|
||
<a href="settings.html">Settings</a>
|
||
</div>
|
||
</div>
|
||
<div class="nav-dropdown">
|
||
<button class="nav-drop-btn">AI Tools ▾</button>
|
||
<div class="nav-drop-menu">
|
||
<span class="nav-drop-cat">INTELLIGENCE /</span>
|
||
<a href="documents.html">Document Intelligence</a>
|
||
<a href="chat-multi.html">Multimodal Chat</a>
|
||
<a href="prompt-studio.html">Prompt Studio</a>
|
||
<a href="meeting.html">Meeting Assistant</a>
|
||
<span class="nav-drop-cat">AUTOMATION /</span>
|
||
<a href="agents.html">Agent Builder</a>
|
||
<a href="schedules.html">Scheduled Jobs</a>
|
||
<a href="workflows.html">Workflow Automation</a>
|
||
<span class="nav-drop-cat">QUALITY /</span>
|
||
<a href="evals.html">AI Eval Suite</a>
|
||
<a href="chatrooms.html">Chat Rooms</a>
|
||
</div>
|
||
</div>
|
||
</nav>
|
||
<a href="notifications.html" style="position:relative">🔔</a>
|
||
<span class="badge" data-brand="tier">Basic Tier</span>
|
||
<div id="nav-org-logo" class="nav-org-logo"></div>
|
||
</header>
|
||
|
||
<div class="page-hero">
|
||
<div class="label">Troubleshooting</div>
|
||
<h1>Something Not Working?</h1>
|
||
<p>Find your issue below and follow the steps. If none of these fix it, contact Cezen support with the details noted at the bottom.</p>
|
||
</div>
|
||
|
||
<div class="content">
|
||
|
||
<!-- SEARCH -->
|
||
<div class="ts-search-wrap">
|
||
<input type="text" id="ts-search" class="ts-search" placeholder="Search issues — e.g. 'slow', 'can't upload', 'GPU'…" oninput="filterIssues(this.value)">
|
||
</div>
|
||
|
||
<div id="ts-issues">
|
||
|
||
<!-- CONNECTIVITY -->
|
||
<div class="section-title">Can't Connect</div>
|
||
|
||
<div class="ts-issue" data-tags="connect access browser url open webui load">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">🌐</div>
|
||
<div class="ts-issue-title">Can't open http://ai.local:3001 in my browser</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Check you're on the same network.</strong> Your computer must be on the same local network as the Nexus One AI server — either the same office Wi-Fi or wired LAN. VPN may block local addresses.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Try the server's IP address instead.</strong> Ask your administrator for the IP address and go to <code>http://[IP]:3001</code> directly. Some networks don't resolve <code>.local</code> hostnames.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Check the system status panel.</strong> Go to the <a href="index.html">home page</a> and look at the status panel. If Open WebUI shows red, the service may be stopped.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">4</div>
|
||
<div><strong>Try a different browser.</strong> Chrome or Firefox are most reliable. If one browser doesn't work, try another.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">5</div>
|
||
<div><strong>Contact your IT administrator.</strong> Ask them to run <code>systemctl status open-webui</code> on the server to check if the service is running.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="ts-issue" data-tags="jupyter notebook open access port 8888">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">📓</div>
|
||
<div class="ts-issue-title">Jupyter Notebook won't open at http://ai.local:8888</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Check the system status panel</strong> on the <a href="index.html">home page</a>. If Jupyter shows red, the service needs to be restarted by your administrator.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>You need the access token.</strong> Jupyter requires a token or password to log in. Ask your administrator for it. They can find it by running <code>jupyter server list</code> on the server.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Try the IP address.</strong> Use <code>http://[server-IP]:8888</code> if <code>ai.local</code> doesn't resolve.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- PERFORMANCE -->
|
||
<div class="section-title">Slow or Unresponsive</div>
|
||
|
||
<div class="ts-issue" data-tags="slow response speed fast model performance lag">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">🐢</div>
|
||
<div class="ts-issue-title">The AI is responding very slowly</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Switch to a smaller model.</strong> Larger models (70B) are slower to respond. Try <strong>llama3.1:8b</strong> or <strong>llama3.2:3b</strong> for faster replies. See the <a href="models.html">model library</a> for comparisons.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Check if many users are active.</strong> The GPU is shared. If 10 people are all chatting simultaneously, everyone gets slower responses. Try again when fewer users are active.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Check GPU utilisation.</strong> Open the <a href="tool-nvtop.html">nvtop</a> tool (via SSH) to see if the GPU is fully loaded. If utilisation is at 100% and you're waiting, the GPU is saturated.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">4</div>
|
||
<div><strong>Shorten your prompts.</strong> Very long input messages (pasting entire large documents) slow things down. Use the document upload feature instead — it's more efficient.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="ts-issue" data-tags="gpu zero utilisation not working model not loaded idle">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">📉</div>
|
||
<div class="ts-issue-title">GPU shows 0% utilisation even when sending queries</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Check if a model is loaded.</strong> SSH into the server and run <code>ollama ps</code>. If the list is empty, no model is loaded. Send a message in Open WebUI to load one — the first response will trigger the load.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>GPU utilisation spikes briefly.</strong> If responses are appearing and the GPU shows 0%, don't worry — the query may process fast enough that nvtop/DCGM misses the spike. GPU% is averaged; instant spikes may not show.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Check Ollama is running.</strong> Run <code>systemctl status ollama</code> on the server. If it's not active, run <code>sudo systemctl start ollama</code>.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- DOCUMENTS -->
|
||
<div class="section-title">Document Upload Issues</div>
|
||
|
||
<div class="ts-issue" data-tags="upload document pdf file error fail not working">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">📄</div>
|
||
<div class="ts-issue-title">Document upload fails or shows an error</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Check the file type.</strong> Supported formats are PDF, DOCX, TXT, MD, CSV, XLSX. Image files (.jpg, .png), PowerPoint (.pptx), and compressed archives (.zip) are not supported for chat queries.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Try a smaller file.</strong> Very large documents (100+ MB) may time out during processing. Split the document or try uploading one section at a time.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Scanned PDFs won't work well.</strong> If your PDF is a scanned image (not text-based), the AI can't read it directly. It needs to be a searchable/text PDF. Use OCR software to convert it first.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">4</div>
|
||
<div><strong>Check ChromaDB is running.</strong> Document uploads go to ChromaDB. Check the status panel on the <a href="index.html">home page</a> — if ChromaDB is red, uploads will fail until it's restarted.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="ts-issue" data-tags="document wrong answer incorrect hallucinate rag search">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">🔍</div>
|
||
<div class="ts-issue-title">AI is not finding the right content in my documents</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Rephrase your question.</strong> RAG searches by meaning, not keywords. Try asking the same thing differently — "What is the payment schedule?" vs "When are payments due?" may give different results.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Be more specific.</strong> Instead of "What does the document say?" try "What does section 3.2 say about termination clauses?" Specificity helps the retrieval step find the right chunk.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Re-upload the document.</strong> If the upload completed but the AI can't find content, try deleting and re-uploading the document. The indexing process may not have completed correctly.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">4</div>
|
||
<div><strong>Use the Knowledge Base for multi-document queries.</strong> If you need the AI to search across many documents consistently, add them to a Knowledge Base in <strong>Workspace → Knowledge</strong> rather than uploading per-conversation.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- AI BEHAVIOUR -->
|
||
<div class="section-title">AI Giving Wrong or Unexpected Answers</div>
|
||
|
||
<div class="ts-issue" data-tags="wrong answer hallucinate incorrect false information made up">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">⚠️</div>
|
||
<div class="ts-issue-title">The AI gave me wrong or made-up information</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="notice" style="margin-bottom:16px">⚠️ This is a known limitation of all AI models, not a system fault. It's called <strong>hallucination</strong>. AI models can generate confident-sounding but incorrect answers, especially for specific facts, numbers, dates, or people.</div>
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Never rely on AI alone for critical decisions.</strong> Always verify important facts, figures, regulations, or legal information from authoritative sources.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Use document mode for factual queries.</strong> Upload the source document and ask the AI to answer from it. The AI is far more accurate when it can read the actual text rather than relying on its training knowledge.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Ask the AI to cite its source.</strong> Try adding "Quote the exact sentence from the document that supports your answer." This forces the AI to ground its response in the uploaded text.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">4</div>
|
||
<div><strong>Try a larger model.</strong> Models like <strong>llama3.1:70b</strong> (if available on your tier) are generally more accurate than 8B models. See the <a href="models.html">model library</a>.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div class="ts-issue" data-tags="model memory vram out of memory error crash killed">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">💾</div>
|
||
<div class="ts-issue-title">Out of memory error / model fails to load</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="ts-fix-list">
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">1</div>
|
||
<div><strong>Switch to a smaller model.</strong> If the model you're trying to load requires more VRAM than is available, it will fail. Try <strong>llama3.1:8b</strong> instead of 70B. See the <a href="models.html">model library</a> for VRAM requirements.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">2</div>
|
||
<div><strong>Unload other models first.</strong> SSH into the server and run <code>ollama stop [model-name]</code> to unload models that are sitting in VRAM idle. Then try loading your model again.</div>
|
||
</div>
|
||
<div class="ts-fix">
|
||
<div class="ts-fix-num">3</div>
|
||
<div><strong>Check available VRAM.</strong> Run <code>nvidia-smi</code> on the server to see how much GPU memory is free. If other processes are using it, that reduces what's available for your model.</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- SERVICES DOWN -->
|
||
<div class="section-title">Services Down</div>
|
||
|
||
<div class="ts-issue" data-tags="service down restart ollama chromadb stopped not running">
|
||
<div class="ts-issue-header" onclick="toggleIssue(this)">
|
||
<div class="ts-issue-icon">🔴</div>
|
||
<div class="ts-issue-title">A service shows red in the status panel — how do I restart it?</div>
|
||
<div class="ts-chevron">›</div>
|
||
</div>
|
||
<div class="ts-issue-body">
|
||
<div class="qs-tip" style="margin-bottom:16px">Ask your IT administrator to run the relevant restart command on the server:</div>
|
||
<div class="access-box" style="margin-bottom:0">
|
||
<h4>Restart commands</h4>
|
||
<div class="access-row"><span class="label">Open WebUI</span><span class="value">sudo systemctl restart open-webui</span></div>
|
||
<div class="access-row"><span class="label">Ollama</span><span class="value">sudo systemctl restart ollama</span></div>
|
||
<div class="access-row"><span class="label">ChromaDB</span><span class="value">sudo systemctl restart chromadb</span></div>
|
||
<div class="access-row"><span class="label">Jupyter</span><span class="value">sudo systemctl restart jupyter</span></div>
|
||
<div class="access-row"><span class="label">Check status</span><span class="value">sudo systemctl status [service]</span></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
</div><!-- end ts-issues -->
|
||
|
||
<!-- CONTACT SUPPORT -->
|
||
<div class="section-title">Still stuck?</div>
|
||
<div class="support-box">
|
||
<div class="support-icon">🛟</div>
|
||
<div class="support-body">
|
||
<h3>Contact Cezen Support</h3>
|
||
<p>Email us at <a href="mailto:support@cezentech.com">support@cezentech.com</a> with the following information to speed up the response:</p>
|
||
<ul>
|
||
<li>What you were trying to do</li>
|
||
<li>What happened instead (exact error message if any)</li>
|
||
<li>Which tool was affected (Open WebUI, Ollama, etc.)</li>
|
||
<li>Screenshot of the status panel on the <a href="index.html">home page</a></li>
|
||
<li>Output of <code>nvidia-smi</code> and <code>ollama ps</code> if GPU-related</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
<footer>
|
||
<p>Nexus One AI · Powered by Cezen · Basic Tier</p>
|
||
<p>Questions? <a href="mailto:support@cezentech.com">support@cezentech.com</a> · <a href="https://cezentech.com" target="_blank">cezentech.com</a></p>
|
||
</footer>
|
||
|
||
<script>
|
||
function toggleIssue(header) {
|
||
const issue = header.parentElement;
|
||
const body = issue.querySelector('.ts-issue-body');
|
||
const chevron = header.querySelector('.ts-chevron');
|
||
const isOpen = issue.classList.contains('open');
|
||
// Close all
|
||
document.querySelectorAll('.ts-issue.open').forEach(el => {
|
||
el.classList.remove('open');
|
||
el.querySelector('.ts-chevron').textContent = '›';
|
||
});
|
||
if (!isOpen) {
|
||
issue.classList.add('open');
|
||
chevron.textContent = '⌄';
|
||
}
|
||
}
|
||
|
||
function filterIssues(query) {
|
||
const q = query.toLowerCase();
|
||
document.querySelectorAll('.ts-issue').forEach(issue => {
|
||
const tags = issue.dataset.tags || '';
|
||
const title = issue.querySelector('.ts-issue-title').textContent.toLowerCase();
|
||
const match = !q || tags.includes(q) || title.includes(q);
|
||
issue.style.display = match ? '' : 'none';
|
||
});
|
||
// Hide section titles if no issues visible below them
|
||
document.querySelectorAll('.section-title').forEach(title => {
|
||
let next = title.nextElementSibling;
|
||
let anyVisible = false;
|
||
while (next && !next.classList.contains('section-title') && next.id !== 'ts-issues') {
|
||
if (next.classList.contains('ts-issue') && next.style.display !== 'none') anyVisible = true;
|
||
next = next.nextElementSibling;
|
||
}
|
||
title.style.display = anyVisible ? '' : 'none';
|
||
});
|
||
}
|
||
|
||
// Open first issue by default
|
||
document.querySelector('.ts-issue-header').click();
|
||
</script>
|
||
|
||
<script src="auth.js"></script>
|
||
<script src="branding.js"></script>
|
||
</body>
|
||
</html>
|