323 lines
17 KiB
HTML
323 lines
17 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>What's New — 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">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" class="active">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">What's New</div>
|
|
<h1>Release Notes & Updates</h1>
|
|
<p>A record of what's been added, changed, or improved on your Nexus One AI system and this portal. Administrators should update this page when new models or features are deployed.</p>
|
|
</div>
|
|
|
|
<div class="content">
|
|
|
|
<!-- CURRENT VERSION BANNER -->
|
|
<div class="wn-current-banner">
|
|
<div class="wn-current-left">
|
|
<div class="wn-version-pill">Current Version</div>
|
|
<div class="wn-current-version">Basic Tier — v2.0</div>
|
|
<div class="wn-current-date">Released June 2026</div>
|
|
</div>
|
|
<div class="wn-current-right">
|
|
<div class="wn-stat">
|
|
<div class="wn-stat-num">9</div>
|
|
<div class="wn-stat-label">Core tools</div>
|
|
</div>
|
|
<div class="wn-stat">
|
|
<div class="wn-stat-num">8</div>
|
|
<div class="wn-stat-label">AI models</div>
|
|
</div>
|
|
<div class="wn-stat">
|
|
<div class="wn-stat-num">43</div>
|
|
<div class="wn-stat-label">Portal pages</div>
|
|
</div>
|
|
<div class="wn-stat">
|
|
<div class="wn-stat-num">12</div>
|
|
<div class="wn-stat-label">AI Tools & features</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- CHANGELOG TIMELINE -->
|
|
<div class="section-title">Changelog</div>
|
|
|
|
<!-- v2.0 -->
|
|
<div class="wn-entry">
|
|
<div class="wn-entry-meta">
|
|
<div class="wn-entry-version">v2.0</div>
|
|
<div class="wn-entry-date">June 2026</div>
|
|
<div class="wn-entry-badge" style="background:rgba(124,58,237,.12);color:var(--purple)">Major Update</div>
|
|
</div>
|
|
<div class="wn-entry-body">
|
|
<h3 class="wn-entry-title">Full AI Platform — Intelligence, Automation & Control</h3>
|
|
<p class="wn-entry-desc">v2.0 transforms Nexus One AI from a chat and document Q&A tool into a complete on-premises AI operating platform. This release adds agents, workflow automation, meeting intelligence, secure collaboration, and a full administrative control layer — all running entirely on your hardware.</p>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🧠 Intelligence Tools</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong><a href="chat-multi.html">Multimodal Chat</a>
|
|
<a href="prompt-studio.html">Prompt Studio</a></strong> — Full rewrite with persistent history, sidebar search, image upload, per-conversation model switching, and markdown rendering with code blocks</li>
|
|
<li><strong><a href="documents.html">Document Intelligence Workbench</a></strong> — Side-by-side document comparison, table extraction, batch processing, and structured output from uploaded files</li>
|
|
<li><strong><a href="meeting.html">Meeting Assistant</a></strong> — On-premises meeting transcription (Whisper), AI summaries, action item extraction, and follow-up email drafting from audio recordings</li>
|
|
<li><strong><a href="chatrooms.html">Secure Chat Rooms</a></strong> — Multi-user AI-assisted collaboration spaces with AI moderation, private to invited members, no external relay</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">⚙️ Automation Tools</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong><a href="agents.html">Agent Builder</a></strong> — Build autonomous AI agents with tool access, multi-step planning, and governance/approval layer for sensitive actions</li>
|
|
<li><strong><a href="workflows.html">Workflow Automation</a></strong> — Visual pipeline builder for chaining AI tasks: trigger → process → output, with support for scheduled and webhook triggers</li>
|
|
<li><strong><a href="schedules.html">Scheduled Jobs</a></strong> — Cron-based AI task scheduling: daily reports, nightly document ingestion, automated monitoring — runs without user interaction</li>
|
|
<li><strong><a href="connectors.html">Connectors</a></strong> — Integration layer for databases, file shares, REST APIs, email, and SharePoint — usable by agents and workflows</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🛡️ Control & Quality Tools</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong><a href="guardrails.html">Guardrails</a></strong> — Keyword blocks, PII redaction, regex rules, and prompt injection detection with block/redact/warn actions</li>
|
|
<li><strong><a href="router.html">Model Router</a></strong> — Automatic query routing to the optimal model based on task type, token count, or custom rules</li>
|
|
<li><strong><a href="rag-quality.html">RAG Quality Dashboard</a></strong> — Chunk quality scoring, retrieval accuracy monitoring, and query testing for knowledge base collections</li>
|
|
<li><strong><a href="evals.html">AI Eval Suite</a></strong> — Standardised test suites for model and prompt quality, with pass rate tracking and regression detection</li>
|
|
<li><strong><a href="benchmark.html">Model Benchmarking</a></strong> — Speed and quality benchmarks across installed models with tokens/second and TTFT metrics</li>
|
|
<li><strong><a href="apikeys.html">API Key Manager</a></strong> — Generate and manage API keys for programmatic access with per-key rate limits and model restrictions</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">📖 Portal & Knowledge Center</div>
|
|
<ul class="wn-change-list">
|
|
<li>Portal expanded from 20 to 43 pages covering all new features</li>
|
|
<li>Quick Start updated with tabbed layout: First Steps, Platform Features, Admin Setup</li>
|
|
<li>FAQ expanded with AI Tools, Automation, and new Technical Q&As</li>
|
|
<li>Use Cases updated with agent, meeting assistant, and automation scenarios</li>
|
|
<li>Glossary updated with 15 new terms covering all new features</li>
|
|
<li>Light lavender theme applied consistently across all 43 pages</li>
|
|
<li>Navigation fixed and standardised across all pages with complete AI Tools section</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🤖 New AI Models</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong>llama3:70b</strong> — Added for high-accuracy complex reasoning tasks</li>
|
|
<li><strong>codellama:34b</strong> — Added for code generation and technical review</li>
|
|
<li><strong>llava:13b</strong> — Added for vision/image understanding queries</li>
|
|
<li><strong>nomic-embed-text</strong> — Dedicated embedding model for RAG (required)</li>
|
|
</ul>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<!-- v1.0 -->
|
|
<div class="wn-entry">
|
|
<div class="wn-entry-meta">
|
|
<div class="wn-entry-version">v1.0</div>
|
|
<div class="wn-entry-date">June 2025</div>
|
|
<div class="wn-entry-badge initial">Initial Release</div>
|
|
</div>
|
|
<div class="wn-entry-body">
|
|
<h3 class="wn-entry-title">Basic Tier — Initial Deployment</h3>
|
|
<p class="wn-entry-desc">First deployment of the Nexus One AI Basic Tier system. Full AI stack installed and configured on-premises with the following components and capabilities.</p>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🛠️ Tools Installed</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong>Ollama</strong> — Local AI model engine running on NVIDIA RTX Pro 6000 GPU</li>
|
|
<li><strong>Open WebUI</strong> — Browser-based chat interface accessible at http://ai.local:3001</li>
|
|
<li><strong>ChromaDB</strong> — Vector database for document storage and RAG</li>
|
|
<li><strong>LangChain</strong> — Python framework for building AI pipelines</li>
|
|
<li><strong>Jupyter Notebook</strong> — Interactive Python environment at http://ai.local:8888</li>
|
|
<li><strong>FastAPI</strong> — REST API layer for application integration</li>
|
|
<li><strong>DCGM</strong> — NVIDIA GPU health monitoring and diagnostics</li>
|
|
<li><strong>nvtop</strong> — Live GPU dashboard for terminal monitoring</li>
|
|
<li><strong>QLoRA / Unsloth</strong> — Efficient model fine-tuning toolkit</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🤖 AI Models Available</div>
|
|
<ul class="wn-change-list">
|
|
<li><strong>llama3.1:8b</strong> — Primary recommended model for general tasks</li>
|
|
<li><strong>llama3.2:3b</strong> — Fast lightweight model for simple tasks</li>
|
|
<li><strong>mistral:7b</strong> — Strong multilingual and structured output model</li>
|
|
<li><strong>llama3.1:70b</strong> — High-accuracy model for complex reasoning</li>
|
|
<li><strong>gemma2:9b</strong> — Google's efficient model with strong instruction following</li>
|
|
<li><strong>phi3:mini</strong> — Ultra-fast 3.8B model for quick responses</li>
|
|
<li><strong>nomic-embed-text</strong> — Embedding model for document search</li>
|
|
<li><strong>mxbai-embed-large</strong> — High-accuracy embedding model</li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">📖 Knowledge Portal Launched</div>
|
|
<ul class="wn-change-list">
|
|
<li>Home page with live service status monitoring (auto-refreshes every 60 seconds)</li>
|
|
<li>Quick Start guide — 5 steps to first AI conversation</li>
|
|
<li>Tool pages for all 9 installed components with direct access buttons</li>
|
|
<li>Prompt Library — 32 ready-to-use prompts across 8 government departments</li>
|
|
<li>Use Case Gallery — 18 real-world scenarios with time savings benchmarks</li>
|
|
<li>Model Library — comparison table and "which model should I use?" guide</li>
|
|
<li>Troubleshooting — 9 common issues with searchable accordion</li>
|
|
<li>FAQ — 14 plain-English answers to common questions</li>
|
|
<li>Glossary — 18 AI terms explained</li>
|
|
<li>Security & Privacy — air-gapped architecture and data handling guide</li>
|
|
<li>Admin Guide — service management, model management, log access, and procedures</li>
|
|
<li>What's New — this page</li>
|
|
</ul>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<!-- UPCOMING -->
|
|
<div class="wn-entry wn-upcoming">
|
|
<div class="wn-entry-meta">
|
|
<div class="wn-entry-version">v3.0</div>
|
|
<div class="wn-entry-date">Planned</div>
|
|
<div class="wn-entry-badge upcoming">Coming Soon</div>
|
|
</div>
|
|
<div class="wn-entry-body">
|
|
<h3 class="wn-entry-title">Pro Tier Upgrade</h3>
|
|
<p class="wn-entry-desc">The Pro Tier upgrade adds enterprise-scale AI infrastructure for higher concurrency, larger models, and production-grade deployment capabilities.</p>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🔜 Planned additions</div>
|
|
<ul class="wn-change-list wn-planned">
|
|
<li><strong>vLLM</strong> — High-throughput inference engine for multi-user production workloads</li>
|
|
<li><strong>Ray</strong> — Distributed computing framework for parallel AI jobs</li>
|
|
<li><strong>DeepSpeed</strong> — Memory-efficient training for larger model fine-tuning</li>
|
|
<li><strong>Milvus</strong> — Scalable vector database replacing ChromaDB for large document collections</li>
|
|
<li><strong>MLflow</strong> — Experiment tracking and model registry</li>
|
|
<li>Additional large models (70B+ class) optimised for the upgraded hardware</li>
|
|
<li>Portal tier switcher — toggle between Entry, Mid, and Advanced documentation</li>
|
|
</ul>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div class="wn-entry wn-upcoming">
|
|
<div class="wn-entry-meta">
|
|
<div class="wn-entry-version">v4.0</div>
|
|
<div class="wn-entry-date">Planned</div>
|
|
<div class="wn-entry-badge upcoming">Coming Soon</div>
|
|
</div>
|
|
<div class="wn-entry-body">
|
|
<h3 class="wn-entry-title">Max Tier Upgrade</h3>
|
|
<p class="wn-entry-desc">The Max Tier adds Kubernetes-based orchestration and enterprise model serving for high-availability, large-scale AI deployment.</p>
|
|
|
|
<div class="wn-change-group">
|
|
<div class="wn-change-group-title">🔜 Planned additions</div>
|
|
<ul class="wn-change-list wn-planned">
|
|
<li><strong>Kubeflow</strong> — ML pipeline orchestration on Kubernetes</li>
|
|
<li><strong>Triton Inference Server</strong> — NVIDIA's production model serving platform</li>
|
|
<li><strong>Megatron-LM</strong> — Large-scale model training across multiple GPU nodes</li>
|
|
<li>High-availability configuration with automatic failover</li>
|
|
<li>Role-based portal access — admin console with embedded terminal</li>
|
|
<li>Usage analytics dashboard for administrators</li>
|
|
</ul>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<!-- ADMIN NOTE -->
|
|
<div class="notice" style="margin-top:40px">
|
|
📝 <strong>For administrators:</strong> Update this page whenever a new model is installed, a service is upgraded, or a configuration change is made. Edit <code>whats-new.html</code> and add a new entry above v1.0 following the same format. Include the date, a brief description, and what changed.
|
|
</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 src="auth.js"></script>
|
|
<script src="branding.js"></script>
|
|
</body>
|
|
</html>
|