new tutorials, reorganization, and pages

docs/bun.lock

@@ -20,7 +20,7 @@
         "embla-carousel-react": "^8.0.0",
         "fs": "^0.0.1-security",
         "gray-matter": "^4.0.3",
-        "lucide-react": "^0.372.0",
+        "lucide-react": "^0.522.0",
         "next": "^14.1.4",
         "next-seo": "^6.5.0",
         "next-sitemap": "^4.2.3",
@@ -1503,7 +1503,7 @@
 
     "lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],
 
-    "lucide-react": ["lucide-react@0.372.0", "", { "peerDependencies": { "react": "^16.5.1 || ^17.0.0 || ^18.0.0" } }, "sha512-0cKdqmilHXWUwWAWnf6CrrjHD8YaqPMtLrmEHXolZusNTr9epULCsiJwIOHk2q1yFxdEwd96D4zShlAj67UJdA=="],
+    "lucide-react": ["lucide-react@0.522.0", "", { "peerDependencies": { "react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, "sha512-jnJbw974yZ7rQHHEFKJOlWAefG3ATSCZHANZxIdx8Rk/16siuwjgA4fBULpXEAWx/RlTs3FzmKW/udWUuO0aRw=="],
 
     "lz-string": ["lz-string@1.5.0", "", { "bin": { "lz-string": "bin/bin.js" } }, "sha512-h5bgJWpxJNswbU7qCrV0tIKQCaS3blPDrqKWx+QxzuzL1zGUzij9XCWLrSLsJPu5t+eWA/ycetzYAO5IOMcWAQ=="],
 

docs/src/pages/_meta.json

@@ -11,6 +11,11 @@
     "type": "page",
     "title": "Documentation"
   },
+  "local-server": {
+    "type": "page",
+    "title": "Jan Local Server",
+    "display": "hidden"
+  },
   "cortex": {
     "type": "page",
     "title": "Cortex",

docs/src/pages/docs/_meta.json

@@ -17,17 +17,13 @@
     "title": "TUTORIALS",
     "type": "separator"
   },
-  "quickstart": "Quickstart",
   "remote-models": "Connect to Remote Models",
-  "server-examples": "Integrations",
 
   "explanation-separator": {
     "title": "EXPLANATION",
     "type": "separator"
   },
   "llama-cpp": "Local AI Engine",
-  "api-server": "Server Overview",
-  "data-folder": "Jan Data Folder",
   "privacy-policy": {
     "type": "page",
     "display": "hidden",
@@ -40,12 +36,14 @@
   },
   "manage-models": "Manage Models",
   "mcp": "Model Context Protocol",
+  "mcp-examples": "MCP Examples",
 
   "reference-separator": {
     "title": "REFERENCE",
     "type": "separator"
   },
   "settings": "Settings",
+  "data-folder": "Jan Data Folder",
   "troubleshooting": "Troubleshooting",
   "model-parameters": "Model Parameters",
   "privacy": "Privacy"

docs/src/pages/docs/mcp-examples/search/exa.mdx

@@ -0,0 +1,200 @@
+---
+title: Exa Search MCP
+description: Connect Jan to real-time web search with Exa's AI-powered search engine.
+keywords:
+  [
+    Jan,
+    MCP,
+    Model Context Protocol,
+    Exa,
+    web search,
+    real-time search,
+    research,
+    AI search,
+    tool calling,
+  ]
+---
+
+import { Callout, Steps } from 'nextra/components'
+
+# Using Exa Search MCP with Jan
+
+Exa MCP turns your AI into a research powerhouse. Instead of hallucinating facts or working with stale training data, your model gets real-time access to the web through Exa's AI-powered search engine.
+
+## What You Get
+
+Exa MCP provides eight specialized search tools that actually work:
+
+- **web_search_exa**: General web search with content extraction
+- **research_paper_search**: Academic papers and research content
+- **company_research**: Deep company analysis and intelligence
+- **crawling**: Extract content from specific URLs
+- **competitor_finder**: Find business competitors
+- **linkedin_search**: Search LinkedIn profiles and companies
+- **wikipedia_search_exa**: Wikipedia content retrieval
+- **github_search**: Repository and code search
+
+Think of it as giving your AI a PhD in Google-fu.
+
+## Prerequisites
+
+You'll need:
+- Jan installed and running
+- An Exa API key ([get yours here](https://dashboard.exa.ai/api-keys))
+- A model with tool calling capabilities (Claude, GPT-4, or compatible local models)
+- Node.js installed on your machine
+
+<Callout type="info">
+  **Model Compatibility**: Not all models play nice with tools. Claude models work exceptionally well. For local models, ensure tool calling is enabled in Jan's model parameters.
+</Callout>
+
+## Setup
+
+### Step 1: Enable MCP in Jan
+
+Navigate to **Settings** > **MCP Servers** and toggle **Allow All MCP Tool Permission** ON.
+
+*[Screenshot placeholder: MCP settings page with toggle enabled]*
+
+### Step 2: Get Your Exa API Key
+
+1. Go to [dashboard.exa.ai/api-keys](https://dashboard.exa.ai/api-keys)
+2. Sign up or log in
+3. Generate a new API key
+4. Copy it somewhere safe
+
+*[Screenshot placeholder: Exa dashboard showing API key generation]*
+
+### Step 3: Add Exa MCP Server
+
+Click the `+` button in the MCP Servers section.
+
+*[Screenshot placeholder: MCP server addition dialog]*
+
+Enter the following configuration:
+
+- **Server Name**: `exa`
+- **Command**: `npx`
+- **Arguments**: `-y exa-mcp-server`
+- **Environment Variables**: 
+  - Key: `EXA_API_KEY`
+  - Value: `your-actual-api-key-here`
+
+*[Screenshot placeholder: Filled MCP server configuration form]*
+
+### Step 4: Verify Connection
+
+Check that the server shows as active in your MCP Servers list.
+
+*[Screenshot placeholder: Active Exa MCP server in the list]*
+
+### Step 5: Configure Your Model
+
+Use a model provider that supports tool calling. For cloud models:
+
+- **Anthropic**: Ensure tool calling is enabled in Model Providers settings
+- **OpenAI**: Tool calling should work by default
+- **OpenRouter**: Works with tool-capable models like Claude
+
+*[Screenshot placeholder: Model provider settings with tool calling enabled]*
+
+For local models, enable tool calling in **Model Parameters** > **Model Capabilities**.
+
+## Using Exa MCP
+
+Once configured, start a new chat with your tool-enabled model. The available Exa tools will appear in the tools section.
+
+*[Screenshot placeholder: Chat interface showing Exa MCP tools available]*
+
+### Example Queries
+
+Try these to see Exa MCP in action:
+
+**Research Query:**
+```
+Find recent research papers about transformer model optimization published in 2024
+```
+
+**Company Intelligence:**
+```
+Research the company Anthropic - their business model, recent funding, and key competitors
+```
+
+**Technical Search:**
+```
+Find GitHub repositories for modern React state management libraries with good TypeScript support
+```
+
+**Content Analysis:**
+```
+Extract and summarize the content from this article: [URL]
+```
+
+*[Screenshot placeholder: Example of Exa MCP performing a search with results]*
+
+## Advanced Configuration
+
+### Selective Tool Enabling
+
+If you don't want all eight tools (and who needs that much power?), you can enable specific ones:
+
+- **Command**: `npx`
+- **Arguments**: `-y exa-mcp-server --tools=web_search_exa,research_paper_search,company_research`
+
+### Remote MCP Option
+
+For the truly lazy, use Exa's hosted MCP server instead of running it locally:
+
+- **Server Name**: `exa-remote`
+- **Command**: `npx`
+- **Arguments**: `-y mcp-remote https://mcp.exa.ai/mcp?exaApiKey=your-api-key`
+
+## Use Cases That Actually Matter
+
+### Academic Research
+Perfect for literature reviews, finding recent papers, and staying current with research trends. No more sifting through Google Scholar's ancient interface.
+
+### Competitive Intelligence
+Research competitors, analyze market positioning, and gather business intelligence without manual browsing.
+
+### Technical Discovery
+Find libraries, tools, and solutions on GitHub. Better than hoping Stack Overflow has the answer.
+
+### Content Curation
+Extract and analyze content from specific URLs for research or content creation.
+
+### Professional Networking
+Search LinkedIn for potential collaborators, industry experts, or business connections.
+
+## Troubleshooting
+
+**Server won't connect?**
+- Verify your API key is correct (no extra spaces or quotes)
+- Ensure Node.js is installed
+- Restart Jan completely
+
+**Model not using tools?**
+- Check that tool calling is enabled for your model
+- Try a different model (Claude works best)
+- Verify the MCP server is active
+
+**Search results seem off?**
+- Exa's AI search is context-aware - be specific in your queries
+- Use natural language rather than keyword stuffing
+
+**API key errors?**
+- Double-check your key at [dashboard.exa.ai](https://dashboard.exa.ai)
+- Ensure you haven't hit rate limits
+- Try regenerating the key if issues persist
+
+<Callout type="warning">
+  **Rate Limits**: Exa has API rate limits. If you're planning to go full researcher mode, check your plan limits to avoid surprises.
+</Callout>
+
+## What's Next
+
+Once you've got Exa MCP running, you'll wonder how you ever did research without it. The combination of Jan's privacy-focused approach with Exa's real-time search capabilities creates a research environment that's both powerful and under your control.
+
+No more tab explosions. No more bookmark chaos. Just ask, and get answers backed by current, relevant sources.
+
+*[Screenshot placeholder: Final example showing a complex research query with multiple Exa tools being used]*

docs/src/pages/docs/mcp-examples/search/perplexity.mdx

@@ -0,0 +1,245 @@
+---
+title: Perplexity MCP
+description: Connect Jan to Perplexity's AI-powered search and reasoning capabilities.
+keywords:
+  [
+    Jan,
+    MCP,
+    Model Context Protocol,
+    Perplexity,
+    AI search,
+    web search,
+    reasoning,
+    Sonar,
+    real-time search,
+    tool calling,
+  ]
+---
+
+import { Callout, Steps } from 'nextra/components'
+
+# Using Perplexity MCP with Jan
+
+Perplexity MCP brings real-time web search and specialized reasoning to your AI conversations. Instead of your model pretending it knows what happened yesterday, it can actually find out.
+
+## What You Get
+
+Perplexity MCP offers two flavors of intelligence:
+
+### Official Go Implementation
+- **perplexity_ask**: Real-time web search using Sonar Pro
+- **perplexity_reason**: Complex reasoning with Sonar Reasoning Pro
+- Fast, minimal setup with pre-built binaries
+
+### Python Implementation  
+- **ask_perplexity**: Expert programming assistance and technical explanations
+- **chat_perplexity**: Maintains ongoing conversations with full history
+- **list_chats_perplexity**: Browse your conversation history
+- **read_chat_perplexity**: Retrieve complete chat histories
+- **search**: General web search with customizable detail levels
+
+Both give your AI the ability to stop guessing and start knowing.
+
+## Prerequisites
+
+You'll need:
+- Jan installed and running
+- A Perplexity API key ([get yours here](https://docs.perplexity.ai/docs/getting-started))
+- For Go version: Homebrew (macOS/Linux) or manual binary installation
+- For Python version: Python 3.10+ and uvx package manager
+- A model with tool calling capabilities
+
+<Callout type="info">
+  **API Key Required**: Unlike some search engines that pretend to be free, Perplexity requires an API key. The good news? Their pricing is actually reasonable for the quality you get.
+</Callout>
+
+## Setup
+
+### Step 1: Enable MCP in Jan
+
+Navigate to **Settings** > **MCP Servers** and toggle **Allow All MCP Tool Permission** ON.
+
+*[Screenshot placeholder: MCP settings page with toggle enabled]*
+
+### Step 2: Get Your Perplexity API Key
+
+1. Go to [docs.perplexity.ai](https://docs.perplexity.ai/docs/getting-started)
+2. Sign up or log in to get API access
+3. Generate your API key
+4. Keep it handy
+
+*[Screenshot placeholder: Perplexity API key generation page]*
+
+### Step 3: Choose Your Installation Method
+
+You have two solid options. Pick your poison:
+
+#### Option A: Go Implementation (Recommended for Speed)
+
+**Using Homebrew (macOS/Linux):**
+```bash
+brew install alcova-ai/tap/perplexity-mcp
+```
+
+**Manual Installation:**
+Download the appropriate binary from [Perplexity MCP releases](https://github.com/Alcova-AI/perplexity-mcp/releases) and place it in your PATH.
+
+#### Option B: Python Implementation (More Features)
+
+**Install uvx if you haven't already:**
+```bash
+pip install uvx
+```
+
+### Step 4: Configure MCP Server
+
+Click the `+` button in the MCP Servers section and choose your configuration:
+
+*[Screenshot placeholder: MCP server addition dialog]*
+
+#### For Go Implementation:
+
+- **Server Name**: `perplexity-go`
+- **Command**: `perplexity-mcp`
+- **Arguments**: (leave empty)
+- **Environment Variables**: 
+  - Key: `PERPLEXITY_API_KEY`
+  - Value: `your-api-key-here`
+
+*[Screenshot placeholder: Go implementation MCP configuration]*
+
+#### For Python Implementation:
+
+- **Server Name**: `perplexity-python`
+- **Command**: `uvx`
+- **Arguments**: `mcp-perplexity`
+- **Environment Variables**: 
+  - Key: `PERPLEXITY_API_KEY`
+  - Value: `your-api-key-here`
+  - Key: `PERPLEXITY_MODEL`
+  - Value: `sonar-pro` (optional, this is the default)
+
+*[Screenshot placeholder: Python implementation MCP configuration]*
+
+### Step 5: Verify Connection
+
+Check that your chosen server shows as active in the MCP Servers list.
+
+*[Screenshot placeholder: Active Perplexity MCP server in the list]*
+
+### Step 6: Configure Your Model
+
+Ensure your model supports tool calling. For cloud models, verify tool calling is enabled in your provider settings.
+
+*[Screenshot placeholder: Model provider settings with tool calling enabled]*
+
+## Using Perplexity MCP
+
+Start a new chat with a tool-enabled model. The available Perplexity tools will appear in the tools section.
+
+*[Screenshot placeholder: Chat interface showing Perplexity MCP tools available]*
+
+### Example Queries
+
+**Real-Time News:**
+```
+What are the latest developments in AI regulation in the EU this week?
+```
+
+**Technical Research:**
+```
+Search for recent best practices in React server components and explain the key differences from client components
+```
+
+**Ongoing Research (Python version):**
+```
+Start a research conversation about quantum computing advancements in 2024. I want to maintain this conversation for follow-up questions.
+```
+
+**Code Validation:**
+```
+Check if using jQuery in 2024 is considered deprecated for modern web development
+```
+
+*[Screenshot placeholder: Example of Perplexity MCP performing a search with results]*
+
+## Advanced Configuration
+
+### Custom Models
+
+For the Go implementation, you can specify different models:
+
+- **Arguments**: `--model sonar-reasoning-pro --reasoning-model sonar-pro`
+
+For the Python implementation, use environment variables:
+
+- **PERPLEXITY_MODEL_ASK**: `sonar-reasoning-pro`
+- **PERPLEXITY_MODEL_CHAT**: `sonar-pro`
+
+### Chat History Management (Python Version)
+
+The Python implementation stores chat history locally. Configure the database path:
+
+- **DB_PATH**: `/path/to/your/chats.db`
+
+### Web UI (Python Version)
+
+Enable a web interface for chat management:
+
+- **WEB_UI_ENABLED**: `true`
+- **WEB_UI_PORT**: `8050`
+- **WEB_UI_HOST**: `127.0.0.1`
+
+## Use Cases That Matter
+
+### Research and Fact-Checking
+Perfect for journalists, researchers, and anyone who needs current, verified information. No more "according to my training data from 2023" responses.
+
+### Technical Problem-Solving
+Get current best practices, recent framework updates, and solutions to bleeding-edge problems. Stack Overflow wishes it was this fresh.
+
+### Market Research
+Track industry trends, competitor analysis, and market developments in real-time. Your AI finally knows what happened after its training cutoff.
+
+### Academic Research
+Access current papers, recent findings, and evolving scientific discussions. Like having a research assistant who never sleeps.
+
+### Code Modernization
+Check if your dependencies are deprecated, find modern alternatives, and stay current with evolving best practices.
+
+## Troubleshooting
+
+**Server won't connect?**
+- Verify your API key is valid and properly formatted
+- For Go version: Ensure the binary is in your PATH
+- For Python version: Check that uvx and Python 3.10+ are installed
+- Restart Jan completely
+
+**API errors?**
+- Check your Perplexity API usage limits
+- Verify your API key hasn't expired
+- Ensure you have sufficient credits
+
+**No search results?**
+- Perplexity's search is context-aware - be specific in your queries
+- Check that your model actually supports tool calling
+- Try rephrasing your question
+
+**Python version issues?**
+- Ensure uvx is properly installed: `pip install uvx`
+- Check Python version: `python --version` (should be 3.10+)
+- Verify dependencies: `uvx --help`
+
+<Callout type="warning">
+  **Rate Limits**: Perplexity has usage limits based on your plan. Monitor your usage to avoid hitting limits during intensive research sessions.
+</Callout>
+
+## What's Next
+
+With Perplexity MCP running, your AI conversations become grounded in reality. No more hallucinated facts, no more outdated information, no more "I don't have access to real-time data" excuses.
+
+Whether you're researching the latest AI developments, debugging modern frameworks, or tracking current events, your AI assistant finally has the tools to give you accurate, up-to-date answers.
+
+Time to retire those bookmark folders. Your AI can find what you need, when you need it.
+
+*[Screenshot placeholder: Complex research query showing Perplexity MCP tools working together]*

docs/src/pages/docs/quickstart.mdx

@@ -1,143 +0,0 @@
----
-title: Installation
-description: Jan is an open-source ChatGPT-alternative and self-hosted AI platform - build and run AI on your own desktop or server.
-sidebar_position: 2
-keywords:
-  [
-    Jan,
-    Customizable Intelligence, LLM,
-    local AI,
-    privacy focus,
-    free and open source,
-    private and offline,
-    conversational AI,
-    no-subscription fee,
-    large language models,
-    quickstart,
-    getting started,
-    using AI model,
-    installation,
-  ]
----
-
-import { Callout, Steps } from 'nextra/components'
-import { Settings } from 'lucide-react'
-
-
-# Quickstart
-
-<Steps>
-
-### Step 1: Install Jan
-
-1. [Download Jan](/download)
-2. Install the app on your system ([Mac](/docs/desktop/mac), [Windows](/docs/desktop/windows), [Linux](/docs/desktop/linux))
-3. Launch Jan
-
-Once installed, you'll see Jan's interface with no pre-installed models. You can:
-- Download and run local AI models
-- Connect to cloud-based AI model providers if desired
-<br/>
-
-![Default State](./_assets/jan_ui.png)
-<br/>
-
-### Step 2: Download a Model
-
-Jan offers various local AI models, from nimble lightweights to hefty powerhouses:
-1. Go to the **Hub Tab** or to [HuggingFace](https://huggingface.co/models) where you will be able
-to find even more models alongside their details. (TIP: You can copy the URL or name of the model on the Hub Tab
-and download it there.)
-2. Browse models and tap any for details (Models need to be in GGUF format)
-3. Select one that matches your needs & hardware specs
-4. Hit **Download** to begin (a progress bar will appear for the duration of the download)
-
-<br/>
-![Download a Model](./_assets/model-management-01.png)
-<br/>
-
-<Callout type="warning">
-Local models consume your computer's memory and processing power. Choose carefully based on your hardware
-specifications ([Mac](/docs/desktop/mac#minimum-requirements), [Windows](/docs/desktop/windows#compatibility),
-[Linux](/docs/desktop/linux#compatibility)).
-</Callout>
-
-**Note:** Some Hugging Face models require an access token. Enter yours
-in **Settings > Model Providers > Llama.cpp > Hugging Face Access Token** before importing.
-
-<br/>
-![Add HF Token](./_assets/hf_token.png)
-<br/>
-
-
-For alternative installation methods, see the [Model Management](/manage-models) section.
-
-
-
-### Step 3: Turn on GPU Acceleration (Optional)
-
-While your model downloads, let's supercharge your setup. On **Windows** or **Linux** with
-a compatible graphics card, you can dramatically boost performance with GPU acceleration.
-1. Head to **(<Settings width={16} height={16} style={{display:"inline"}}/>) Settings** > **Hardware**
-2. Under **GPUs**, toggle the setting to ON if not already enabled.
-
-![Turn on GPU acceleration](./_assets/gpu_accl.png)
-
-<Callout type="info">
-Install all required dependencies and drivers before enabling GPU acceleration. Check the **GPU Setup Guide** for [Windows](/docs/desktop/windows#gpu-acceleration) & [Linux](/docs/desktop/linux#gpu-acceleration).
-</Callout>
-<br/>
-
-### Step 4: Customize Assistant Instructions
-
-With your model ready to roll, you can tailor how it responds by tweaking instructions or model configurations
-through the [Assistants feature](/docs/assistants).
-
-<br/>
-
-![Assistant Instruction](./_assets/assistant-dropdown.png)
-
-<br/>
-
-You can also go to the assistant tab to manage all of your personalized instructions. The cool thing about
-these is that you can use them no matter which model you choose.
-
-<br/>
-
-![Add an Assistant Instruction](./_assets/assistant-edit-dialog.png)
-
-<br/>
-
-### Step 5: Start Chatting and Update the Settings
-
-Model downloaded? Instructions set? Time to chat. Type your message in the **input field** at
-the bottom to kickstart the conversation.
-
-Fine-tune your experience by:
-- Tweaking [model parameters](/docs/model-parameters) via the **Gear icon** next to your model or in **Assistant Settings**
-- Switching models for different tasks through the **model selector** in **Model** tab or **input field**
-- [Creating new threads](/docs/threads#creating-new-thread) with custom instructions and configurations
-
-<br/>
-
-![Chat with a Model](./_assets/model-parameters.png)
-
-<br/>
-
-
-### Step 6: Connect to cloud models (Optional)
-
-Jan plays nice with both open source and cloud models. Connect to OpenAI (GPT-4o, o1), Anthropic (Claude), Groq, Mistral, and others:
-1. Open any **Thread**
-2. Select a model from the **model selector** dropdown
-3. Pick your provider, click the **Gear icon** beside it
-4. Grab a valid API key from your chosen provider (make sure it has sufficient credits)
-5. Paste your **API Key** into Jan
-
-For detailed setup, check [Remote APIs](/docs/remote-models/openai).
-
-<br/>
-![Connect Remote APIs](./_assets/quick-start-03.png)
-<br/>
-
-</Steps>

docs/src/pages/docs/threads.mdx

@@ -1,86 +1,145 @@
 ---
 title: Start Chatting
-description: Manage your interaction with AI models locally.
+description: Download models and manage your conversations with AI models locally.
 keywords:
   [
     Jan,
-    Customizable Intelligence, LLM,
     local AI,
-    privacy focus,
-    free and open source,
-    private and offline,
-    conversational AI,
-    no-subscription fee,
-    large language models,
+    LLM,
+    chat,
     threads,
-    chat history,
-    thread history,
+    models,
+    download,
+    installation,
+    conversations,
   ]
 ---
 
-import { Callout } from 'nextra/components'
-import { SquarePen, Pencil, Ellipsis, Paintbrush, Trash2 } from 'lucide-react'
+import { Callout, Steps } from 'nextra/components'
+import { SquarePen, Pencil, Ellipsis, Paintbrush, Trash2, Settings } from 'lucide-react'
 
+# Start Chatting
 
-# Chat with a Model
+<Steps>
 
-Jan organizes your conversations with a model into chats or threads, making it easy to track and revisit
-your interactions. This guide will help you effectively manage your chat history.
+### Step 1: Install Jan
 
-## Creating New Conversation/Thread
-1. Click **New Chat** (<SquarePen width={16} height={16} style={{display:"inline"}}/>) icon on the
-bottom left of Jan.
-2. Select your preferred model in **Model Selector** in input field & start chatting.
+1. [Download Jan](/download)
+2. Install the app ([Mac](/docs/desktop/mac), [Windows](/docs/desktop/windows), [Linux](/docs/desktop/linux))
+3. Launch Jan
 
-<br/>
-![Create New Thread](./_assets/threads-new-chat-updated.png)
+### Step 2: Download a Model
 
-## View Your Chat History
+Jan requires a model to chat. Download one from the Hub:
 
-1. Once you open Jan, the default screen is **Chat**
-2. On the **left sidebar**, you can:
-  - View your **Conversations** and scroll through your history
-  - Click any chat to open the full conversation
+1. Go to the **Hub Tab**
+2. Browse available models (must be GGUF format)
+3. Select one matching your hardware specs
+4. Click **Download**
 
-## Favorites and Recents
-
-Jan helps you quickly access important and recent conversations with **Favorites** and **Recents**
-in the left sidebar:
-- **Favorites**: Pin threads you use often for instant access. Click the three dots icon on the right of the
-thread and a context menu will pop up with the favorite option for you to click on.
-- **Recents**: See your most recently accessed threads for quick navigation.
-
-<br/>
-![Favorites and Recents](./_assets/threads-favorites-and-recents-updated.png)
-
-
-## Edit a Chat Title
-1. Navigate to the **Conversation** that you want to edit title on the sidebar to your left
-2. Hover on the conversation and click on **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
-3. Click <Pencil width={16} height={16} style={{display:"inline"}}/> **Rename**
-4. Add new title & save
-
-<br/>
-![Context Menu](./_assets/threads-context-menu-updated.png)
-
-## Delete Thread
+![Download a Model](./_assets/model-management-01.png)
 
 <Callout type="warning">
-There's no undo for chat deletion, so make sure you REALLY want to remove it permanently.
+Models consume memory and processing power. Choose based on your hardware specs.
 </Callout>
 
-When you want to completely remove a thread:
+**HuggingFace models:** Some require an access token. Add yours in **Settings > Model Providers > Llama.cpp > Hugging Face Access Token**.
 
-1. Navigate to the **Thread** that you want to delete in left sidebar
-2. Hover on the thread and click on **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
+![Add HF Token](./_assets/hf_token.png)
+
+### Step 3: Enable GPU Acceleration (Optional)
+
+For Windows/Linux with compatible graphics cards:
+
+1. Go to **(<Settings width={16} height={16} style={{display:"inline"}}/>) Settings** > **Hardware**
+2. Toggle **GPUs** to ON
+
+![Turn on GPU acceleration](./_assets/gpu_accl.png)
+
+<Callout type="info">
+Install required drivers before enabling GPU acceleration. See setup guides for [Windows](/docs/desktop/windows#gpu-acceleration) & [Linux](/docs/desktop/linux#gpu-acceleration).
+</Callout>
+
+### Step 4: Start Chatting
+
+1. Click **New Chat** (<SquarePen width={16} height={16} style={{display:"inline"}}/>) icon
+2. Select your model in the input field dropdown
+3. Type your message and start chatting
+
+![Create New Thread](./_assets/threads-new-chat-updated.png)
+
+</Steps>
+
+## Managing Conversations
+
+Jan organizes conversations into threads for easy tracking and revisiting.
+
+### View Chat History
+
+- **Left sidebar** shows all conversations
+- Click any chat to open the full conversation
+- **Favorites**: Pin important threads for quick access
+- **Recents**: Access recently used threads
+
+![Favorites and Recents](./_assets/threads-favorites-and-recents-updated.png)
+
+### Edit Chat Titles
+
+1. Hover over a conversation in the sidebar
+2. Click **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
+3. Click <Pencil width={16} height={16} style={{display:"inline"}}/> **Rename**
+4. Enter new title and save
+
+![Context Menu](./_assets/threads-context-menu-updated.png)
+
+### Delete Threads
+
+<Callout type="warning">
+Thread deletion is permanent. No undo available.
+</Callout>
+
+**Single thread:**
+1. Hover over thread in sidebar
+2. Click **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
 3. Click <Trash2 width={16} height={16} style={{display:"inline"}}/> **Delete**
 
+**All threads:**
+1. Hover over `Recents` category
+2. Click **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon  
+3. Select <Trash2 width={16} height={16} style={{display:"inline"}}/> **Delete All**
 
-<br/>
-![Delete Thread](./_assets/threads-context-menu-updated.png)
+## Advanced Features
 
-### Delete all threads at once
+### Custom Assistant Instructions
 
-In case you need to remove all conversations at once:
-1. Hover on the `Recents` category and click on **three dots** (<Ellipsis width={16} height={16} style={{display:"inline"}}/>) icon
-2. Select <Trash2 width={16} height={16} style={{display:"inline"}}/> **Delete All**
+Customize how models respond:
+
+1. Use the assistant dropdown in the input field
+2. Or go to the **Assistant tab** to create custom instructions
+3. Instructions work across all models
+
+![Assistant Instruction](./_assets/assistant-dropdown.png)
+
+![Add an Assistant Instruction](./_assets/assistant-edit-dialog.png)
+
+### Model Parameters
+
+Fine-tune model behavior:
+- Click the **Gear icon** next to your model
+- Adjust parameters in **Assistant Settings**
+- Switch models via the **model selector**
+
+![Chat with a Model](./_assets/model-parameters.png)
+
+### Connect Cloud Models (Optional)
+
+Connect to OpenAI, Anthropic, Groq, Mistral, and others:
+
+1. Open any thread
+2. Select a cloud model from the dropdown
+3. Click the **Gear icon** beside the provider
+4. Add your API key (ensure sufficient credits)
+
+![Connect Remote APIs](./_assets/quick-start-03.png)
+
+For detailed setup, see [Remote APIs](/docs/remote-models/openai).