> ## Documentation Index
> Fetch the complete documentation index at: https://docs.glyphformac.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Chat Assistant

> Multi-provider AI chat with context attachment and conversation history

Glyph includes a built-in AI assistant that supports multiple providers (OpenAI, Anthropic, Google, Ollama, and more). Attach notes and folders as context to ground conversations in your knowledge base.

## Overview

The AI panel is a resizable sidebar that provides:

* **Multi-provider support**: OpenAI, Anthropic, Gemini, Ollama, OpenRouter, and custom endpoints
* **Context attachment**: Include notes and folders in your prompts
* **Conversation history**: Review and restore past chats
* **Two modes**: Chat (conversational) and Create (single-shot generation)
* **Profile management**: Switch between API keys and models instantly

<Frame>
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/sidhuk-glyph-76/images/ai-panel.png" alt="AI chat panel with context attachments" />
</Frame>

## Getting Started

<Steps>
  <Step title="Open AI settings">
    Go to Settings → AI to configure your first profile.
  </Step>

  <Step title="Create a profile">
    Choose a provider, add your API key, and select a model.
  </Step>

  <Step title="Open the AI panel">
    Click the AI icon in the sidebar or use the keyboard shortcut.
  </Step>

  <Step title="Start chatting">
    Type your message and press Enter to send.
  </Step>
</Steps>

## AI Providers

Glyph supports multiple AI providers out of the box:

<CardGroup cols={2}>
  <Card title="OpenAI" icon="robot">
    GPT-4, GPT-4 Turbo, GPT-3.5 Turbo, and o-series reasoning models with configurable reasoning effort.
  </Card>

  <Card title="Anthropic" icon="robot">
    Claude 3.5 Sonnet, Opus, and Haiku models with extended context windows.
  </Card>

  <Card title="Google Gemini" icon="robot">
    Gemini 1.5 Pro, Flash, and other Google AI models.
  </Card>

  <Card title="Ollama" icon="server">
    Run local models like Llama, Mistral, and Phi directly on your machine.
  </Card>

  <Card title="OpenRouter" icon="route">
    Access dozens of models through a single API with unified pricing.
  </Card>

  <Card title="Custom (OpenAI-compatible)" icon="code">
    Connect to any OpenAI-compatible endpoint with custom base URLs and headers.
  </Card>
</CardGroup>

### Provider Configuration

Each provider requires:

* **Name**: Display name for the profile (e.g., "Work GPT-4")
* **Provider**: Select from the dropdown
* **Model**: Choose an available model
* **API Key**: Your provider's API key (stored securely)
* **Base URL** (optional): Custom endpoint for compatible providers
* **Headers** (optional): Additional HTTP headers for authentication

<Note>
  API keys are stored locally using your system's secure credential storage. They never leave your machine.
</Note>

## Chat Modes

### Chat Mode

**Conversational assistant** with full context awareness:

* Multi-turn conversations with memory
* Follow-up questions and clarifications
* Context persists across messages
* Ideal for research, brainstorming, and exploration

### Create Mode

**Single-shot generation** for focused tasks:

* Optimized for content creation
* Each request is independent
* Less conversational, more generative
* Ideal for drafting, summarizing, and transforming content

Switch modes in Settings → AI → Assistant Mode.

## Context Attachments

Attach notes and folders to ground AI responses in your knowledge:

### Adding Context

<Tabs>
  <Tab title="Type @ Mentions">
    Type `@` in the composer to search for files and folders. Select one to attach it.
  </Tab>

  <Tab title="Click the + Button">
    Click the add context button to browse and select files/folders.
  </Tab>

  <Tab title="Drag and Drop">
    Drag notes from the file tree into the AI panel to attach them.
  </Tab>
</Tabs>

### Context Types

<CardGroup cols={2}>
  <Card title="File Context" icon="file">
    Attach a single note. Its full markdown content is included in the prompt.
  </Card>

  <Card title="Folder Context" icon="folder">
    Attach an entire folder. All markdown files within are concatenated and sent.
  </Card>
</CardGroup>

### Context Budget

Glyph automatically manages context size:

* **Character budget**: 100,000 characters by default
* **Token estimation**: Displays estimated token count before sending
* **Truncation**: If content exceeds budget, files are truncated in order
* **Manifest**: View exactly what's included in the "Attached" section

### Removing Context

Click the X on any attached item to remove it. Context persists for the current conversation until manually cleared or you start a new chat.

## Using the AI Panel

### Panel Layout

1. **Header**: Model selector, new chat button, settings, minimize
2. **History**: Expandable list of recent conversations
3. **Chat thread**: Messages from you and the AI
4. **Composer**: Input area with context attachments and send button

### Model Selector

Click the model dropdown to:

* Switch models without losing your conversation
* View model details (context length, pricing, modalities)
* Filter models by name or ID
* Switch between API key profiles

<Frame>
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/sidhuk-glyph-76/images/model-selector.png" alt="Model selector showing available models with details" />
</Frame>

### Sending Messages

<Steps>
  <Step title="Attach context (optional)">
    Use @ mentions or the + button to add relevant notes/folders.
  </Step>

  <Step title="Type your message">
    Enter your prompt in the composer. Shift+Enter for new lines.
  </Step>

  <Step title="Send">
    Press Enter or click the send button to submit.
  </Step>

  <Step title="AI responds">
    Streaming response appears in the chat thread.
  </Step>
</Steps>

### Message Actions

<Tabs>
  <Tab title="Copy">
    Click the copy icon to copy AI responses to your clipboard.
  </Tab>

  <Tab title="Save to Note">
    Click the save icon to append the response to a note of your choice.
  </Tab>

  <Tab title="Retry">
    Click retry to regenerate the last response (uses same context).
  </Tab>

  <Tab title="Stop">
    Click stop during streaming to halt the response early.
  </Tab>
</Tabs>

## Conversation History

### Viewing History

Click the history toggle to expand the history panel:

* Shows last 14 conversations
* Each entry displays title, model, provider, and timestamp
* Click any conversation to restore it

### Restoring Conversations

<Steps>
  <Step title="Open history">
    Click the history button to expand the panel.
  </Step>

  <Step title="Select a conversation">
    Click any conversation to load its full message history.
  </Step>

  <Step title="Continue chatting">
    Add new messages to continue where you left off.
  </Step>
</Steps>

### Conversation Metadata

Each conversation stores:

* **Job ID**: Unique identifier
* **Title**: Auto-generated from first message
* **Provider**: Which AI service was used
* **Model**: Specific model name
* **Created**: Timestamp
* **Message count**: Number of messages exchanged
* **Preview**: First line of the conversation

### Starting Fresh

Click the "New Chat" button to:

* Clear the current conversation
* Reset attached context
* Start with a blank slate

<Warning>
  New chat does not save the current conversation. Make sure to finish your current chat before starting a new one.
</Warning>

## Profile Management

### Creating Profiles

<Steps>
  <Step title="Open AI settings">
    Navigate to Settings → AI.
  </Step>

  <Step title="Click Add Profile">
    Create a new profile with a descriptive name.
  </Step>

  <Step title="Configure provider">
    Select your provider and enter the required details.
  </Step>

  <Step title="Add API key">
    Enter your API key (stored securely on your system).
  </Step>

  <Step title="Select model">
    Choose from the provider's available models.
  </Step>
</Steps>

### Switching Profiles

If you have multiple profiles configured:

* Click the model selector
* Use the "API keys" pill switcher at the top
* Click a profile to switch instantly
* Model list updates to show that provider's models

### Use Cases for Multiple Profiles

* **Work/Personal**: Separate API keys for different contexts
* **Cost optimization**: Use cheaper models for drafts, expensive ones for final output
* **Local/Cloud**: Switch between Ollama (free) and OpenAI (paid)
* **Provider comparison**: Test same prompt across different providers

## Advanced Features

### Reasoning Effort (o-series models)

For OpenAI's o-series reasoning models:

* Configure reasoning effort: low, medium, high
* Higher effort = more thinking time = better answers (and higher cost)
* Set in profile configuration

### Custom Headers

Add custom HTTP headers for authentication or routing:

```json theme={null}
[
  {"key": "X-API-Version", "value": "2024-01-01"},
  {"key": "X-Organization", "value": "your-org"}
]
```

### Private Hosts

Enable "Allow private hosts" to connect to local AI services:

* Required for Ollama ([http://localhost:11434](http://localhost:11434))
* Required for self-hosted endpoints on private IPs
* Security warning: Only enable for trusted endpoints

### Tool Timeline (Create Mode)

When using Create mode, the AI may use tools:

* **create\_note**: Creates a new note in your space
* **search\_notes**: Searches your knowledge base
* **list\_files**: Lists files in a directory

The tool timeline shows:

* Which tools were called
* Tool parameters
* Results or errors
* Execution timing

<Frame>
  <img src="https://mintlify.s3.us-west-1.amazonaws.com/sidhuk-glyph-76/images/ai-tools.png" alt="AI tool timeline showing create_note and search_notes calls" />
</Frame>

## Context Strategies

### Minimal Context

**When**: Quick questions, general knowledge

**Approach**: Send prompts without attachments

```
Explain the concept of atomic notes
```

### Single Note Context

**When**: Analyzing, summarizing, or transforming a specific note

**Approach**: Attach the target note

```
@daily/2024-03-10.md

Summarize the key points from this daily note
```

### Folder Context

**When**: Cross-referencing multiple notes, finding patterns

**Approach**: Attach a relevant folder

```
@projects/client-work

What are the common themes across these project notes?
```

### Mixed Context

**When**: Comparing specific notes against broader context

**Approach**: Attach multiple files and folders

```
@projects/q1-goals.md @projects/completed

How do my Q1 goals compare to what I actually completed?
```

## Best Practices

1. **Be specific with prompts** - Clear instructions yield better results
2. **Use context strategically** - More context ≠ better answers; be selective
3. **Review token estimates** - Stay within model limits for best performance
4. **Leverage history** - Continue conversations instead of repeating context
5. **Try different models** - Each excels at different tasks
6. **Use Create mode for generation** - Chat mode for back-and-forth
7. **Save useful responses** - Click save to preserve insights in your notes
8. **Name profiles clearly** - "Work GPT-4" vs "Personal Claude" helps when switching

## Keyboard Shortcuts

| Shortcut    | Action                 |
| ----------- | ---------------------- |
| Enter       | Send message           |
| Shift+Enter | New line in composer   |
| Escape      | Minimize AI panel      |
| @           | Trigger context picker |
| Click model | Open model selector    |

## Privacy & Security

* **API keys**: Stored in system credential manager (Keychain on macOS, Credential Manager on Windows)
* **Conversations**: Stored locally in your space's `.glyph` directory
* **Context**: Only sent when explicitly attached
* **No telemetry**: Glyph doesn't log or transmit your prompts
* **Provider privacy**: Subject to each AI provider's privacy policy

<Warning>
  AI providers may retain conversation logs according to their policies. Do not send sensitive information unless you trust the provider.
</Warning>

## Common Issues

### "No API key configured"

**Solution**: Add an API key for the selected profile in Settings → AI

### "Model not available"

**Solution**: Check that your API key has access to the model, or select a different model

### "Context too large"

**Solution**: Remove some attachments or use a model with a larger context window

### Streaming stops early

**Possible causes**:

* Network interruption
* Provider rate limiting
* Model hit token limit

**Solution**: Click retry or reduce context size

## Related Features

* [Tags & Search](/features/tags-search) - Find notes to attach as context
* [Daily Notes](/features/daily-notes) - Use AI to reflect on daily notes
* [Attachments](/features/attachments) - Include images in AI conversations (vision models)
* [AI Setup](/ai/setup) - Configure AI providers and profiles