BoltAI Documentation
HomepagePricingChangelogDownload
  • Overview
  • Features
  • License
  • Getting Started
    • Setup
    • Your First Chat
    • AI Command
    • AI Inline
    • Use another AI Service
  • Chat UI
    • Overview
    • Basic Chat
    • Document Analysis
    • Advanced Voice Mode (beta)
    • Image Generation
    • Chat Configuration
    • AI Assistant
    • AI Plugins
    • App Appearance
    • Folder & Sidebar
    • Keyboard Shortcuts
    • Import from ChatGPT
    • Import from Claude.ai
    • Import / Export
    • Database Maintenance
    • Locations
    • Feature Flags
    • Community Icon
  • AI Command
    • Overview
    • Customize an AI Command
    • Alternative Profile
    • AI Command Behaviors
    • Instant Command
    • Bulk Editing Commands
    • FAQs
  • AI Inline
    • Overview
    • Inline Assistant
    • Inline Prompt
    • Inline Whisper
    • Advanced Configurations
  • Plugin
    • Overview
    • MCP Servers
    • Google Search
    • Web Browsing
    • Memory
    • Perplexity Search
    • Kagi Search
    • Brave Search
    • You.com Search
    • AppleScript
    • Shell Access
    • FFmpeg
    • DALL·E
    • Replicate
    • Whisper
    • Whisper (via Groq)
    • WolframAlpha
    • Gemini Code Execution
  • BoltAI on Setapp
    • Setapp Limitation
    • AI Inline on Setapp
    • Troubleshooting
  • BoltAI Mobile
    • Getting Started
    • MCP Servers (mobile)
  • Guides
    • How to create an OpenAI API Key
    • How to setup Web Search Plugin for BoltAI
    • How to set up BoltAI without an OpenAI API Key
    • How to generate Azure OpenAI API key
    • How to use Azure OpenAI API key in BoltAI
    • How to create an OpenRouter API key
    • How to set up a custom OpenAI-compatible Server in BoltAI
    • How to use Mistral AI on macOS with BoltAI
    • How to use Perplexity AI on mac with BoltAI
    • How to use Anthropic Claude on macOS with BoltAI
    • How to use Replicate AI on macOS with BoltAI
    • How to use Jina DeepSearch with BoltAI
    • How to migrate data to another Mac
    • How to back up your database
    • Cloud Sync Workaround
  • Troubleshooting
    • How to fix "This license key has reached the activation limit"
    • How to fix "You exceeded your current quota, please check your plan and billing details"
    • How to fix Accessbility permission
    • How to completely uninstall BoltAI
    • Can't select text in conversation prompt
    • API keys not persisted?
    • Download Previous Versions
  • Company
    • Run by a human
Powered by GitBook
On this page
  • How to customize the chat configurtion?
  • Advanced Parameters

Was this helpful?

  1. Chat UI

Chat Configuration

PreviousImage GenerationNextAI Assistant

Last updated 10 months ago

Was this helpful?

While BoltAI Chat UI is simple to use, power users can always tweak advanced configurations for better AI responses.

How to customize the chat configurtion?

Find the Chat Configuration popover button (next to the Chat Title in the navigation toolbar).

You can then customize basic information such as chat title, AI service & model, custom system instruction or advanced parameters such as Context Limits, Temperature, Max Tokens...

You can also open the chat configuration in a new panel window ( Detach) or Save the current configuration as Default

Advanced Parameters

Context Limit

By default, most large language models (LLM) do not maintain the between each request. It's up to the chat client to decide which content to be included.

BoltAI supports multiple strategy to control this chat context:

  • All Previous Messages: when enabled, BoltAI would include all previous messages in the conversation to LLM.

  • No Context: each request contains only the System Instruction and your prompt.

  • First n Messages*: BoltAI would pick the first n messages in the conversation (excluding your prompt) as the chat context.

  • Last n Messages: BoltAI would pick the last n messages in the conversation (excluding your prompt) as the chat context.

By default, BoltAI use last 10 messages as the chat context.

Note:

Depending on your AI service/model, the actual number of messages in the chat context might be slighly different. The reason is because some model such as Anthropic Claude requires a strict order of user/assistant messages.

Temperature

This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses

Max Tokens

This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.

Presence Penalty

Adjusts how often the model repeats specific tokens already used in the input. Higher values make such repetition less likely, while negative values do the opposite. Token penalty does not scale with the number of occurrences. Negative values will encourage token reuse.

Frequency Penalty

This setting aims to control the repetition of tokens based on how often they appear in the input. It tries to use less frequently those tokens that appear more in the input, proportional to how frequently they occur. Token penalty scales with the number of occurrences. Negative values will encourage token reuse.

Top P

This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model's responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

Top K

This limits the model's choice of tokens at each step, making it choose from a smaller set. A value of 1 means the model will always pick the most likely next token, leading to predictable results. By default this setting is disabled, making the model to consider all choices.

Reference:

https://openrouter.ai/docs/parameters
How BoltAI handles Chat Context
Open Chat Configuration in a new panel
Drawing