Skip to main content

​
Overview

Avante.nvim provides auto-suggestions (also known as inline completions) that give you AI-powered code suggestions as you type, similar to GitHub Copilot. This feature is currently in experimental stage.
Auto-suggestions are a high-frequency operation and can be expensive. Be mindful of your API usage, especially with providers like Copilot.

​
Enabling Auto-Suggestions

Auto-suggestions are disabled by default. Enable them in your configuration: 
require('avante').setup({
  behaviour = {
    auto_suggestions = true, -- Enable auto-suggestions
  },
  auto_suggestions_provider = "claude", -- Provider to use
})

​
Provider Selection

Designating copilot as the auto-suggestions provider can be dangerous due to high-frequency requests. See issue #1048 for details.
Recommended providers for auto-suggestions:
  • "claude" - Claude models (recommended)
  • "openai" - OpenAI models
  • "gemini" - Google Gemini
Avoid using "copilot" unless you understand the implications.

​
Configuration

​
Debounce and Throttle Settings

To control the frequency of suggestion requests, configure debounce and throttle: 
require('avante').setup({
  suggestion = {
    debounce = 600,  -- Wait 600ms after typing stops
    throttle = 600,  -- Maximum one request per 600ms
  },
})
​
debounce
number
default:"600"
Time in milliseconds to wait after typing stops before requesting a suggestion
​
throttle
number
default:"600"
Minimum time in milliseconds between suggestion requests
If you’re using the Copilot provider or experiencing too many API calls, increase these values to reduce request frequency:
suggestion = {
  debounce = 1000,
  throttle = 1000,
}

​
Keybindings

Default keybindings for working with suggestions:
Key BindingModeDescription
<M-l>InsertAccept current suggestion
<M-]>InsertShow next suggestion
<M-[>InsertShow previous suggestion
<C-]>InsertDismiss current suggestion
<M-l> means Alt+l on Linux/Windows or Option+l on macOS.

​
Customizing Keybindings

You can customize the suggestion keybindings in your configuration: 
require('avante').setup({
  mappings = {
    suggestion = {
      accept = "<M-l>",      -- Accept suggestion
      next = "<M-]>",        -- Next suggestion
      prev = "<M-[>",        -- Previous suggestion
      dismiss = "<C-]>",     -- Dismiss suggestion
    },
  },
})

​
Custom Keybinding Example

-- Use Tab to accept, Ctrl+n/p for navigation
require('avante').setup({
  mappings = {
    suggestion = {
      accept = "<Tab>",
      next = "<C-n>",
      prev = "<C-p>",
      dismiss = "<Esc>",
    },
  },
})

​
Toggle Suggestions

You can toggle the suggestion display on and off: 
:AvanteToggleSuggestion
Or use the default keybinding: 
<Leader>as

​
Provider Configuration

Configure your auto-suggestions provider with appropriate settings: 
require('avante').setup({
  auto_suggestions_provider = "claude",
  providers = {
    claude = {
      endpoint = "https://api.anthropic.com",
      model = "claude-3-5-sonnet-20241022",
      timeout = 30000,
      extra_request_body = {
        temperature = 0.5, -- Lower temperature for more focused suggestions
        max_tokens = 2048,
      },
    },
  },
})

​
How Auto-Suggestions Work

1

Typing Detection

As you type, Avante monitors your input and waits for the debounce period.
2

Context Gathering

When the debounce period expires, Avante gathers context from:
  • Current file content
  • Cursor position
  • Recent changes
  • Project context (if RAG is enabled)
3

Request Generation

A suggestion request is sent to the configured provider (respecting throttle limits).
4

Inline Display

The suggestion is displayed inline as ghost text, which you can accept, cycle through, or dismiss.

​
Best Practices

Choose the Right Provider

Use providers with good latency and reasonable pricing for auto-suggestions. Claude is generally recommended.

Adjust Timing

Fine-tune debounce and throttle to balance responsiveness with API costs.

Monitor Usage

Keep an eye on your API usage, especially during heavy coding sessions.

Use with RAG

Enable the RAG service for better context-aware suggestions.

​
Troubleshooting

  1. Reduce debounce value (but this increases API calls)
  2. Use a faster provider (e.g., Claude Haiku instead of Sonnet)
  3. Check your internet connection
  4. Ensure your provider endpoint is responsive
  1. Increase debounce value (e.g., to 1000ms)
  2. Increase throttle value
  3. Consider disabling auto-suggestions for certain file types
  1. Verify behaviour.auto_suggestions = true
  2. Check that your provider is configured correctly
  3. Ensure API keys are set
  4. Look for errors in :messages
  1. Enable the RAG service for better context
  2. Adjust provider temperature (lower for more focused)
  3. Ensure you’re using a capable model
  4. Add project instructions via avante.md

​
Disabling Auto-Suggestions

If you want to disable auto-suggestions: 
require('avante').setup({
  behaviour = {
    auto_suggestions = false,
  },
})
Or toggle them temporarily with <Leader>as or :AvanteToggleSuggestion.

Providers

Configure AI providers

Keybindings

Customize all keybindings

RAG Service

Enable RAG for better suggestions

Project Instructions

Guide AI with project-specific context

Build docs developers (and LLMs) love

Get started for freeTalk to us