Home

---

Table of Contents

• Q & A
  • The format of curl usage in Windows is different from Linux, and the default request format of llm.nvim may cause issues under Windows.
  • Switching between multiple LLMs and frequently changing the value of LLM_KEY is troublesome, and I don't want to expose my key in Neovim's configuration file.
  • Priority of different parse/streaming functions
  • How can the AI-generated git commit message feature be integrated with lazygit
  • How to switch models
  • How to display the thinking (reasoning) contents

Q & A

The format of curl usage in Windows is different from Linux, and the default request format of llm.nvim may cause issues under Windows.

Use a custom request format

• Basic Chat and some AI tools (using streaming output) with customized request format

  Define the args parameter at the same level as the prompt.

  --[[ custom request args ]]
  args = [[return {url, "-N", "-X", "POST", "-H", "Content-Type: application/json", "-H", authorization, "-d", vim.fn.json_encode(body)}]],

• AI tools (using non-streaming output) custom request format

  Define args in opts

    WordTranslate = {
      handler = tools.flexi_handler,
      prompt = "Translate the following text to Chinese, please only return the translation",
      opts = {
        fetch_key = function()
          return vim.env.GLM_KEY
        end,
        url = "https://open.bigmodel.cn/api/paas/v4/chat/completions",
        model = "glm-4-flash",
        api_type = "zhipu",
        args = [[return {url, "-N", "-X", "POST", "-H", "Content-Type: application/json", "-H", authorization, "-d", vim.fn.json_encode(body)}]],
        exit_on_move = true,
        enter_flexible_window = false,
      },
    },

Note

You need to modify the args according to your actual situation.

⬆ back to top

Switching between multiple LLMs and frequently changing the value of LLM_KEY is troublesome, and I don't want to expose my key in Neovim's configuration file.

• Create a .env file specifically to store your various keys. Note: Do not upload this file to GitHub.

export GITHUB_TOKEN=xxxxxxx
export DEEPSEEK_TOKEN=xxxxxxx
export SILICONFLOW_TOKEN=xxxxxxx

• Load the .env file in zshrc or bashrc

  source ~/.config/zsh/.env
  
  # Default to using the LLM provided by Github Models.
  export LLM_KEY=$GITHUB_TOKEN

• Finally, switching keys is completed through fetch_key.

    fetch_key = function()
      return vim.env.DEEPSEEK_TOKEN
    end,

⬆ back to top

Priority of different parse/streaming functions

AI tool configuration's streaming_handler or parse_handler > AI tool configuration's api_type > Main configuration's streaming_handler or parse_handler > Main configuration's api_type

⬆ back to top

How can the AI-generated git commit message feature be integrated with lazygit

{
  "kdheepak/lazygit.nvim",
  lazy = true,
  cmd = {
    "LazyGit",
    "LazyGitConfig",
    "LazyGitCurrentFile",
    "LazyGitFilter",
    "LazyGitFilterCurrentFile",
  },
  -- optional for floating window border decoration
  dependencies = {
    "nvim-lua/plenary.nvim",
  },
  config = function()
    vim.keymap.set("t", "<C-c>", function()
      vim.api.nvim_win_close(vim.api.nvim_get_current_win(), true)
      vim.api.nvim_command("LLMAppHandler CommitMsg")
    end, { desc = "AI Commit Msg" })
  end,
}

⬆ back to top

How to switch models

Need to configure models:

{
  "Kurama622/llm.nvim",
  dependencies = { "nvim-lua/plenary.nvim", "MunifTanjim/nui.nvim"},
  cmd = { "LLMSessionToggle", "LLMSelectedTextHandler", "LLMAppHandler" },
  config = function()
    require("llm").setup({
        -- set models list
        models = {
          {
            name = "GithubModels",
            url = "https://models.inference.ai.azure.com/chat/completions",
            model = "gpt-4o-mini",
            api_type = "openai"
            fetch_key = function()
              return "<your api key>"
            end,
            -- max_tokens = 4096,
            -- temperature = 0.3,
            -- top_p = 0.7,
          },
          {
            name = "Model2",
            -- ...
          }
        },
    })
  end,
  keys = {
    { "<leader>ac", mode = "n", "<cmd>LLMSessionToggle<cr>" },
    -- float style
    ["Input:ModelsNext"]  = { mode = {"n", "i"}, key = "<C-S-J>" },
    ["Input:ModelsPrev"]  = { mode = {"n", "i"}, key = "<C-S-K>" },

    -- Applicable to AI tools with split style and UI interfaces
    ["Session:Models"]     = { mode = "n", key = {"<C-m>"} },
  },
}

⬆ back to top

How to display the thinking (reasoning) contents

Configure enable_thinking (thinking_budget can be optionally configured)

{
  url = "https://api.siliconflow.cn/v1/chat/completions",
  api_type = "openai",
  max_tokens = 4096,
  model = "Qwen/Qwen3-8B", -- think
  fetch_key = function()
    return vim.env.SILICONFLOW_TOKEN
  end,
  temperature = 0.3,
  top_p = 0.7,
  enable_thinking = true,
  thinking_budget = 512,
}

⬆ back to top