New adapter: Nvidia NIM

[basedcatx]

I built and nvidia nim adapter, I don't know if it is worth it for a PR. I just read the CONTRIBUTIONS.md and it recommends I asked here first.

[olimorris]

Appreciate you reading the CONTRIBUTING file. My advice is to share it in these discussions first. If it gains traction then I can consider including it in the plugin in the future.

[basedcatx]

Alright.

[basedcatx]

return {
  "olimorris/codecompanion.nvim",
  dependencies = {
    "nvim-lua/plenary.nvim",
    "nvim-treesitter/nvim-treesitter",
  },
  config = function()
    require("codecompanion").setup({
      adapters = {
        nvidia_nim = function()
          local openai = require("codecompanion.adapters.openai")
          return {
            name = "nvidia_nim",
            formatted_name = "Nvidia NIM",
            url = "https://integrate.api.nvidia.com/v1/chat/completions",
            env = {
              api_key = "NVIDIA-API-KEY"
            },
            headers = {
              ["Content-Type"] = "application/json",
              ["Authorization"] = "Bearer ${api_key}",
            },
            parameters = {
              sync = true
            },
            handlers = {
              setup = function(self)
                if self.opts and self.opts.stream then
                  self.parameters.stream = true
                end
                return true
              end,

              tokens = function(self, data)
                return openai.handlers.tokens(self, data)
              end,

              form_parameters = function(self, params, messages)
                return openai.handlers.form_parameters(self, params, messages)
              end,

              form_messages = function(self, messages)
                return openai.handlers.form_messages(self, messages)
              end,

              chat_output = function(self, data)
                return openai.handlers.chat_output(self, data)
              end,

              inline_output = function(self, data, context)
                return openai.handlers.inline_output(self, data, context)
              end,

              on_exit = function(self, data)
                return openai.handlers.on_exit(self, data)
              end,
            },
            schema = {
              model = {
                order = 1,
                mapping = "parameters",
                type = "enum",
                desc = "ID of the model to use",
                default = "meta/llama-3-70b-instruct",
                choices = {
                  ["nvidia/nemotron-3-nano-30b-a3b"] = { opts = { can_reason = true } },
                  ["meta/llama-3-70b-instruct"] = { opts = { can_reason = true } },
                  ["z-ai/glm4.7"] = { opts = { can_reason = true } },
                },
              },
              max_tokens = {
                mapping = "parameters",
                default = 16384,
              },
            },
          }
        end,
      },
      strategies = {
        chat = {
          adapter = "nvidia_nim",
        },
        inline = {
          adapter = "nvidia_nim",
        },
      },
    })
  end,
}

[CRAG666]

Not work with new version

[basedcatx]

Alright i should get it refixed soon.

[basedcatx]

So I went through everything again. It still works. Rather unfortunately, NIM has become tremendously slower than at first.