Configuring Adapters
TIP
Want to connect to an LLM that isn't supported out of the box? Check out these user contributed adapters, create your own or post in the discussions
An adapter is what connects Neovim to an LLM. It's the interface that allows data to be sent, received and processed and there are a multitude of ways to customize them.
Changing the Default Adapter
You can change the default adapter as follows:
require("codecompanion").setup({
strategies = {
chat = {
adapter = "anthropic",
},
inline = {
adapter = "copilot",
},
},
}),Setting an API Key
Extend a base adapter to set options like api_key or model:
require("codecompanion").setup({
adapters = {
anthropic = function()
return require("codecompanion.adapters").extend("anthropic", {
env = {
api_key = "MY_OTHER_ANTHROPIC_KEY",
},
})
end,
},
}),If you do not want to store secrets in plain text, prefix commands with cmd::
require("codecompanion").setup({
adapters = {
openai = function()
return require("codecompanion.adapters").extend("openai", {
env = {
api_key = "cmd:op read op://personal/OpenAI/credential --no-newline",
},
})
end,
},
}),NOTE
In this example, we're using the 1Password CLI to extract the OpenAI API Key. You could also use gpg as outlined here
Configuring Adapter Settings
LLMs have many settings such as model, temperature and max_tokens. In an adapter, these sit within a schema table and can be configured during setup:
require("codecompanion").setup({
adapters = {
llama3 = function()
return require("codecompanion.adapters").extend("ollama", {
name = "llama3", -- Give this adapter a different name to differentiate it from the default ollama adapter
schema = {
model = {
default = "llama3:latest",
},
num_ctx = {
default = 16384,
},
num_predict = {
default = -1,
},
},
})
end,
},
})Adding a Custom Adapter
NOTE
See the Creating Adapters section to learn how to create custom adapters
Custom adapters can be added to the plugin as follows:
require("codecompanion").setup({
adapters = {
my_custom_adapter = function()
return {} -- My adapter logic
end,
},
}),Setting a Proxy
A proxy can be configured by utilising the adapters.opts table in the config:
require("codecompanion").setup({
adapters = {
opts = {
allow_insecure = true,
proxy = "socks5://127.0.0.1:9999",
},
},
}),Changing a Model
Many adapters allow model selection via the schema.model.default property:
require("codecompanion").setup({
adapters = {
openai = function()
return require("codecompanion.adapters").extend("openai", {
schema = {
model = {
default = "gpt-4",
},
},
})
end,
},
}),User Contributed Adapters
Thanks to the community for building the following adapters:
The section of the discussion forums which is dedicated to user created adapters can be found here. Use these individual threads as a place to raise issues and ask questions about your specific adapters.
Example: Using OpenAI Compatible Models
If your LLM states that it is "OpenAI compatible", then you can leverage the openai_compatible adapter, modifying some elements such as the URL in the env table, the API key and altering the schema:
NOTE
The schema in this instance is provided only as an example and must be modified according to the requirements of the model you use. The options are chosen to show how to use different types of parameters.
require("codecompanion").setup({
adapters = {
my_openai = function()
return require("codecompanion.adapters").extend("openai_compatible", {
env = {
url = "http[s]://open_compatible_ai_url", -- optional: default value is ollama url http://127.0.0.1:11434
api_key = "OpenAI_API_KEY", -- optional: if your endpoint is authenticated
chat_url = "/v1/chat/completions", -- optional: default value, override if different
models_endpoint = "/v1/models", -- optional: attaches to the end of the URL to form the endpoint to retrieve models
},
schema = {
model = {
default = "deepseek-r1-671b", -- define llm model to be used
},
temperature = {
order = 2,
mapping = "parameters",
type = "number",
optional = true,
default = 0.8,
desc = "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.",
validate = function(n)
return n >= 0 and n <= 2, "Must be between 0 and 2"
end,
},
max_completion_tokens = {
order = 3,
mapping = "parameters",
type = "integer",
optional = true,
default = nil,
desc = "An upper bound for the number of tokens that can be generated for a completion.",
validate = function(n)
return n > 0, "Must be greater than 0"
end,
},
stop = {
order = 4,
mapping = "parameters",
type = "string",
optional = true,
default = nil,
desc = "Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile.",
validate = function(s)
return s:len() > 0, "Cannot be an empty string"
end,
},
logit_bias = {
order = 5,
mapping = "parameters",
type = "map",
optional = true,
default = nil,
desc = "Modify the likelihood of specified tokens appearing in the completion. Maps tokens (specified by their token ID) to an associated bias value from -100 to 100. Use https://platform.openai.com/tokenizer to find token IDs.",
subtype_key = {
type = "integer",
},
subtype = {
type = "integer",
validate = function(n)
return n >= -100 and n <= 100, "Must be between -100 and 100"
end,
},
},
},
})
end,
},
})Example: Using Ollama Remotely
To use Ollama remotely, change the URL in the env table, set an API key and pass it via an "Authorization" header:
require("codecompanion").setup({
adapters = {
ollama = function()
return require("codecompanion.adapters").extend("ollama", {
env = {
url = "https://my_ollama_url",
api_key = "OLLAMA_API_KEY",
},
headers = {
["Content-Type"] = "application/json",
["Authorization"] = "Bearer ${api_key}",
},
parameters = {
sync = true,
},
})
end,
},
})Example: Azure OpenAI
Below is an example of how you can leverage the azure_openai adapter within the plugin:
require("codecompanion").setup({
adapters = {
azure_openai = function()
return require("codecompanion.adapters").extend("azure_openai", {
env = {
api_key = "YOUR_AZURE_OPENAI_API_KEY",
endpoint = "YOUR_AZURE_OPENAI_ENDPOINT",
},
schema = {
model = {
default = "YOUR_DEPLOYMENT_NAME",
},
},
})
end,
},
strategies = {
chat = {
adapter = "azure_openai",
},
inline = {
adapter = "azure_openai",
},
},
}),Hiding Default Adapters
By default, the plugin shows all available adapters, including the defaults. If you prefer to only display the adapters defined in your user configuration, you can set the show_defaults option to false:
require("codecompanion").setup({
adapters = {
opts = {
show_defaults = false,
},
-- Define your custom adapters here
},
})When show_defaults is set to false, only the adapters specified in your configuration will be used, hiding the default ones provided by the plugin.