Skip to main content

Home Assistant API for Large Language Models

Home Assistant can interact with large language models (LLMs). By exposing a Home Assistant API to an LLM, the LLM can fetch data or control Home Assistant to better assist the user. Home Assistant comes with a built-in LLM API, but custom integrations can register their own to provide more advanced functionality.

Built-in Assist API

Home Assistant has a built-in API which exposes the Assist API to LLMs. This API allows LLMs to interact with Home Assistant via intents, and can be extended by registering intents.

The Assist API is equivalent to the capabilities and exposed entities that are also accessible to the built-in conversation agent. No administrative tasks can be performed.

Supporting LLM APIs

The LLM API needs to be integrated in two places in your integration. Users need to be able to configure which API should be used, and the tools offered by the API should be passed to the LLM when interacting with it.

Options flow

The chosen API should be stored in the config entry options. It should hold a string reference to the API ID. If no API is selected, the key must be omitted.

In your options flow, you should offer a selector to the user to pick which API should be used.

from types import MappingProxyType

from homeassistant.const import CONF_LLM_HASS_API
from homeassistant.core import HomeAssistant, callback
from homeassistant.helpers import llm
from homeassistant.helpers.selector import (

def async_get_options_schema(
hass: HomeAssistant,
options: MappingProxyType[str, Any],
) -> vol.Schema:
"""Return the options schema."""
apis: list[SelectOptionDict] = [
label="No control",
for api in llm.async_get_apis(hass)

return vol.Schema(
description={"suggested_value": options.get(CONF_LLM_HASS_API)},
): SelectSelector(SelectSelectorConfig(options=apis)),

When processing the options, make sure to remove the key if the user selected none before storing the options.

if user_input[CONF_LLM_HASS_API] == "none":
return self.async_create_entry(title="", data=user_input)

Fetching tools

When interacting with the LLM, you should fetch the tools from the selected API and pass them to the LLM together with the extra prompt provided by the API.

from homeassistant.const import CONF_LLM_HASS_API
from homeassistant.core import HomeAssistant, callback
from homeassistant.components import conversation
from homeassistant.helpers import intent, llm

class MyConversationEntity(conversation.ConversationEntity):

def __init__(self, entry: ConfigEntry) -> None:
"""Initialize the agent."""
self.entry = entry


async def async_process(
self, user_input: conversation.ConversationInput
) -> conversation.ConversationResult:
"""Process the user input."""
intent_response = intent.IntentResponse(language=user_input.language)
llm_api: llm.API | None = None
tools: list[dict[str, Any]] | None = None

if self.entry.options.get(CONF_LLM_HASS_API):
llm_api = await llm.async_get_api(
except HomeAssistantError as err:
LOGGER.error("Error getting LLM API: %s", err)
f"Error preparing LLM API: {err}",
return conversation.ConversationResult(
response=intent_response, conversation_id=user_input.conversation_id
tools = [
_format_tool(tool) # TODO format the tools as your LLM expects
for tool in

if llm_api:
api_prompt = llm_api.api_prompt

api_prompt = llm.async_render_no_api_prompt(self.hass)

prompt = "\n".join((user_prompt, api_prompt))

# Interact with LLM and pass tools
request = user_input.text
for _iteration in range(10):
response = ... # Send request to LLM and get response, include tools

if not response.tool_call:

"Tool call: %s(%s)",,
tool_input = llm.ToolInput(,
tool_response = await llm_api.async_call_tool(tool_input)
except (HomeAssistantError, vol.Invalid) as e:
tool_response = {"error": type(e).__name__}
if str(e):
tool_response["error_text"] = str(e)

LOGGER.debug("Tool response: %s", tool_response)
response = tool_response

Best practices

If your conversation entity allows the user to maintain conversation history using the conversation_id, make sure to re-generate the prompt for each interaction and override it in the history that is passed for the follow-up command. This allows the user to always be able to query the latest state of the home.

Creating your own API

To create your own API, you need to create a class that inherits from API and implement the async_get_tools method. The async_get_tools method should return a list of Tool objects that represent the functionality that you want to expose to the LLM.


The llm.Tool class represents a tool that can be called by the LLM.

from homeassistant.core import HomeAssistant
from homeassistant.helper import llm
from homeassistant.util import dt as dt_util
from homeassistant.util.json import JsonObjectType

class TimeTool(llm.Tool):
"""Tool to get the current time."""

name = "GetTime"
description: "Returns the current time."

# Optional. A voluptuous schema of the input parameters.
parameters = vol.Schema({
vol.Optional('timezone'): str,

async def async_call(
self, hass: HomeAssistant, tool_input: ToolInput, llm_context: LLMContext
) -> JsonObjectType:
"""Call the tool."""
if "timezone" in tool_input.tool_args:
tzinfo = dt_util.get_time_zone(tool_input.tool_args["timezone"])
tzinfo = dt_util.DEFAULT_TIME_ZONE


The llm.Tool class has the following attributes:

namestringThe name of the tool. Required.
descriptionstringDescription of the tool to help the LLM understand when and how it should be called. Optional but recommended.
parametersvol.SchemaThe voluptuous schema of the parameters. Defaults to vol.Schema()

The llm.Tool class has the following methods:


Perform the actual operation of the tool when called by the LLM. This must be an async method. Its arguments are hass and an instance of llm.ToolInput.

Response data must be a dict and serializable in JSON homeassistant.util.json.JsonObjectType.

Errors must be raised as HomeAssistantError exceptions (or its subclasses). The response data should not contain error codes used for error handling.

The ToolInput has following attributes:

tool_namestringThe name of the tool being called
tool_argsdictThe arguments provided by the LLM. The arguments are converted and validated using parameters schema.
platformstringThe DOMAIN of the conversation agent using the tool
contextContextThe homeassistant.core.Context of the conversation
user_promptstringThe raw text input that initiated the tool call
languagestringThe language of the conversation agent, or "*" for any language
assistantstringThe assistant name used to control exposed entities. Currently, only conversation is supported.
device_idstringThe device_id of the device the user used to initiate the conversation.


The API object allows creating API instances. An API Instance represents a collection of tools that will be made available to the LLM.

from homeassistant.core import HomeAssistant
from homeassistant.helper import llm
from homeassistant.util import dt as dt_util
from homeassistant.util.json import JsonObjectType

class MyAPI(API):
"""My own API for LLMs."""

def __init__(self, hass: HomeAssistant) -> None:
"""Init the class."""
name="My own API",

async def async_get_api_instance(self, llm_context: LLMContext) -> APIInstance:
"""Return the instance of the API."""
return APIInstance(
api_prompt="Call the tools to fetch data from Home Assistant.",

async def async_setup_api(hass: HomeAssistant) -> None:
"""Register the API with Home Assistant."""
llm.async_register_api(hass, MyAPI())

The llm.API class has the following attributes:

idstringA unique identifier for the API. Required.
namestringThe name of the API. Required.

The llm.APIInstance class has the following attributes:

apiAPIThe API object. Required.
api_promptstringInstructions for LLM on how to use the LLM tools. Required.
llm_contextLLMContextThe context of the tool call. Required.
toolslist[Tool]The tools that are available in this API. Required.