Method●Since v0.3

create

Create a new assistant.

Useful when graph is configurable and you want to create different assistants based on different configurations.

create(
  self,
  graph_id: str | None,
  config: Config | None = None,
  *,
  context: Context | None = None,
  metadata: Json = None,
  assistant_id: str | None = None,
  if_exists: OnConflictBehavior | None = None,
  name: str | None = None,
  headers: Mapping[str, str] | None = None,
  description: str | None = None,
  params: QueryParamTypes | None = None
) -> Assistant

client = get_sync_client(url="http://localhost:2024")
assistant = client.assistants.create(
    graph_id="agent",
    context={"model_name": "openai"},
    metadata={"number":1},
    assistant_id="my-assistant-id",
    if_exists="do_nothing",
    name="my_name"
)

Parameters

Name	Type	Description
`graph_id`*	`str \| None`	The ID of the graph the assistant should use. The graph ID is normally set in your langgraph.json configuration.
`config`	`Config \| None`	Default:`None` Configuration to use for the graph.
`context`	`Context \| None`	Default:`None` Static context to add to the assistant.
`metadata`	`Json`	Default:`None` Metadata to add to assistant.
`assistant_id`	`str \| None`	Default:`None` Assistant ID to use, will default to a random UUID if not provided.
`if_exists`	`OnConflictBehavior \| None`	Default:`None` How to handle duplicate creation. Defaults to 'raise' under the hood. Must be either 'raise' (raise error if duplicate), or 'do_nothing' (return existing assistant).
`name`	`str \| None`	Default:`None` The name of the assistant. Defaults to 'Untitled' under the hood.
`headers`	`Mapping[str, str] \| None`	Default:`None` Optional custom headers to include with the request.
`description`	`str \| None`	Default:`None` Optional description of the assistant. The description field is available for langgraph-api server version>=0.0.45
`params`	`QueryParamTypes \| None`	Default:`None` Optional query parameters to include with the request.

View source on GitHub

client = get_sync_client(url="http://localhost:2024") assistant = client.assistants.create( graph_id="agent", context={"model_name": "openai"}, metadata={"number":1}, assistant_id="my-assistant-id", if_exists="do_nothing", name="my_name" )

Parameters

Name	Type	Description
`graph_id`*	`str \| None`	The ID of the graph the assistant should use. The graph ID is normally set in your langgraph.json configuration.
`config`	`Config \| None`	Default:`None` Configuration to use for the graph.
`context`	`Context \| None`	Default:`None` Static context to add to the assistant.
`metadata`	`Json`	Default:`None` Metadata to add to assistant.
`assistant_id`	`str \| None`	Default:`None` Assistant ID to use, will default to a random UUID if not provided.
`if_exists`	`OnConflictBehavior \| None`	Default:`None` How to handle duplicate creation. Defaults to 'raise' under the hood. Must be either 'raise' (raise error if duplicate), or 'do_nothing' (return existing assistant).
`name`	`str \| None`	Default:`None` The name of the assistant. Defaults to 'Untitled' under the hood.
`headers`	`Mapping[str, str] \| None`	Default:`None` Optional custom headers to include with the request.
`description`	`str \| None`	Default:`None` Optional description of the assistant. The description field is available for langgraph-api server version>=0.0.45
`params`	`QueryParamTypes \| None`	Default:`None` Optional query parameters to include with the request.

create

Parameters

LangChain Assistant

Menu

create

Parameters