| Name | Type | Description |
|---|---|---|
metadata | Json | Default: NoneMetadata to filter by. Exact match filter for each KV pair. |
graph_id | str | None | Default: NoneThe ID of the graph to filter by. The graph ID is normally set in your langgraph.json configuration. |
name | str | None | Default: None |
limit | int | Default: 10 |
offset | int | Default: 0 |
sort_by | AssistantSortBy | None | Default: None |
sort_order | SortOrder | None | Default: None |
select | list[AssistantSelectField] | None | Default: None |
response_format | Literal['array', 'object'] | Default: 'array' |
headers | Mapping[str, str] | None | Default: None |
Search for assistants.
client = get_sync_client(url="http://localhost:2024")
response = client.assistants.search(
metadata = {"name":"my_name"},
graph_id="my_graph_id",
limit=5,
offset=5,
response_format="object",
)
assistants = response["assistants"]
next_cursor = response["next"]The name of the assistant to filter by. The filtering logic will match assistants where 'name' is a substring (case insensitive) of the assistant name.
The maximum number of results to return.
The number of results to skip.
The field to sort by.
The order to sort by.
Specific assistant fields to include in the response.
Controls the response shape. Use "array" (default)
to return a bare list of assistants, or "object" to return
a mapping containing assistants plus pagination metadata.
Defaults to "array", though this default will be changed to "object" in a future release.
Optional custom headers to include with the request.