Performs semantic search using auto-generated embeddings.
semantic_search(
self,
search_text: str,
search_field: str,
k: int = 4,
task_type: str = 'RETRIEVAL_QUERY',
filter_: dict | None = None,
**kwargs: Any = {}
) -> list[dict[str, Any]]| Name | Type | Description |
|---|---|---|
search_text* | str | Natural language query text. |
search_field* | str | Name of the vector field to search (must have auto-embedding config). |
k | int | Default: 4Number of neighbors to return. |
task_type | str | Default: 'RETRIEVAL_QUERY'Embedding task type (e.g., "RETRIEVAL_QUERY", "RETRIEVAL_DOCUMENT"). |
filter_ | dict | None | Default: NoneFilter dict (v2 only). |