Execute a SemQL semantic search query
Compiles the SemQL query, embeds any text anchors, evaluates matches across the namespace, and returns ranked results.
If the request omits limit, the limit is taken from the SemQL
LIMIT n clause when present.
Requires Content-Type: application/json.
Authorizations
API key bearer token. Obtain from the Noetive dashboard.
Pass as: Authorization: Bearer <api-key>.
Body
Raw SemQL text submitted by the client. Subject to the SemQL query limits — see the "SemQL query limits" section in the API description.
Target namespace alias — a registered name (e.g. articles) or
the well-known global alias. Required; there is no default.
Every request is validated against the namespace's configured
model and dimensions; a mismatch returns 400 invalid_request.
Pass the alias, not the ns_... identifier shown in the
dashboard — a raw identifier is rejected with
400 invalid_request.
64^[A-Za-z0-9_-]+$Embedding model name. Required; there is no default. Must match
the model configured on the namespace, or the request fails with
400 model_not_provisioned.
Embedding vector dimensionality. Required; there is no default.
Must match the dimensionality configured on the namespace for
model, or the request fails with 400 model_not_provisioned.
1 <= x <= 4096Maximum number of results to return. Takes precedence over the
SemQL LIMIT n clause; when both are omitted, 100 results are
returned.
Values above 1000 are clamped to 1000, not rejected — the
request succeeds and returns at most 1000 results. A client that
treats a successful response as "everything matched" will
silently miss results. Narrow the WINDOW or tighten the query
instead of raising the limit.
x >= 1Response
Ranked search results
Ranked list of matched documents.

