The runtime handle the index is resolved from.
Stores a vector, replacing any vector already under that id.
The runtime handle.
Id to store the vector under.
The embedding.
Optionalmetadata: Record<string, unknown>
Metadata to store alongside it.
The mutation id.
Reports whether the capability is actually usable on this runtime.
The runtime handle.
true when calls will reach a real backing resource.
A capability backed by an optional resource answers false when that
resource was never provisioned. Implementations must document what each
method does in that state — degrade or throw — and must not vary it, since
a caller choosing between two implementations is relying on the answer
meaning the same thing in both.
Deletes vectors by id.
The runtime handle.
Ids to delete.
The mutation id.
Finds the vectors nearest to one supplied.
The runtime handle.
The query embedding.
OptionaltopK: number
How many matches to return. Falls back to the configured default.
The matches, nearest first.
Finds the vectors nearest to one already indexed.
The runtime handle.
Id of the vector to search from.
The matches, nearest first.
Storage and nearest-neighbour search over embeddings.
Remarks
Has no opinion about where a vector came from — pairing it with InferenceEngine is the caller's decision, and an embedding produced anywhere else indexes just as well.
Writes are applied asynchronously by most backends, so a mutation id comes back rather than the applied state: a vector just written is not necessarily a vector already searchable.
Author
Bayu Dwiyan Satria
Version
1.0.0
Since
1.0.0