Try it
button to try this API now in our playground. It’s the best way to check the full request and response in one place, customize your parameters, and generate ready-to-use code snippets.Sample Request
Requirements
- Maximum dimensions: 2000 rows × 3024 columns; i.e. 2000 chunks with a maximum dimension of 3024
- Format: Dictionary with chunk IDs as keys and embedding arrays as values. These chunk IDs should match the ones that you got on inserting the embeddings.
- Batch constraint: All chunk IDs must belong to the same batch/source
- Chunk ID format: Must be valid strings in format
{batch_id}_{index}
- Consistency: All embedding vectors must have the same dimension
- Values: All embedding values must be numeric (int or float)
Error Responses
All endpoints return consistent error responses following the standard format. For detailed error information, see our Error Responses documentation.Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Query Parameters
Unique identifier for the tenant/organization
"tenant_1234"
Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.
"sub_tenant_4567"
Body
The embeddings of source you want to index
{
"CortexEmbeddings123_0": [
0.123413,
0.655367,
0.987654,
0.123456,
0.789012
],
"CortexEmbeddings123_1": [
0.123413,
0.655367,
0.987654,
0.123456,
0.789012
]
}