Optional authenticationObject containing any necessary collections-bound authentication, if any.
Most commonly, providerKey: '*SHARED_SECRET_NAME*' may be used here to reference an API key from the Astra KMS.
Db.createCollection and Db.collection both offer an embeddingApiKey parameter which utilizes
header-based auth to pass the provider's token/api-key to the Data API on a per-request basis instead, if that
is preferred (or necessary).
The name of the embedding model to use.
You can find out more information about each model in the DataStax docs, or through DbAdmin.findEmbeddingProviders.
Optional parametersObject allowing arbitrary parameters that may be necessary on a per-model/per-provider basis.
Not all providers need this, but some, such as huggingfaceDedicated have required parameters, others have
optional parameters (e.g. openAi), and some don't require any at all.
You can find out more information about each provider/model in the DataStax docs, or through DbAdmin.findEmbeddingProviders.
The name of the embedding provider which provides the model to use.
You can find out more information about each provider in the DataStax docs, or through DbAdmin.findEmbeddingProviders.
The options for defining the embedding service used for vectorize, to automatically transform your text into a vector ready for semantic vector searching.
You can find out more information about each provider/model in the DataStax docs, or through DbAdmin.findEmbeddingProviders.
Field
provider - The name of the embedding provider which provides the model to use
Field
model - The specific model to use for embedding, or undefined if it's an endpoint-defined model
Field
authentication - Object containing any necessary collections-bound authentication, if any
Field
parameters - Object allowing arbitrary parameters that may be necessary on a per-model basis