This endpoint follows the OpenAI API format for generating vector embeddings from input text, but with confidential processing (through AEAD encryption and TEE hardware). The handler receives pre-processed metadata from middleware and forwards the request to the selected node.
Ok(Response) - The embeddings response from the processing nodeErr(AtomaProxyError) - An error status code if any step failsINTERNAL_SERVER_ERROR - Processing or node communication failuresBearer authentication header of the form Bearer <token>, where <token> is your auth token.
A request for confidential computation that includes encrypted data and associated cryptographic parameters
The encrypted payload that needs to be processed (base64 encoded)
Client's public key for Diffie-Hellman key exchange (base64 encoded)
Model name
Node's public key for Diffie-Hellman key exchange (base64 encoded)
Cryptographic nonce used for encryption (base64 encoded)
Hash of the original plaintext body for integrity verification (base64 encoded)
Salt value used in key derivation (base64 encoded)
Unique identifier for the small stack being used
x >= 0Number of compute units to be used for the request, for image generations, as this value is known in advance (the number of pixels to generate)
x >= 0Indicates whether this is a streaming request
Confidential embeddings generated successfully
Represents a response from a confidential compute request
Encrypted response body (base64 encoded)
Nonce used for encryption (base64 encoded)
Hash of the response body (base64 encoded)
Signature of the response body (base64 encoded)
Usage statistics for the request