Skip to content

Latest commit

 

History

History
132 lines (94 loc) · 17.8 KB

README.md

File metadata and controls

132 lines (94 loc) · 17.8 KB

ConfidentialChat

(confidential_chat)

Overview

Atoma's API confidential chat completions v1 endpoint

Available Operations

create

This handler processes chat completion requests in a confidential manner, providing additional encryption and security measures for sensitive data processing. It supports both streaming and non-streaming responses while maintaining data confidentiality through AEAD encryption and TEE hardware, for full private AI compute.

Returns

Returns a Result containing either:

  • An HTTP response with the chat completion result
  • A streaming SSE connection for real-time completions
  • An AtomaProxyError error if the request processing fails

Errors

Returns AtomaProxyError::InvalidBody if:

  • The 'stream' field is missing or invalid in the payload

Returns AtomaProxyError::InternalError if:

  • The inference service request fails
  • Response processing encounters errors
  • State manager updates fail

Security Features

  • Utilizes AEAD encryption for request/response data
  • Supports TEE (Trusted Execution Environment) processing
  • Implements secure key exchange using X25519
  • Maintains confidentiality throughout the request lifecycle

Example Usage

from atoma_sdk import AtomaSDK
import os

with AtomaSDK(
    bearer_auth=os.getenv("ATOMASDK_BEARER_AUTH", ""),
) as atoma_sdk:

    res = atoma_sdk.confidential_chat.create(ciphertext="<value>", client_dh_public_key="<value>", model_name="<value>", node_dh_public_key="<value>", nonce="<value>", plaintext_body_hash="<value>", salt="<value>", stack_small_id=486589)

    # Handle response
    print(res)

Parameters

Parameter Type Required Description
ciphertext str ✔️ The encrypted payload that needs to be processed (base64 encoded)
client_dh_public_key str ✔️ Client's public key for Diffie-Hellman key exchange (base64 encoded)
model_name str ✔️ Model name
node_dh_public_key str ✔️ Node's public key for Diffie-Hellman key exchange (base64 encoded)
nonce str ✔️ Cryptographic nonce used for encryption (base64 encoded)
plaintext_body_hash str ✔️ Hash of the original plaintext body for integrity verification (base64 encoded)
salt str ✔️ Salt value used in key derivation (base64 encoded)
stack_small_id int ✔️ Unique identifier for the small stack being used
num_compute_units OptionalNullable[int] ➖ Number 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)
stream OptionalNullable[bool] ➖ Indicates whether this is a streaming request
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.ConfidentialComputeResponse

Errors

Error Type Status Code Content Type
models.APIError 4XX, 5XX */*

create_stream

Example Usage

from atoma_sdk import AtomaSDK
import os

with AtomaSDK(
    bearer_auth=os.getenv("ATOMASDK_BEARER_AUTH", ""),
) as atoma_sdk:

    res = atoma_sdk.confidential_chat.create_stream(ciphertext="<value>", client_dh_public_key="<value>", model_name="<value>", node_dh_public_key="<value>", nonce="<value>", plaintext_body_hash="<value>", salt="<value>", stack_small_id=180107)

    with res as event_stream:
        for event in event_stream:
            # handle event
            print(event, flush=True)

Parameters

Parameter Type Required Description
ciphertext str ✔️ The encrypted payload that needs to be processed (base64 encoded)
client_dh_public_key str ✔️ Client's public key for Diffie-Hellman key exchange (base64 encoded)
model_name str ✔️ Model name
node_dh_public_key str ✔️ Node's public key for Diffie-Hellman key exchange (base64 encoded)
nonce str ✔️ Cryptographic nonce used for encryption (base64 encoded)
plaintext_body_hash str ✔️ Hash of the original plaintext body for integrity verification (base64 encoded)
salt str ✔️ Salt value used in key derivation (base64 encoded)
stack_small_id int ✔️ Unique identifier for the small stack being used
num_compute_units OptionalNullable[int] ➖ Number 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)
stream OptionalNullable[bool] ➖ Indicates whether this is a streaming request
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

Union[eventstreaming.EventStream[models.ConfidentialComputeStreamResponse], eventstreaming.EventStreamAsync[models.ConfidentialComputeStreamResponse]]

Errors

Error Type Status Code Content Type
models.APIError 4XX, 5XX */*