Module `blind_llama.completion`

Functions

def create(model: str = 'meta-llama/Llama-2-70b-chat-hf', prompt: str = '', temperature: float = 0.7, verbose: bool = False) ‑> str

Start a prediction.

Args

model (str, default = "meta-llama/Llama-2-70b-chat-hf"): The model on which you want to run a prediction on.
prompt : str: The prompt on which you want to run a prediction on.
temperature : float, default = 0.7: The temperature requested (default to 0.7).
verbose : bool, default = False: Allows to print all details of the verification process.

Returns

str: The result of the prediction made by the server

Classes

class AICertInvalidAttestationException (message: str, *args: object)

Invalid attestation error

Ancestors

AICertException
builtins.Exception
builtins.BaseException

class AICertInvalidAttestationFormatException (err: Exception)

AICert attestation parsing error (json)

Ancestors

AICertException
builtins.Exception
builtins.BaseException

class Client (verbose: bool = False)

A class to represent a connection to a BlindLlama server.

Init the Client class.

Args

verbose : bool, default = False: Allows to print all details of the verification process.

Returns

Client: Client object.

Methods

def predict(self, prompt: str, temperature: float = 0.7) ‑> str

Start a prediction.

Args

prompt : str: The prompt on which you want to run a prediction on.
temperature : float, default = 0.7: The temperature requested.

Returns

str: The result of the prediction made by the server

def verify_build_response(self, build_response: bytes, ca_cert='', expected_pcr='')

Verify received attesation validity

Parse the JSON reponse
Check simulation mode
Verify certificate chain
Verify quote signature
Verify boot PCRs (firmware, bootloader, initramfs, OS)
Verify event log (final hash in PCR_FOR_MEASUREMENT) by replaying it (works like a chain of hashes)
Verify TLS certificate (final hash in PCR_FOR_CERTIFICATE)

Args

build_response : bytes: reponse of the attestation endpoint
verbose : bool, default = False: whether to print verification information in stdout

def verify_server_certificate(self, expected_pcr)

Retrieve server certificate and validate it with the attestation report.

class PromptRequest (**data: Any)

Usage docs: https://docs.pydantic.dev/2.5/concepts/models/

A base class for creating Pydantic models.

Attributes

__class_vars__: The names of classvars defined on the model.
__private_attributes__: Metadata about the private attributes of the model.
__signature__: The signature for instantiating the model.
__pydantic_complete__: Whether model building is completed, or if there are still undefined fields.
__pydantic_core_schema__: The pydantic-core schema used to build the SchemaValidator and SchemaSerializer.
__pydantic_custom_init__: Whether the model has a custom __init__ function.
__pydantic_decorators__: Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.
__pydantic_generic_metadata__: Metadata for generic models; contains data used for a similar purpose to args, origin, parameters in typing-module generics. May eventually be replaced by these.
__pydantic_parent_namespace__: Parent namespace of the model, used for automatic rebuilding of models.
__pydantic_post_init__: The name of the post-init method for the model, if defined.
__pydantic_root_model__: Whether the model is a RootModel.
__pydantic_serializer__: The pydantic-core SchemaSerializer used to dump instances of the model.
__pydantic_validator__: The pydantic-core SchemaValidator used to validate instances of the model.
__pydantic_extra__: An instance attribute with the values of extra fields from validation when model_config['extra'] == 'allow'.
__pydantic_fields_set__: An instance attribute with the names of fields explicitly set.
__pydantic_private__: Instance attribute with the values of private attributes set on the model instance.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

__init__ uses __pydantic_self__ instead of the more common self for the first arg to allow self as a field name.

Ancestors

pydantic.main.BaseModel

Class variables

var inputs : str
var model_config
var model_fields
var temperature : float

Static methods

def valid_input(v)
def valid_temperature(v)