Create an OpenAI-compatible client using Cerebras’s API.

Example:

llm_config={

  • "config_list" - [{

  • "api_type" - “cerebras”,

  • "model" - “llama3.1-8b”,

  • "api_key" - os.environ.get(“CEREBRAS_API_KEY”) }] }

    agent = autogen.AssistantAgent(“my_agent”, llm_config=llm_config)

    Install Cerebras’s python library using: pip install —upgrade cerebras_cloud_sdk

    Resources:

CerebrasClient

class CerebrasClient()

Client for Cerebras’s API.

__init__

def __init__(api_key=None, **kwargs)

Requires api_key or environment variable to be set

Arguments:

  • api_key str - The API key for using Cerebras (or environment variable CEREBRAS_API_KEY needs to be set)

message_retrieval

def message_retrieval(response: ChatCompletion) -> list

Retrieve and return a list of strings or a list of Choice.Message from the response.

NOTE: if a list of Choice.Message is returned, it currently needs to contain the fields of OpenAI’s ChatCompletion Message object, since that is expected for function or tool calling in the rest of the codebase at the moment, unless a custom agent is being used.

get_usage

@staticmethod
def get_usage(response: ChatCompletion) -> dict

Return usage summary of the response using RESPONSE_USAGE_KEYS.

parse_params

def parse_params(params: dict[str, Any]) -> dict[str, Any]

Loads the parameters for Cerebras API from the passed in parameters and returns a validated set. Checks types, ranges, and sets defaults

oai_messages_to_cerebras_messages

def oai_messages_to_cerebras_messages(
        messages: list[dict[str, Any]]) -> list[dict[str, Any]]

Convert messages from OAI format to Cerebras’s format. We correct for any specific role orders and types.

calculate_cerebras_cost

def calculate_cerebras_cost(input_tokens: int, output_tokens: int,
                            model: str) -> float

Calculate the cost of the completion using the Cerebras pricing.