autogen.oai.anthropic.AnthropicClient

AnthropicClient

AnthropicClient(**kwargs: Any)

Initialize the Anthropic API client.

Parameters:

Name	Description
**kwargs	Type: Any

Instance Attributes

api_key

aws_access_key

aws_region

aws_secret_key

aws_session_token

gcp_auth_token

gcp_project_id

gcp_region

Instance Methods

convert_tools_to_functions

convert_tools_to_functions(tools: list) -> list

Convert tool definitions into Anthropic-compatible functions, updating nested $ref paths in property schemas.

Parameters:

Name	Description
tools	List of tool definitions. Type: list

Returns:

Type	Description
list	list: List of functions with updated $ref paths.

cost

cost(self, response) -> float

Calculate the cost of the completion using the Anthropic pricing.

Parameters:

Name	Description
response

create

create(self, params: dict[str, Any]) -> ChatCompletionExtended

Creates a completion using the Anthropic API.

Parameters:

Name	Description
params	Type: dict[str, Any]

get_usage

get_usage(response: ChatCompletion) -> dict

Get the usage of tokens and their cost information.

Parameters:

Name	Description
response	Type: ChatCompletion

load_config

load_config(self, params: dict[str, Any]) -> 

Load the configuration for the Anthropic API client.

Parameters:

Name	Description
params	Type: dict[str, Any]

message_retrieval

message_retrieval(self, response) -> 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.

Parameters:

Name	Description
response

openai_func_to_anthropic

openai_func_to_anthropic(openai_func: dict) -> dict

Parameters:

Name	Description
openai_func	Type: dict