# ModelClient ## ``autogen.ModelClient`` Bases: `Protocol` A client class must implement the following methods: - `create` must return a response object that implements the `ModelClientResponseProtocol` - `cost` must return the cost of the response - `get_usage` must return a dict with the following keys: - `prompt_tokens` - `completion_tokens` - `total_tokens` - `cost` - `model` This class is used to create a client that can be used by OpenAIWrapper. The response returned from `create` must adhere to the `ModelClientResponseProtocol` but can be extended however needed. The `message_retrieval` method must be implemented to return a list of str or a list of messages from the response. ### ``RESPONSE_USAGE_KEYS`` ```python RESPONSE_USAGE_KEYS = ['prompt_tokens', 'completion_tokens', 'total_tokens', 'cost', 'model'] ``` ### ``ModelClientResponseProtocol`` Bases: `Protocol` #### ``choices`` ``choices`` #### ``model`` ``model`` #### ``Choice`` Bases: `Protocol` ##### ``message`` ``message`` ##### ``Message`` Bases: `Protocol` ###### ``content`` ``content`` ### ``create`` ``create(params)`` Source code in `autogen/llm_config/client.py` | | | | --- | --- | | ```
42
``` | ```
def create(self, params: dict[str, Any]) -> ModelClientResponseProtocol: ... # pragma: no cover
``` | ### ``message_retrieval`` ``message_retrieval(response)`` 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. Source code in `autogen/llm_config/client.py` | | | | --- | --- | | ```
44
45
46
47
48
49
50
51
52
``` | ```
def message_retrieval(
self, response: ModelClientResponseProtocol
) -> list[str] | list["ModelClient.ModelClientResponseProtocol.Choice.Message"]:
"""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.
"""
... # pragma: no cover
``` | ### ``cost`` ``cost(response)`` Source code in `autogen/llm_config/client.py` | | | | --- | --- | | ```
54
``` | ```
def cost(self, response: ModelClientResponseProtocol) -> float: ... # pragma: no cover
``` | ### ``get_usage`` ``get_usage(response)`` Return usage summary of the response using `RESPONSE_USAGE_KEYS`. Source code in `autogen/llm_config/client.py` | | | | --- | --- | | ```
56
57
58
59
``` | ```
@staticmethod
def get_usage(response: ModelClientResponseProtocol) -> dict[str, Any]:
"""Return usage summary of the response using RESPONSE_USAGE_KEYS."""
... # pragma: no cover
``` |