agentscope.models.openai_model

Model wrapper for OpenAI models

class OpenAIChatWrapper(config_name: str, model_name: str | None = None, api_key: str | None = None, organization: str | None = None, client_args: dict | None = None, stream: bool = False, generate_args: dict | None = None, **kwargs: Any)[source]

Bases: OpenAIWrapperBase

The model wrapper for OpenAI’s chat API.

format(*args: Msg | list[Msg] | None, multi_agent_mode: bool = True) → List[dict][source]

Format the input string and dictionary into the format that OpenAI Chat API required. If you’re using a OpenAI-compatible model without a prefix “gpt-” in its name, the format method will automatically format the input messages into the required format.

Parameters:

  • args (Union[Msg, list[Msg], None]) – The input arguments to be formatted, where each argument should be a Msg object, or a list of Msg objects. The None input will be ignored.

  • multi_agent_mode (bool, defaults to True) – Formatting the messages in multi-agent mode or not. If false, the messages will be formatted in chat mode, where only a user and an assistant roles are involved.

Returns:

The formatted messages in the format that OpenAI Chat API required.

Return type:

List[dict]

format_tools_json_schemas(schemas: dict[str, dict]) → list[dict][source]

Format the JSON schemas of the tool functions to the format that the model API provider expects.

Example

An example of the input schemas parsed from the service toolkit

..code-block:: json

{
“bing_search”: {

“type”: “function”, “function”: {

“name”: “bing_search”, “description”: “Search the web using Bing.”, “parameters”: {

“type”: “object”, “properties”: {

“query”: {

“type”: “string”, “description”: “The search query.”,

}

}, “required”: [“query”],

}

}

}

}

Parameters:

schemas (dict[str, dict]) – The tools JSON schemas parsed from the service toolkit module, which can be accessed by service_toolkit.json_schemas.

Returns:

The formatted JSON schemas of the tool functions.

Return type:

list[dict]

config_name: str

The name of the model configuration.

model_name: str

The name of the model, which is used in model api calling.

model_type: str = 'openai_chat'

The type of the model wrapper, which is to identify the model wrapper class in model configuration.

class OpenAIDALLEWrapper(config_name: str, model_name: str | None = None, api_key: str | None = None, organization: str | None = None, client_args: dict | None = None, generate_args: dict | None = None, **kwargs: Any)[source]

Bases: OpenAIWrapperBase

The model wrapper for OpenAI’s DALL·E API.

Response:
{
    "created": 1589478378,
    "data": [
        {
            "url": "https://..."
        },
        {
            "url": "https://..."
        }
    ]
}
config_name: str

The name of the model configuration.

model_name: str

The name of the model, which is used in model api calling.

model_type: str = 'openai_dall_e'

The type of the model wrapper, which is to identify the model wrapper class in model configuration.

class OpenAIEmbeddingWrapper(config_name: str, model_name: str | None = None, api_key: str | None = None, organization: str | None = None, client_args: dict | None = None, generate_args: dict | None = None, **kwargs: Any)[source]

Bases: OpenAIWrapperBase

The model wrapper for OpenAI embedding API.

Response:

  • Refer to

https://platform.openai.com/docs/api-reference/embeddings/create

{
    "object": "list",
    "data": [
        {
            "object": "embedding",
            "embedding": [
                0.0023064255,
                -0.009327292,
                .... (1536 floats total for ada-002)
                -0.0028842222,
            ],
            "index": 0
        }
    ],
    "model": "text-embedding-ada-002",
    "usage": {
        "prompt_tokens": 8,
        "total_tokens": 8
    }
}
config_name: str

The name of the model configuration.

model_name: str

The name of the model, which is used in model api calling.

model_type: str = 'openai_embedding'

The type of the model wrapper, which is to identify the model wrapper class in model configuration.

class OpenAIWrapperBase(config_name: str, model_name: str | None = None, api_key: str | None = None, organization: str | None = None, client_args: dict | None = None, generate_args: dict | None = None, **kwargs: Any)[source]

Bases: ModelWrapperBase, ABC

The model wrapper for OpenAI API.

Response:
{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "gpt-4o-mini",
    "system_fingerprint": "fp_44709d6fcb",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello there, how may I assist you?",
            },
            "logprobs": null,
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}