Skip to content

Openai

OpenaiLLM

OpenAILLM

Bases: AsyncLLM

OpenAI LLM implementation running the async API client.

Attributes:

Name Type Description
model str

the model name to use for the LLM e.g. "gpt-3.5-turbo", "gpt-4", etc. Supported models can be found here.
base_url Optional[RuntimeParameter[str]]

the base URL to use for the OpenAI API requests. Defaults to None, which means that the value set for the environment variable OPENAI_BASE_URL will be used, or "https://api.openai.com/v1" if not set.
api_key Optional[RuntimeParameter[SecretStr]]

the API key to authenticate the requests to the OpenAI API. Defaults to None which means that the value set for the environment variable OPENAI_API_KEY will be used, or None if not set.
max_retries RuntimeParameter[int]

the maximum number of times to retry the request to the API before failing. Defaults to 6.
timeout RuntimeParameter[int]

the maximum time in seconds to wait for a response from the API. Defaults to 120.
Runtime parameters
  • base_url: the base URL to use for the OpenAI API requests. Defaults to None.
  • api_key: the API key to authenticate the requests to the OpenAI API. Defaults to None.
  • max_retries: the maximum number of times to retry the request to the API before failing. Defaults to 6.
  • timeout: the maximum time in seconds to wait for a response from the API. Defaults to 120.
Source code in src/distilabel/llms/openai.py 
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
class OpenAILLM(AsyncLLM):
    """OpenAI LLM implementation running the async API client.

    Attributes:
        model: the model name to use for the LLM e.g. "gpt-3.5-turbo", "gpt-4", etc.
            Supported models can be found [here](https://platform.openai.com/docs/guides/text-generation).
        base_url: the base URL to use for the OpenAI API requests. Defaults to `None`, which
            means that the value set for the environment variable `OPENAI_BASE_URL` will
            be used, or "https://api.openai.com/v1" if not set.
        api_key: the API key to authenticate the requests to the OpenAI API. Defaults to
            `None` which means that the value set for the environment variable `OPENAI_API_KEY`
            will be used, or `None` if not set.
        max_retries: the maximum number of times to retry the request to the API before
            failing. Defaults to `6`.
        timeout: the maximum time in seconds to wait for a response from the API. Defaults
            to `120`.

    Runtime parameters:
        - `base_url`: the base URL to use for the OpenAI API requests. Defaults to `None`.
        - `api_key`: the API key to authenticate the requests to the OpenAI API. Defaults
            to `None`.
        - `max_retries`: the maximum number of times to retry the request to the API before
            failing. Defaults to `6`.
        - `timeout`: the maximum time in seconds to wait for a response from the API. Defaults
            to `120`.
    """

    model: str
    base_url: Optional[RuntimeParameter[str]] = Field(
        default_factory=lambda: os.getenv(
            "OPENAI_BASE_URL", "https://api.openai.com/v1"
        ),
        description="The base URL to use for the OpenAI API requests.",
    )
    api_key: Optional[RuntimeParameter[SecretStr]] = Field(
        default_factory=lambda: os.getenv(_OPENAI_API_KEY_ENV_VAR_NAME),
        description="The API key to authenticate the requests to the OpenAI API.",
    )
    max_retries: RuntimeParameter[int] = Field(
        default=6,
        description="The maximum number of times to retry the request to the API before"
        " failing.",
    )
    timeout: RuntimeParameter[int] = Field(
        default=120,
        description="The maximum time in seconds to wait for a response from the API.",
    )

    _api_key_env_var: str = PrivateAttr(_OPENAI_API_KEY_ENV_VAR_NAME)
    _aclient: Optional["AsyncOpenAI"] = PrivateAttr(...)

    def load(self) -> None:
        """Loads the `AsyncOpenAI` client to benefit from async requests."""
        super().load()

        try:
            from openai import AsyncOpenAI
        except ImportError as ie:
            raise ImportError(
                "OpenAI Python client is not installed. Please install it using"
                " `pip install openai`."
            ) from ie

        if self.api_key is None:
            raise ValueError(
                f"To use `{self.__class__.__name__}` an API key must be provided via `api_key`"
                f" attribute or runtime parameter, or set the environment variable `{self._api_key_env_var}`."
            )

        self._aclient = AsyncOpenAI(
            base_url=self.base_url,
            api_key=self.api_key.get_secret_value(),
            max_retries=self.max_retries,
            timeout=self.timeout,
        )

    @property
    def model_name(self) -> str:
        """Returns the model name used for the LLM."""
        return self.model

    @validate_call
    async def agenerate(  # type: ignore
        self,
        input: ChatType,
        num_generations: int = 1,
        max_new_tokens: int = 128,
        frequency_penalty: float = 0.0,
        presence_penalty: float = 0.0,
        temperature: float = 1.0,
        top_p: float = 1.0,
    ) -> GenerateOutput:
        """Generates `num_generations` responses for the given input using the OpenAI async
        client.

        Args:
            input: a single input in chat format to generate responses for.
            num_generations: the number of generations to create per input. Defaults to
                `1`.
            max_new_tokens: the maximum number of new tokens that the model will generate.
                Defaults to `128`.
            frequency_penalty: the repetition penalty to use for the generation. Defaults
                to `0.0`.
            presence_penalty: the presence penalty to use for the generation. Defaults to
                `0.0`.
            temperature: the temperature to use for the generation. Defaults to `0.1`.
            top_p: the top-p value to use for the generation. Defaults to `1.0`.

        Returns:
            A list of lists of strings containing the generated responses for each input.
        """
        completion = await self._aclient.chat.completions.create(  # type: ignore
            messages=input,  # type: ignore
            model=self.model,
            max_tokens=max_new_tokens,
            n=num_generations,
            frequency_penalty=frequency_penalty,
            presence_penalty=presence_penalty,
            temperature=temperature,
            top_p=top_p,
            timeout=50,
        )
        generations = []
        for choice in completion.choices:
            if (content := choice.message.content) is None:
                self._logger.warning(
                    f"Received no response using OpenAI client (model: '{self.model}')."
                    f" Finish reason was: {choice.finish_reason}"
                )
            generations.append(content)
        return generations

model_name: str property

Returns the model name used for the LLM.

agenerate(input, num_generations=1, max_new_tokens=128, frequency_penalty=0.0, presence_penalty=0.0, temperature=1.0, top_p=1.0) async

Generates num_generations responses for the given input using the OpenAI async client.

Parameters:

Name Type Description Default
input ChatType

a single input in chat format to generate responses for.

 required
num_generations int

the number of generations to create per input. Defaults to 1.

 1
max_new_tokens int

the maximum number of new tokens that the model will generate. Defaults to 128.

 128
frequency_penalty float

the repetition penalty to use for the generation. Defaults to 0.0.

 0.0
presence_penalty float

the presence penalty to use for the generation. Defaults to 0.0.

 0.0
temperature float

the temperature to use for the generation. Defaults to 0.1.

 1.0
top_p float

the top-p value to use for the generation. Defaults to 1.0.

 1.0

Returns:

Type Description
GenerateOutput

A list of lists of strings containing the generated responses for each input.
Source code in src/distilabel/llms/openai.py 
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
@validate_call
async def agenerate(  # type: ignore
    self,
    input: ChatType,
    num_generations: int = 1,
    max_new_tokens: int = 128,
    frequency_penalty: float = 0.0,
    presence_penalty: float = 0.0,
    temperature: float = 1.0,
    top_p: float = 1.0,
) -> GenerateOutput:
    """Generates `num_generations` responses for the given input using the OpenAI async
    client.

    Args:
        input: a single input in chat format to generate responses for.
        num_generations: the number of generations to create per input. Defaults to
            `1`.
        max_new_tokens: the maximum number of new tokens that the model will generate.
            Defaults to `128`.
        frequency_penalty: the repetition penalty to use for the generation. Defaults
            to `0.0`.
        presence_penalty: the presence penalty to use for the generation. Defaults to
            `0.0`.
        temperature: the temperature to use for the generation. Defaults to `0.1`.
        top_p: the top-p value to use for the generation. Defaults to `1.0`.

    Returns:
        A list of lists of strings containing the generated responses for each input.
    """
    completion = await self._aclient.chat.completions.create(  # type: ignore
        messages=input,  # type: ignore
        model=self.model,
        max_tokens=max_new_tokens,
        n=num_generations,
        frequency_penalty=frequency_penalty,
        presence_penalty=presence_penalty,
        temperature=temperature,
        top_p=top_p,
        timeout=50,
    )
    generations = []
    for choice in completion.choices:
        if (content := choice.message.content) is None:
            self._logger.warning(
                f"Received no response using OpenAI client (model: '{self.model}')."
                f" Finish reason was: {choice.finish_reason}"
            )
        generations.append(content)
    return generations

load()

Loads the AsyncOpenAI client to benefit from async requests.

Source code in src/distilabel/llms/openai.py 
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
def load(self) -> None:
    """Loads the `AsyncOpenAI` client to benefit from async requests."""
    super().load()

    try:
        from openai import AsyncOpenAI
    except ImportError as ie:
        raise ImportError(
            "OpenAI Python client is not installed. Please install it using"
            " `pip install openai`."
        ) from ie

    if self.api_key is None:
        raise ValueError(
            f"To use `{self.__class__.__name__}` an API key must be provided via `api_key`"
            f" attribute or runtime parameter, or set the environment variable `{self._api_key_env_var}`."
        )

    self._aclient = AsyncOpenAI(
        base_url=self.base_url,
        api_key=self.api_key.get_secret_value(),
        max_retries=self.max_retries,
        timeout=self.timeout,
    )