Method create_chat_completion

llama_cpp/llama.py:1997–2098

Generate a chat completion from a list of messages. Args: messages: A list of messages to generate a response for. functions: A list of functions to use for the chat completion. function_call: A function call to use for the chat completion. to

(
        self,
        messages: List[ChatCompletionRequestMessage],
        functions: Optional[List[ChatCompletionFunction]] = None,
        function_call: Optional[ChatCompletionRequestFunctionCall] = None,
        tools: Optional[List[ChatCompletionTool]] = None,
        tool_choice: Optional[ChatCompletionToolChoiceOption] = None,
        temperature: float = 0.2,
        top_p: float = 0.95,
        top_k: int = 40,
        min_p: float = 0.05,
        typical_p: float = 1.0,
        stream: bool = False,
        stop: Optional[Union[str, List[str]]] = [],
        seed: Optional[int] = None,
        response_format: Optional[ChatCompletionRequestResponseFormat] = None,
        max_tokens: Optional[int] = None,
        presence_penalty: float = 0.0,
        frequency_penalty: float = 0.0,
        repeat_penalty: float = 1.0,
        tfs_z: float = 1.0,
        mirostat_mode: int = 0,
        mirostat_tau: float = 5.0,
        mirostat_eta: float = 0.1,
        model: Optional[str] = None,
        logits_processor: Optional[LogitsProcessorList] = None,
        grammar: Optional[LlamaGrammar] = None,
        logit_bias: Optional[Dict[int, float]] = None,
        logprobs: Optional[bool] = None,
        top_logprobs: Optional[int] = None,
    )

        )

    def create_chat_completion(
        self,
        messages: List[ChatCompletionRequestMessage],
        functions: Optional[List[ChatCompletionFunction]] = None,
        function_call: Optional[ChatCompletionRequestFunctionCall] = None,
        tools: Optional[List[ChatCompletionTool]] = None,
        tool_choice: Optional[ChatCompletionToolChoiceOption] = None,
        temperature: float = 0.2,
        top_p: float = 0.95,
        top_k: int = 40,
        min_p: float = 0.05,
        typical_p: float = 1.0,
        stream: bool = False,
        stop: Optional[Union[str, List[str]]] = [],
        seed: Optional[int] = None,
        response_format: Optional[ChatCompletionRequestResponseFormat] = None,
        max_tokens: Optional[int] = None,
        presence_penalty: float = 0.0,
        frequency_penalty: float = 0.0,
        repeat_penalty: float = 1.0,
        tfs_z: float = 1.0,
        mirostat_mode: int = 0,
        mirostat_tau: float = 5.0,
        mirostat_eta: float = 0.1,
        model: Optional[str] = None,
        logits_processor: Optional[LogitsProcessorList] = None,
        grammar: Optional[LlamaGrammar] = None,
        logit_bias: Optional[Dict[int, float]] = None,
        logprobs: Optional[bool] = None,
        top_logprobs: Optional[int] = None,
    ) -> Union[
        CreateChatCompletionResponse, Iterator[CreateChatCompletionStreamResponse]
    ]:
        """Generate a chat completion from a list of messages.

        Args:
            messages: A list of messages to generate a response for.
            functions: A list of functions to use for the chat completion.
            function_call: A function call to use for the chat completion.
            tools: A list of tools to use for the chat completion.
            tool_choice: A tool choice to use for the chat completion.
            temperature: The temperature to use for sampling.
            top_p: The top-p value to use for nucleus sampling. Nucleus sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
            top_k: The top-k value to use for sampling. Top-K sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
            min_p: The min-p value to use for minimum p sampling. Minimum P sampling as described in https://github.com/ggerganov/llama.cpp/pull/3841
            typical_p: The typical-p value to use for sampling. Locally Typical Sampling implementation described in the paper https://arxiv.org/abs/2202.00666.
            stream: Whether to stream the results.
            stop: A list of strings to stop generation when encountered.
            seed: The seed to use for sampling.
            response_format: The response format to use for the chat completion. Use { "type": "json_object" } to contstrain output to only valid json.
            max_tokens: The maximum number of tokens to generate. If max_tokens <= 0 or None, the maximum number of tokens to generate is unlimited and depends on n_ctx.
            presence_penalty: The penalty to apply to tokens based on their presence in the prompt.
            frequency_penalty: The penalty to apply to tokens based on their frequency in the prompt.
            repeat_penalty: The penalty to apply to repeated tokens.
            tfs_z: The tail-free sampling parameter.
            mirostat_mode: The mirostat sampling mode.
            mirostat_tau: The mirostat sampling tau parameter.
            mirostat_eta: The mirostat sampling eta parameter.