模型接口

def validate_provider_credentials(self, credentials: dict) -> None:
    """
    Validate provider credentials
    You can choose any validate_credentials method of model type or implement validate method by yourself,
    such as: get model list api

    if validate failed, raise exception

    :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
    """

class XinferenceProvider(Provider):
    def validate_provider_credentials(self, credentials: dict) -> None:
        pass

def validate_credentials(self, model: str, credentials: dict) -> None:
    """
    Validate model credentials

    :param model: model name
    :param credentials: model credentials
    :return:
    """

@property
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
    """
    Map model invoke error to unified error
    The key is the error type thrown to the caller
    The value is the error type thrown by the model,
    which needs to be converted into a unified error type for the caller.

    :return: Invoke error mapping
    """

def _invoke(self, model: str, credentials: dict,
            prompt_messages: list[PromptMessage], model_parameters: dict,
            tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
            stream: bool = True, user: Optional[str] = None) \
        -> Union[LLMResult, Generator]:
    """
    Invoke large language model

    :param model: model name
    :param credentials: model credentials
    :param prompt_messages: prompt messages
    :param model_parameters: model parameters
    :param tools: tools for tool calling
    :param stop: stop words
    :param stream: is stream response
    :param user: unique user id
    :return: full response or stream response chunk generator result
    """

def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
                   tools: Optional[list[PromptMessageTool]] = None) -> int:
    """
    Get number of tokens for given prompt messages

    :param model: model name
    :param credentials: model credentials
    :param prompt_messages: prompt messages
    :param tools: tools for tool calling
    :return:
    """

def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
    """
    Get customizable model schema

    :param model: model name
    :param credentials: model credentials
    :return: model schema
    """

def _invoke(self, model: str, credentials: dict,
            texts: list[str], user: Optional[str] = None) \
        -> TextEmbeddingResult:
    """
    Invoke large language model

    :param model: model name
    :param credentials: model credentials
    :param texts: texts to embed
    :param user: unique user id
    :return: embeddings result
    """

def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
    """
    Get number of tokens for given prompt messages

    :param model: model name
    :param credentials: model credentials
    :param texts: texts to embed
    :return:
    """

def _invoke(self, model: str, credentials: dict,
            query: str, docs: list[str], score_threshold: Optional[float] = None, top_n: Optional[int] = None,
            user: Optional[str] = None) \
        -> RerankResult:
    """
    Invoke rerank model

    :param model: model name
    :param credentials: model credentials
    :param query: search query
    :param docs: docs for reranking
    :param score_threshold: score threshold
    :param top_n: top n
    :param user: unique user id
    :return: rerank result
    """

def _invoke(self, model: str, credentials: dict,
            file: IO[bytes], user: Optional[str] = None) \
        -> str:
    """
    Invoke large language model

    :param model: model name
    :param credentials: model credentials
    :param file: audio file
    :param user: unique user id
    :return: text for given audio file
    """        

def _invoke(self, model: str, credentials: dict, content_text: str, streaming: bool, user: Optional[str] = None):
    """
    Invoke large language model

    :param model: model name
    :param credentials: model credentials
    :param content_text: text content to be translated
    :param streaming: output is streaming
    :param user: unique user id
    :return: translated audio file
    """        

def _invoke(self, model: str, credentials: dict,
            text: str, user: Optional[str] = None) \
        -> bool:
    """
    Invoke large language model

    :param model: model name
    :param credentials: model credentials
    :param text: text to moderate
    :param user: unique user id
    :return: false if text is safe, true otherwise
    """

class PromptMessageRole(Enum):
    """
    Enum class for prompt message.
    """
    SYSTEM = "system"
    USER = "user"
    ASSISTANT = "assistant"
    TOOL = "tool"

class PromptMessageContentType(Enum):
    """
    Enum class for prompt message content type.
    """
    TEXT = 'text'
    IMAGE = 'image'

class PromptMessageContent(BaseModel):
    """
    Model class for prompt message content.
    """
    type: PromptMessageContentType
    data: str  # 内容数据

class TextPromptMessageContent(PromptMessageContent):
    """
    Model class for text prompt message content.
    """
    type: PromptMessageContentType = PromptMessageContentType.TEXT

class ImagePromptMessageContent(PromptMessageContent):
    """
    Model class for image prompt message content.
    """
    class DETAIL(Enum):
        LOW = 'low'
        HIGH = 'high'

    type: PromptMessageContentType = PromptMessageContentType.IMAGE
    detail: DETAIL = DETAIL.LOW  # 分辨率

class PromptMessage(ABC, BaseModel):
    """
    Model class for prompt message.
    """
    role: PromptMessageRole  # 消息角色
    content: Optional[str | list[PromptMessageContent]] = None  # 支持两种类型，字符串和内容列表，内容列表是为了满足多模态的需要，可详见 PromptMessageContent 说明。
    name: Optional[str] = None  # 名称，可选。

class UserPromptMessage(PromptMessage):
    """
    Model class for user prompt message.
    """
    role: PromptMessageRole = PromptMessageRole.USER

class AssistantPromptMessage(PromptMessage):
    """
    Model class for assistant prompt message.
    """
    class ToolCall(BaseModel):
        """
        Model class for assistant prompt message tool call.
        """
        class ToolCallFunction(BaseModel):
            """
            Model class for assistant prompt message tool call function.
            """
            name: str  # 工具名称
            arguments: str  # 工具参数

        id: str  # 工具 ID，仅在 OpenAI tool call 生效，为工具调用的唯一 ID，同一个工具可以调用多次
        type: str  # 默认 function
        function: ToolCallFunction  # 工具调用信息

    role: PromptMessageRole = PromptMessageRole.ASSISTANT
    tool_calls: list[ToolCall] = []  # 模型回复的工具调用结果（仅当传入 tools，并且模型认为需要调用工具时返回）

class SystemPromptMessage(PromptMessage):
    """
    Model class for system prompt message.
    """
    role: PromptMessageRole = PromptMessageRole.SYSTEM

class ToolPromptMessage(PromptMessage):
    """
    Model class for tool prompt message.
    """
    role: PromptMessageRole = PromptMessageRole.TOOL
    tool_call_id: str  # 工具调用 ID，若不支持 OpenAI tool call，也可传入工具名称

class PromptMessageTool(BaseModel):
    """
    Model class for prompt message tool.
    """
    name: str  # 工具名称
    description: str  # 工具描述
    parameters: dict  # 工具参数 dict

class LLMResult(BaseModel):
    """
    Model class for llm result.
    """
    model: str  # 实际使用模型
    prompt_messages: list[PromptMessage]  # prompt 消息列表
    message: AssistantPromptMessage  # 回复消息
    usage: LLMUsage  # 使用的 tokens 及费用信息
    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义

class LLMResultChunkDelta(BaseModel):
    """
    Model class for llm result chunk delta.
    """
    index: int  # 序号
    message: AssistantPromptMessage  # 回复消息
    usage: Optional[LLMUsage] = None  # 使用的 tokens 及费用信息，仅最后一条返回
    finish_reason: Optional[str] = None  # 结束原因，仅最后一条返回

class LLMResultChunk(BaseModel):
    """
    Model class for llm result chunk.
    """
    model: str  # 实际使用模型
    prompt_messages: list[PromptMessage]  # prompt 消息列表
    system_fingerprint: Optional[str] = None  # 请求指纹，可参考 OpenAI 该参数定义
    delta: LLMResultChunkDelta  # 每个迭代存在变化的内容

class LLMUsage(ModelUsage):
    """
    Model class for llm usage.
    """
    prompt_tokens: int  # prompt 使用 tokens
    prompt_unit_price: Decimal  # prompt 单价
    prompt_price_unit: Decimal  # prompt 价格单位，即单价基于多少 tokens 
    prompt_price: Decimal  # prompt 费用
    completion_tokens: int  # 回复使用 tokens
    completion_unit_price: Decimal  # 回复单价
    completion_price_unit: Decimal  # 回复价格单位，即单价基于多少 tokens 
    completion_price: Decimal  # 回复费用
    total_tokens: int  # 总使用 token 数
    total_price: Decimal  # 总费用
    currency: str  # 货币单位
    latency: float  # 请求耗时(s)

class TextEmbeddingResult(BaseModel):
    """
    Model class for text embedding result.
    """
    model: str  # 实际使用模型
    embeddings: list[list[float]]  # embedding 向量列表，对应传入的 texts 列表
    usage: EmbeddingUsage  # 使用信息

class EmbeddingUsage(ModelUsage):
    """
    Model class for embedding usage.
    """
    tokens: int  # 使用 token 数
    total_tokens: int  # 总使用 token 数
    unit_price: Decimal  # 单价
    price_unit: Decimal  # 价格单位，即单价基于多少 tokens
    total_price: Decimal  # 总费用
    currency: str  # 货币单位
    latency: float  # 请求耗时(s)

class RerankResult(BaseModel):
    """
    Model class for rerank result.
    """
    model: str  # 实际使用模型
    docs: list[RerankDocument]  # 重排后的分段列表        

class RerankDocument(BaseModel):
    """
    Model class for rerank document.
    """
    index: int  # 原序号
    text: str  # 分段文本内容
    score: float  # 分数