openai_protocol
OpenAI API data model
This module defines Pydantic objects that implement an OpenAI compatible data model.
See: https://platform.openai.com/docs/api-reference/chat
Classes
AssistantMessage
Bases: BaseMessage
OpenAI compatible assistant message object
Attributes
role
class-attribute
instance-attribute
role: str = Field(
default=assistant.value,
frozen=True,
description="The role of the message.",
)
tool_calls
class-attribute
instance-attribute
tool_calls: Optional[List[ToolCall]] = Field(
default_factory=list,
description="The tool calls generated by the model.",
)
Functions
BaseChoice
Bases: BaseDataModel
Base OpenAI choice object, note that streaming and non-streaming choices have slight differences
Attributes
finish_reason
class-attribute
instance-attribute
finish_reason: Optional[
Literal[
"stop", "length", "content_filter", "tool_calls"
]
] = Field(
default=None,
description="The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool.",
)
index
class-attribute
instance-attribute
logprobs
class-attribute
instance-attribute
logprobs: Optional[ChatCompletionLogProbs] = Field(
default=None,
description="Log probability information for the choice.",
)
BaseMessage
Bases: BaseDataModel
ChatCompletionBaseResponse
Bases: BaseDataModel
Attributes
created
class-attribute
instance-attribute
created: int = Field(
default_factory=lambda: int(timestamp()),
description="The Unix timestamp (in seconds) of when the chat completion was created.",
)
field_id
class-attribute
instance-attribute
field_id: str = Field(
default_factory=lambda: gen_uuid(prefix="chatcmpl-"),
alias="id",
description="A unique identifier for the chat completion.",
)
model
class-attribute
instance-attribute
system_fingerprint
class-attribute
instance-attribute
system_fingerprint: Optional[str] = Field(
default=None,
description="This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism. Ex: fp_44709d6fcb",
)
ChatCompletionChunk
Bases: ChatCompletionBaseResponse
OpenAI compatible chat completion chunk object
Attributes
choices
class-attribute
instance-attribute
choices: List[StreamingChoice] = Field(
default_factory=list,
description="A list of chat completion choices. Can be more than one if n is greater than 1.",
)
ChatCompletionLogProbs
Bases: BaseDataModel
OpenAI compatible chat completion logprobs object
Attributes
content
class-attribute
instance-attribute
content: Optional[List[ChatCompletionLogProbsContent]] = (
Field(
default=None,
description="A list of message content tokens with log probability information.",
)
)
ChatCompletionLogProbsContent
Bases: ChatCompletionLogprobToken
OpenAI compatible chat completion logprobs content object
Attributes
top_logprobs
class-attribute
instance-attribute
top_logprobs: List[ChatCompletionLogprobToken] = Field(
...,
description="List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned",
)
ChatCompletionLogprobToken
Bases: BaseDataModel
OpenAI compatible chat completion logprob token object
Attributes
field_bytes
class-attribute
instance-attribute
field_bytes: Optional[List[int]] = Field(
default=None,
alias="bytes",
description="A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.",
)
logprob
class-attribute
instance-attribute
Functions
token_to_field_bytes
staticmethod
Converts a string to a list of integers representing the UTF-8 byte values.
Intended use case is to convert tokens returned in the OpenAI API logits response
to a list of integer suitable to populate the field_bytes
field
Parameters:
-
token_string
(str
) –The input string to be converted.
Returns:
-
list
(List[int]
) –A list of integers representing the UTF-8 byte values of the input string.
ChatCompletionMessage
Bases: BaseDataModel
OpenAI compatible chat completion message object
Attributes
content
class-attribute
instance-attribute
role
class-attribute
instance-attribute
role: Optional[Literal["user", "assistant", "tool"]] = (
Field(
default=None,
description="The role of the author of this message.",
)
)
tool_calls
class-attribute
instance-attribute
tool_calls: List[ToolCall] = Field(
default_factory=list,
description="The tool calls generated by the model, such as function calls.",
)
ChatCompletionRequest
Bases: BaseModel
OpenAI compatible chat completion request object
Attributes
frequency_penalty
class-attribute
instance-attribute
frequency_penalty: float = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
)
logit_bias
class-attribute
instance-attribute
logit_bias: Optional[Dict[str, float]] = Field(
default=None,
description="Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.",
)
logprobs
class-attribute
instance-attribute
logprobs: bool = Field(
default=False,
description="Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message",
)
max_tokens
class-attribute
instance-attribute
max_tokens: Optional[int] = Field(
default=None,
description="The maximum number of tokens that can be generated in the chat completion.",
)
messages
class-attribute
instance-attribute
messages: List[
Union[
SystemMessage,
UserMessage,
AssistantMessage,
ToolMessage,
]
] = Field(
...,
description="A list of messages comprising the conversation so far.",
)
model
class-attribute
instance-attribute
n
class-attribute
instance-attribute
n: int = Field(
default=1,
description="How many chat completion choices to generate for each input message.",
)
presence_penalty
class-attribute
instance-attribute
presence_penalty: float = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
)
response_format
class-attribute
instance-attribute
response_format: Optional[Dict[str, str]] = Field(
default=None,
description="An object specifying the format that the model must output",
)
seed
class-attribute
instance-attribute
seed: int = Field(
default=-1,
description="This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.",
)
stop
class-attribute
instance-attribute
stop: Union[str, List[str]] = Field(
default_factory=list,
description="Up to 4 sequences where the API will stop generating further tokens.",
)
stream
class-attribute
instance-attribute
temperature
class-attribute
instance-attribute
temperature: float = Field(
default=1.0,
ge=0.0,
le=2.0,
description="What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.",
)
tool_choice
class-attribute
instance-attribute
tool_choice: Union[str, ToolChoice] = Field(
default="none",
description="Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function.",
)
tools
class-attribute
instance-attribute
tools: List[Tool] = Field(
default_factory=list,
description="A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.",
)
top_logprobs
class-attribute
instance-attribute
top_logprobs: Optional[int] = Field(
default=None,
ge=0,
le=5,
description="An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.",
)
top_p
class-attribute
instance-attribute
top_p: float = Field(
default=1.0,
description="An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.",
)
ChatCompletionResponse
Bases: ChatCompletionBaseResponse
OpenAI compatible chat completion response object
Attributes
choices
class-attribute
instance-attribute
choices: List[Choice] = Field(
...,
description="A list of chat completion choices. Can be more than one if n is greater than 1.",
)
field_object
class-attribute
instance-attribute
field_object: Optional[Literal["chat.completion"]] = Field(
default="chat.completion",
alias="object",
description="The object type, which is always chat.completion",
)
usage
class-attribute
instance-attribute
usage: Optional[ChatCompletionUsage] = Field(
default=None,
description="Usage statistics for the chat completion.",
)
ChatCompletionUsage
Bases: BaseDataModel
OpenAI compatible chat completion usage object
Attributes
completion_tokens
class-attribute
instance-attribute
prompt_tokens
class-attribute
instance-attribute
Choice
Bases: BaseChoice
OpenAI compatible non-streaming choice object
Attributes
message
class-attribute
instance-attribute
message: Optional[ChatCompletionMessage] = Field(
default=None,
description="A chat completion message generated by the model.",
)
Model
Bases: BaseDataModel
OpenAI compatible model object
Attributes
created
class-attribute
instance-attribute
created: int = Field(
default_factory=lambda: int(timestamp()),
description="The Unix timestamp (in seconds) when the model was created.",
)
field_id
class-attribute
instance-attribute
field_id: str = Field(
...,
serialization_alias="id",
description="The model identifier, which can be referenced in the API endpoints.",
)
ModelsListResponse
Bases: BaseDataModel
OpenAI compatible model list response object
Attributes
data
class-attribute
instance-attribute
data: List[Model] = Field(
..., description="A list of models."
)
OpenAIRole
StreamingChoice
Bases: BaseChoice
OpenAI compatible streaming choice object
Attributes
delta
class-attribute
instance-attribute
delta: Optional[ChatCompletionMessage] = Field(
default=None,
description="A chat completion delta generated by streamed model responses.",
)
StreamingErrorResponse
Bases: BaseDataModel
OpenAI compatible streaming error response object
Attributes
error
class-attribute
instance-attribute
error: StreamingErrorResponseRecord = Field(
..., description=__doc__
)
StreamingErrorResponseRecord
Bases: BaseDataModel
OpenAI compatible streaming error response record object
Attributes
code
class-attribute
instance-attribute
field_type
class-attribute
instance-attribute
message
class-attribute
instance-attribute
SystemMessage
Bases: BaseMessage
OpenAI compatible system message object
Attributes
role
class-attribute
instance-attribute
role: str = Field(
default=system.value,
frozen=True,
description="The role of the message.",
)
Functions
Tool
Bases: BaseDataModel
OpenAI compatible tool object
Attributes
field_function
class-attribute
instance-attribute
field_function: ToolFunction = Field(
...,
alias="function",
description="The function that the model called.",
)
ToolCall
Bases: BaseDataModel
The tool call generated by the model
Attributes
field_function
class-attribute
instance-attribute
field_function: ToolCallFunction = Field(
...,
alias="function",
description="The function that the model called.",
)
field_id
class-attribute
instance-attribute
ToolCallFunction
Bases: BaseDataModel
The function that the model called
ToolChoice
Bases: BaseDataModel
OpenAI compatible tool choice object
Attributes
field_function
class-attribute
instance-attribute
field_function: ToolChoiceFunction = Field(
...,
alias="function",
description="The function that the model called.",
)
ToolChoiceFunction
Bases: BaseDataModel
OpenAI compatible tool choice function object
ToolFunction
Bases: BaseDataModel
OpenAI compatible tool function object
Attributes
description
class-attribute
instance-attribute
description: Optional[str] = Field(
default=None,
description="A description of what the function does, used by the model to choose when and how to call the function.",
)
ToolMessage
Bases: BaseMessage
OpenAI compatible tool message object
Attributes
content
class-attribute
instance-attribute
role
class-attribute
instance-attribute
role: str = Field(
default=tool.value,
frozen=True,
description="The role of the messages author, in this case tool",
)
tool_call_id
class-attribute
instance-attribute
Functions
UserMessage
Bases: BaseMessage
OpenAI compatible user message object
Attributes
role
class-attribute
instance-attribute
role: str = Field(
default=user.value,
frozen=True,
description="The role of the message.",
)