sglang/python/sglang/srt/managers/openai_protocol.py

import time
from typing import Dict, List, Optional, Union

from pydantic import BaseModel, Field


class LogProbs(BaseModel):
    text_offset: List[int] = Field(default_factory=list)
    token_logprobs: List[Optional[float]] = Field(default_factory=list)
    tokens: List[str] = Field(default_factory=list)
    top_logprobs: List[Optional[Dict[str, float]]] = Field(default_factory=list)


class UsageInfo(BaseModel):
    prompt_tokens: int = 0
    total_tokens: int = 0
    completion_tokens: Optional[int] = 0


class CompletionRequest(BaseModel):
    model: str
    prompt: Union[str, List[str]]
    suffix: Optional[str] = None
    max_tokens: Optional[int] = 16
    temperature: Optional[float] = 0.7
    top_p: Optional[float] = 1.0
    n: Optional[int] = 1
    stream: Optional[bool] = False
    logprobs: Optional[int] = None
    echo: Optional[bool] = False
    stop: Optional[Union[str, List[str]]] = Field(default_factory=list)
    presence_penalty: Optional[float] = 0.0
    frequency_penalty: Optional[float] = 0.0
    best_of: Optional[int] = None
    logit_bias: Optional[Dict[str, float]] = None
    user: Optional[str] = None


class CompletionResponseChoice(BaseModel):
    index: int
    text: str
    logprobs: Optional[LogProbs] = None
    finish_reason: Optional[str] = None


class CompletionResponse(BaseModel):
    id: str
    object: str = "text_completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[CompletionResponseChoice]
    usage: UsageInfo


class CompletionResponseStreamChoice(BaseModel):
    index: int
    text: str
    logprobs: Optional[LogProbs] = None
    finish_reason: Optional[str] = None


class CompletionStreamResponse(BaseModel):
    id: str
    object: str = "text_completion"
    created: int = Field(default_factory=lambda: int(time.time()))
    model: str
    choices: List[CompletionResponseStreamChoice]