File size: 3,009 Bytes
cc886b8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 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 |
import time
from enum import Enum, unique
from typing import Any, Dict, List, Optional, Union
from pydantic import BaseModel, Field
from typing_extensions import Literal
@unique
class Role(str, Enum):
USER = "user"
ASSISTANT = "assistant"
SYSTEM = "system"
FUNCTION = "function"
TOOL = "tool"
@unique
class Finish(str, Enum):
STOP = "stop"
LENGTH = "length"
TOOL = "tool_calls"
class ModelCard(BaseModel):
id: str
object: Literal["model"] = "model"
created: int = Field(default_factory=lambda: int(time.time()))
owned_by: Literal["owner"] = "owner"
class ModelList(BaseModel):
object: Literal["list"] = "list"
data: List[ModelCard] = []
class Function(BaseModel):
name: str
arguments: str
class FunctionDefinition(BaseModel):
name: str
description: str
parameters: Dict[str, Any]
class FunctionAvailable(BaseModel):
type: Literal["function", "code_interpreter"] = "function"
function: Optional[FunctionDefinition] = None
class FunctionCall(BaseModel):
id: str
type: Literal["function"] = "function"
function: Function
class ChatMessage(BaseModel):
role: Role
content: Optional[str] = None
tool_calls: Optional[List[FunctionCall]] = None
class ChatCompletionMessage(BaseModel):
role: Optional[Role] = None
content: Optional[str] = None
tool_calls: Optional[List[FunctionCall]] = None
class ChatCompletionRequest(BaseModel):
model: str
messages: List[ChatMessage]
tools: Optional[List[FunctionAvailable]] = None
do_sample: bool = True
temperature: Optional[float] = None
top_p: Optional[float] = None
n: int = 1
max_tokens: Optional[int] = None
stop: Optional[Union[str, List[str]]] = None
stream: bool = False
class ChatCompletionResponseChoice(BaseModel):
index: int
message: ChatCompletionMessage
finish_reason: Finish
class ChatCompletionStreamResponseChoice(BaseModel):
index: int
delta: ChatCompletionMessage
finish_reason: Optional[Finish] = None
class ChatCompletionResponseUsage(BaseModel):
prompt_tokens: int
completion_tokens: int
total_tokens: int
class ChatCompletionResponse(BaseModel):
id: str
object: Literal["chat.completion"] = "chat.completion"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[ChatCompletionResponseChoice]
usage: ChatCompletionResponseUsage
class ChatCompletionStreamResponse(BaseModel):
id: str
object: Literal["chat.completion.chunk"] = "chat.completion.chunk"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[ChatCompletionStreamResponseChoice]
class ScoreEvaluationRequest(BaseModel):
model: str
messages: List[str]
max_length: Optional[int] = None
class ScoreEvaluationResponse(BaseModel):
id: str
object: Literal["score.evaluation"] = "score.evaluation"
model: str
scores: List[float]
|