visual-arena / fastchat /protocol /api_protocol.py
tianleliphoebe's picture
Upload folder using huggingface_hub
ec0c335 verified
from typing import Literal, Optional, List, Dict, Any, Union
import time
import shortuuid
from pydantic import BaseModel, Field
class ErrorResponse(BaseModel):
object: str = "error"
message: str
code: int
class ModelPermission(BaseModel):
id: str = Field(default_factory=lambda: f"modelperm-{shortuuid.random()}")
object: str = "model_permission"
created: int = Field(default_factory=lambda: int(time.time()))
allow_create_engine: bool = False
allow_sampling: bool = True
allow_logprobs: bool = True
allow_search_indices: bool = True
allow_view: bool = True
allow_fine_tuning: bool = False
organization: str = "*"
group: Optional[str] = None
is_blocking: str = False
class ModelCard(BaseModel):
id: str
object: str = "model"
created: int = Field(default_factory=lambda: int(time.time()))
owned_by: str = "fastchat"
root: Optional[str] = None
parent: Optional[str] = None
permission: List[ModelPermission] = []
class ModelList(BaseModel):
object: str = "list"
data: List[ModelCard] = []
class UsageInfo(BaseModel):
prompt_tokens: int = 0
total_tokens: int = 0
completion_tokens: Optional[int] = 0
class APIChatCompletionRequest(BaseModel):
model: str
messages: Union[str, List[Dict[str, str]]]
temperature: Optional[float] = 0.7
top_p: Optional[float] = 1.0
top_k: Optional[int] = -1
n: Optional[int] = 1
max_tokens: Optional[int] = None
stop: Optional[Union[str, List[str]]] = None
stream: Optional[bool] = False
user: Optional[str] = None
repetition_penalty: Optional[float] = 1.0
frequency_penalty: Optional[float] = 0.0
presence_penalty: Optional[float] = 0.0
class ChatMessage(BaseModel):
role: str
content: str
class ChatCompletionResponseChoice(BaseModel):
index: int
message: ChatMessage
finish_reason: Optional[Literal["stop", "length"]] = None
class ChatCompletionResponse(BaseModel):
id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
object: str = "chat.completion"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[ChatCompletionResponseChoice]
usage: UsageInfo
class DeltaMessage(BaseModel):
role: Optional[str] = None
content: Optional[str] = None
class ChatCompletionResponseStreamChoice(BaseModel):
index: int
delta: DeltaMessage
finish_reason: Optional[Literal["stop", "length"]] = None
class ChatCompletionStreamResponse(BaseModel):
id: str = Field(default_factory=lambda: f"chatcmpl-{shortuuid.random()}")
object: str = "chat.completion.chunk"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[ChatCompletionResponseStreamChoice]
class APITokenCheckRequestItem(BaseModel):
model: str
prompt: str
max_tokens: int
class APITokenCheckRequest(BaseModel):
prompts: List[APITokenCheckRequestItem]
class APITokenCheckResponseItem(BaseModel):
fits: bool
tokenCount: int
contextLength: int
class APITokenCheckResponse(BaseModel):
prompts: List[APITokenCheckResponseItem]
class CompletionRequest(BaseModel):
model: str
prompt: Union[str, List[Any]]
suffix: Optional[str] = None
temperature: Optional[float] = 0.7
n: Optional[int] = 1
max_tokens: Optional[int] = 16
stop: Optional[Union[str, List[str]]] = None
stream: Optional[bool] = False
top_p: Optional[float] = 1.0
top_k: Optional[int] = -1
logprobs: Optional[int] = None
echo: Optional[bool] = False
presence_penalty: Optional[float] = 0.0
frequency_penalty: Optional[float] = 0.0
user: Optional[str] = None
class CompletionResponseChoice(BaseModel):
index: int
text: str
logprobs: Optional[int] = None
finish_reason: Optional[Literal["stop", "length"]] = None
class CompletionResponse(BaseModel):
id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
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[float] = None
finish_reason: Optional[Literal["stop", "length"]] = None
class CompletionStreamResponse(BaseModel):
id: str = Field(default_factory=lambda: f"cmpl-{shortuuid.random()}")
object: str = "text_completion"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[CompletionResponseStreamChoice]