chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Move openai api server into a separate file (#429)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-05-12 06:41:32 -07:00
committed by GitHub
parent abc548c707
commit 3fc97f6709
5 changed files with 423 additions and 380 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
python/sglang/srt/openai_protocol.py
View File

@@ -20,21 +20,24 @@ class UsageInfo(BaseModel):
class CompletionRequest(BaseModel):
# Ordered by official OpenAI API documentation
# https://platform.openai.com/docs/api-reference/completions/create
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
prompt: Union[List[int], List[List[int]], str, List[str]]
best_of: Optional[int] = None
echo: Optional[bool] = False
frequency_penalty: Optional[float] = 0.0
logit_bias: Optional[Dict[str, float]] = None
logprobs: Optional[int] = None
max_tokens: Optional[int] = 16
n: int = 1
presence_penalty: Optional[float] = 0.0
seed: Optional[int] = None
stop: Optional[Union[str, List[str]]] = Field(default_factory=list)
stream: Optional[bool] = False
suffix: Optional[str] = None
temperature: Optional[float] = 1.0
top_p: Optional[float] = 1.0
user: Optional[str] = None
# Extra parameters for SRT backend only and will be ignored by OpenAI models.
@@ -108,20 +111,30 @@ ChatCompletionMessageParam = Union[
]
class ResponseFormat(BaseModel):
# type must be "json_object" or "text"
type: Literal["text", "json_object"]
class ChatCompletionRequest(BaseModel):
# Ordered by official OpenAI API documentation
# https://platform.openai.com/docs/api-reference/chat/create
messages: List[ChatCompletionMessageParam]
model: str
messages: Union[str, List[ChatCompletionMessageParam]]
temperature: Optional[float] = 0.7
top_p: Optional[float] = 1.0
n: Optional[int] = 1
max_tokens: Optional[int] = 16
stop: Optional[Union[str, List[str]]] = Field(default_factory=list)
stream: Optional[bool] = False
presence_penalty: Optional[float] = 0.0
frequency_penalty: Optional[float] = 0.0
logit_bias: Optional[Dict[str, float]] = None
logprobs: Optional[bool] = False
top_logprobs: Optional[int] = None
max_tokens: Optional[int] = None
n: Optional[int] = 1
presence_penalty: Optional[float] = 0.0
response_format: Optional[ResponseFormat] = None
seed: Optional[int] = None
stop: Optional[Union[str, List[str]]] = Field(default_factory=list)
stream: Optional[bool] = False
temperature: Optional[float] = 0.7
top_p: Optional[float] = 1.0
user: Optional[str] = None
best_of: Optional[int] = None
# Extra parameters for SRT backend only and will be ignored by OpenAI models.
regex: Optional[str] = None
@@ -135,6 +148,7 @@ class ChatMessage(BaseModel):
class ChatCompletionResponseChoice(BaseModel):
index: int
message: ChatMessage
logprobs: Optional[LogProbs] = None
finish_reason: Optional[str] = None
@@ -155,6 +169,7 @@ class DeltaMessage(BaseModel):
class ChatCompletionResponseStreamChoice(BaseModel):
index: int
delta: DeltaMessage
logprobs: Optional[LogProbs] = None
finish_reason: Optional[str] = None
@@ -163,4 +178,4 @@ class ChatCompletionStreamResponse(BaseModel):
object: str = "chat.completion.chunk"
created: int = Field(default_factory=lambda: int(time.time()))
model: str
choices: List[ChatCompletionResponseStreamChoice]
choices: List[ChatCompletionResponseStreamChoice]