Support v1/chat/completions (#50)

python/sglang/srt/managers/openai_protocol.py

@@ -65,3 +65,59 @@ class CompletionStreamResponse(BaseModel):
     created: int = Field(default_factory=lambda: int(time.time()))
     model: str
     choices: List[CompletionResponseStreamChoice]
+    usage: UsageInfo
+
+
+class ChatCompletionRequest(BaseModel):
+    model: str
+    messages: Union[str, List[Dict[str, str]]]
+    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
+    user: Optional[str] = None
+    best_of: Optional[int] = None
+
+
+class ChatMessage(BaseModel):
+    role: Optional[str] = None
+    content: Optional[str] = None
+
+
+class ChatCompletionResponseChoice(BaseModel):
+    index: int
+    message: ChatMessage
+    finish_reason: Optional[str] = None
+
+
+class ChatCompletionResponse(BaseModel):
+    id: str
+    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[str] = None
+
+
+class ChatCompletionStreamResponse(BaseModel):
+    id: str
+    object: str = "chat.completion.chunk"
+    created: int = Field(default_factory=lambda: int(time.time()))
+    model: str
+    choices: List[ChatCompletionResponseStreamChoice]