[Doc] Add docs about OpenAI compatible server (#3288)

This commit is contained in:
Simon Mo
2024-03-18 22:05:34 -07:00
committed by GitHub
parent 6a9c583e73
commit ef65dcfa6f
10 changed files with 383 additions and 161 deletions
+119 -47
View File
@@ -61,41 +61,80 @@ class ResponseFormat(BaseModel):
class ChatCompletionRequest(BaseModel):
model: str
# Ordered by official OpenAI API documentation
# https://platform.openai.com/docs/api-reference/chat/create
messages: List[Dict[str, str]]
temperature: Optional[float] = 0.7
top_p: Optional[float] = 1.0
n: Optional[int] = 1
model: str
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
logprobs: Optional[bool] = False
top_logprobs: Optional[int] = None
presence_penalty: Optional[float] = 0.0
frequency_penalty: Optional[float] = 0.0
logit_bias: Optional[Dict[str, float]] = None
temperature: Optional[float] = 0.7
top_p: Optional[float] = 1.0
user: Optional[str] = None
# Additional parameters supported by vLLM
# doc: begin-chat-completion-sampling-params
best_of: Optional[int] = None
top_k: Optional[int] = -1
ignore_eos: Optional[bool] = False
use_beam_search: Optional[bool] = False
top_k: Optional[int] = -1
min_p: Optional[float] = 0.0
repetition_penalty: Optional[float] = 1.0
length_penalty: Optional[float] = 1.0
early_stopping: Optional[bool] = False
ignore_eos: Optional[bool] = False
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
skip_special_tokens: Optional[bool] = True
spaces_between_special_tokens: Optional[bool] = True
add_generation_prompt: Optional[bool] = True
echo: Optional[bool] = False
repetition_penalty: Optional[float] = 1.0
min_p: Optional[float] = 0.0
include_stop_str_in_output: Optional[bool] = False
length_penalty: Optional[float] = 1.0
guided_json: Optional[Union[str, dict, BaseModel]] = None
guided_regex: Optional[str] = None
guided_choice: Optional[List[str]] = None
guided_grammar: Optional[str] = None
response_format: Optional[ResponseFormat] = None
# doc: end-chat-completion-sampling-params
# doc: begin-chat-completion-extra-params
echo: Optional[bool] = Field(
default=False,
description=(
"If true, the new message will be prepended with the last message "
"if they belong to the same role."),
)
add_generation_prompt: Optional[bool] = Field(
default=True,
description=
("If true, the generation prompt will be added to the chat template. "
"This is a parameter used by chat template in tokenizer config of the "
"model."),
)
include_stop_str_in_output: Optional[bool] = Field(
default=False,
description=(
"Whether to include the stop string in the output. "
"This is only applied when the stop or stop_token_ids is set."),
)
guided_json: Optional[Union[str, dict, BaseModel]] = Field(
default=None,
description=("If specified, the output will follow the JSON schema."),
)
guided_regex: Optional[str] = Field(
default=None,
description=(
"If specified, the output will follow the regex pattern."),
)
guided_choice: Optional[List[str]] = Field(
default=None,
description=(
"If specified, the output will be exactly one of the choices."),
)
guided_grammar: Optional[str] = Field(
default=None,
description=(
"If specified, the output will follow the context free grammar."),
)
# doc: end-chat-completion-extra-params
def to_sampling_params(self) -> SamplingParams:
if self.logprobs and not self.top_logprobs:
@@ -157,41 +196,74 @@ class ChatCompletionRequest(BaseModel):
class CompletionRequest(BaseModel):
# Ordered by official OpenAI API documentation
# https://platform.openai.com/docs/api-reference/completions/create
model: str
# a string, array of strings, array of tokens, or array of token arrays
prompt: Union[List[int], List[List[int]], str, List[str]]
suffix: Optional[str] = None
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: Optional[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
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)
seed: Optional[int] = None
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
# Additional parameters supported by vLLM
top_k: Optional[int] = -1
ignore_eos: Optional[bool] = False
# doc: begin-completion-sampling-params
use_beam_search: Optional[bool] = False
top_k: Optional[int] = -1
min_p: Optional[float] = 0.0
repetition_penalty: Optional[float] = 1.0
length_penalty: Optional[float] = 1.0
early_stopping: Optional[bool] = False
stop_token_ids: Optional[List[int]] = Field(default_factory=list)
ignore_eos: Optional[bool] = False
skip_special_tokens: Optional[bool] = True
spaces_between_special_tokens: Optional[bool] = True
repetition_penalty: Optional[float] = 1.0
min_p: Optional[float] = 0.0
include_stop_str_in_output: Optional[bool] = False
length_penalty: Optional[float] = 1.0
guided_json: Optional[Union[str, dict, BaseModel]] = None
guided_regex: Optional[str] = None
guided_choice: Optional[List[str]] = None
guided_grammar: Optional[str] = None
response_format: Optional[ResponseFormat] = None
# doc: end-completion-sampling-params
# doc: begin-completion-extra-params
include_stop_str_in_output: Optional[bool] = Field(
default=False,
description=(
"Whether to include the stop string in the output. "
"This is only applied when the stop or stop_token_ids is set."),
)
response_format: Optional[ResponseFormat] = Field(
default=None,
description=
("Similar to chat completion, this parameter specifies the format of "
"output. Only {'type': 'json_object'} or {'type': 'text' } is "
"supported."),
)
guided_json: Optional[Union[str, dict, BaseModel]] = Field(
default=None,
description=("If specified, the output will follow the JSON schema."),
)
guided_regex: Optional[str] = Field(
default=None,
description=(
"If specified, the output will follow the regex pattern."),
)
guided_choice: Optional[List[str]] = Field(
default=None,
description=(
"If specified, the output will be exactly one of the choices."),
)
guided_grammar: Optional[str] = Field(
default=None,
description=(
"If specified, the output will follow the context free grammar."),
)
# doc: end-completion-extra-params
def to_sampling_params(self):
echo_without_generation = self.echo and self.max_tokens == 0