Skip to content

Grammar support for Web Server #855

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 1, 2023
Merged

Grammar support for Web Server #855

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions llama_cpp/server/app.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -518,6 +518,10 @@ async def get_event_publisher(
default=0.1, ge=0.001, le=1.0, description="Mirostat learning rate"
)

grammar = Field(
default=None,
description="A CBNF grammar (as string) to be used for formatting the model's output."
)

class CreateCompletionRequest(BaseModel):
prompt: Union[str, List[str]] = Field(
Expand All @@ -533,6 +537,7 @@ class CreateCompletionRequest(BaseModel):
mirostat_mode: int = mirostat_mode_field
mirostat_tau: float = mirostat_tau_field
mirostat_eta: float = mirostat_eta_field
grammar: Optional[str] = None
echo: bool = Field(
default=False,
description="Whether to echo the prompt in the generated text. Useful for chatbots.",
Expand Down Expand Up @@ -634,6 +639,9 @@ async def create_completion(
]
)

if body.grammar is not None:
kwargs["grammar"] = llama_cpp.LlamaGrammar.from_string(body.grammar)

iterator_or_completion: Union[
llama_cpp.Completion, Iterator[llama_cpp.CompletionChunk]
] = await run_in_threadpool(llama, **kwargs)
Expand Down Expand Up @@ -714,6 +722,7 @@ class CreateChatCompletionRequest(BaseModel):
mirostat_mode: int = mirostat_mode_field
mirostat_tau: float = mirostat_tau_field
mirostat_eta: float = mirostat_eta_field
grammar: Optional[str] = None
stop: Optional[List[str]] = stop_field
stream: bool = stream_field
presence_penalty: Optional[float] = presence_penalty_field
Expand Down Expand Up @@ -772,6 +781,9 @@ async def create_chat_completion(
]
)

if body.grammar is not None:
kwargs["grammar"] = llama_cpp.LlamaGrammar.from_string(body.grammar)

iterator_or_completion: Union[
llama_cpp.ChatCompletion, Iterator[llama_cpp.ChatCompletionChunk]
] = await run_in_threadpool(llama.create_chat_completion, **kwargs)
Expand Down