baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Formatting

Browse source
This commit is contained in:
Andrei Betlen 2023-04-12 22:40:12 -04:00
parent 0daf16defc
commit 4f5f99ef2a
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
llama_cpp/server/__main__.py
View file

@ -109,7 +109,9 @@ CreateCompletionResponse = create_model_from_typeddict(llama_cpp.Completion)
"/v1/completions", "/v1/completions",
response_model=CreateCompletionResponse, response_model=CreateCompletionResponse,
) )
def create_completion(request: CreateCompletionRequest, llama: llama_cpp.Llama=Depends(get_llama)): def create_completion(
request: CreateCompletionRequest, llama: llama_cpp.Llama = Depends(get_llama)
):
if isinstance(request.prompt, list): if isinstance(request.prompt, list):
request.prompt = "".join(request.prompt) request.prompt = "".join(request.prompt)
@ -153,7 +155,9 @@ CreateEmbeddingResponse = create_model_from_typeddict(llama_cpp.Embedding)
"/v1/embeddings", "/v1/embeddings",
response_model=CreateEmbeddingResponse, response_model=CreateEmbeddingResponse,
) )
def create_embedding(request: CreateEmbeddingRequest, llama: llama_cpp.Llama=Depends(get_llama)): def create_embedding(
request: CreateEmbeddingRequest, llama: llama_cpp.Llama = Depends(get_llama)
):
return llama.create_embedding(**request.dict(exclude={"model", "user"})) return llama.create_embedding(**request.dict(exclude={"model", "user"}))
@ -207,7 +211,7 @@ CreateChatCompletionResponse = create_model_from_typeddict(llama_cpp.ChatComplet
) )
def create_chat_completion( def create_chat_completion(
request: CreateChatCompletionRequest, request: CreateChatCompletionRequest,
llama: llama_cpp.Llama=Depends(get_llama), llama: llama_cpp.Llama = Depends(get_llama),
) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]: ) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:
completion_or_chunks = llama.create_chat_completion( completion_or_chunks = llama.create_chat_completion(
**request.dict( **request.dict(