@@ -109,7 +109,9 @@ class Config:
109
109
"/v1/completions" ,
110
110
response_model = CreateCompletionResponse ,
111
111
)
112
- def create_completion (request : CreateCompletionRequest , llama : llama_cpp .Llama = Depends (get_llama )):
112
+ def create_completion (
113
+ request : CreateCompletionRequest , llama : llama_cpp .Llama = Depends (get_llama )
114
+ ):
113
115
if isinstance (request .prompt , list ):
114
116
request .prompt = "" .join (request .prompt )
115
117
@@ -153,7 +155,9 @@ class Config:
153
155
"/v1/embeddings" ,
154
156
response_model = CreateEmbeddingResponse ,
155
157
)
156
- def create_embedding (request : CreateEmbeddingRequest , llama : llama_cpp .Llama = Depends (get_llama )):
158
+ def create_embedding (
159
+ request : CreateEmbeddingRequest , llama : llama_cpp .Llama = Depends (get_llama )
160
+ ):
157
161
return llama .create_embedding (** request .dict (exclude = {"model" , "user" }))
158
162
159
163
@@ -207,7 +211,7 @@ class Config:
207
211
)
208
212
def create_chat_completion (
209
213
request : CreateChatCompletionRequest ,
210
- llama : llama_cpp .Llama = Depends (get_llama ),
214
+ llama : llama_cpp .Llama = Depends (get_llama ),
211
215
) -> Union [llama_cpp .ChatCompletion , EventSourceResponse ]:
212
216
completion_or_chunks = llama .create_chat_completion (
213
217
** request .dict (
0 commit comments