mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2025-09-10 14:51:06 +00:00
fix: workaround return dummy usage
This commit is contained in:
parent
db61375f1a
commit
6d45871de8
1 changed files with 2 additions and 1 deletions
|
@ -5,7 +5,7 @@ from fastapi import APIRouter
|
||||||
from fastapi.requests import Request
|
from fastapi.requests import Request
|
||||||
from ktransformers.server.utils.create_interface import get_interface
|
from ktransformers.server.utils.create_interface import get_interface
|
||||||
from ktransformers.server.schemas.assistants.streaming import chat_stream_response
|
from ktransformers.server.schemas.assistants.streaming import chat_stream_response
|
||||||
from ktransformers.server.schemas.endpoints.chat import ChatCompletionCreate,ChatCompletionChunk,ChatCompletionObject
|
from ktransformers.server.schemas.endpoints.chat import ChatCompletionCreate,ChatCompletionChunk,ChatCompletionObject, Usage
|
||||||
from ktransformers.server.backend.base import BackendInterfaceBase
|
from ktransformers.server.backend.base import BackendInterfaceBase
|
||||||
from ktransformers.server.config.config import Config
|
from ktransformers.server.config.config import Config
|
||||||
|
|
||||||
|
@ -34,6 +34,7 @@ async def chat_completion(request:Request,create:ChatCompletionCreate):
|
||||||
return chat_stream_response(request,inner())
|
return chat_stream_response(request,inner())
|
||||||
else:
|
else:
|
||||||
comp = ChatCompletionObject(id=id,object='chat.completion.chunk',created=int(time()))
|
comp = ChatCompletionObject(id=id,object='chat.completion.chunk',created=int(time()))
|
||||||
|
comp.usage = Usage(completion_tokens=1, prompt_tokens=1, total_tokens=2)
|
||||||
async for token in interface.inference(input_message,id):
|
async for token in interface.inference(input_message,id):
|
||||||
comp.append_token(token)
|
comp.append_token(token)
|
||||||
return comp
|
return comp
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue