biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

migrate pydantic from v1 to v2 (#2531)

Browse Source
This commit is contained in:
Jannis Schönleber
2024-01-22 01:05:56 +01:00
committed by GitHub
parent d75c40734a
commit 71d63ed72e
7 changed files with 26 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/entrypoints/openai/api_server.py
View File

@@ -106,7 +106,7 @@ app.add_route("/metrics", metrics) # Exposes HTTP metrics
@app.exception_handler(RequestValidationError)
async def validation_exception_handler(_, exc):
err = openai_serving_chat.create_error_response(message=str(exc))
return JSONResponse(err.dict(), status_code=HTTPStatus.BAD_REQUEST)
return JSONResponse(err.model_dump(), status_code=HTTPStatus.BAD_REQUEST)
@app.get("/health")
@@ -118,7 +118,7 @@ async def health() -> Response:
@app.get("/v1/models")
async def show_available_models():
models = await openai_serving_chat.show_available_models()
return JSONResponse(content=models.dict())
return JSONResponse(content=models.model_dump())
@app.post("/v1/chat/completions")
@@ -126,22 +126,28 @@ async def create_chat_completion(request: ChatCompletionRequest,
raw_request: Request):
generator = await openai_serving_chat.create_chat_completion(
request, raw_request)
if request.stream and not isinstance(generator, ErrorResponse):
if isinstance(generator, ErrorResponse):
return JSONResponse(content=generator.model_dump(),
status_code=generator.code)
if request.stream:
return StreamingResponse(content=generator,
media_type="text/event-stream")
else:
return JSONResponse(content=generator.dict())
return JSONResponse(content=generator.model_dump())
@app.post("/v1/completions")
async def create_completion(request: CompletionRequest, raw_request: Request):
generator = await openai_serving_completion.create_completion(
request, raw_request)
if request.stream and not isinstance(generator, ErrorResponse):
if isinstance(generator, ErrorResponse):
return JSONResponse(content=generator.model_dump(),
status_code=generator.code)
if request.stream:
return StreamingResponse(content=generator,
media_type="text/event-stream")
else:
return JSONResponse(content=generator.dict())
return JSONResponse(content=generator.model_dump())
if __name__ == "__main__":