xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 23:45:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Enable request body OpenAPI spec for OpenAI endpoints (#865)

Browse Source
This commit is contained in:
lplcor 2023-08-29 21:54:08 -07:00 committed by GitHub
parent 75471386de
commit becd7a56f1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/entrypoints/openai/api_server.py
View File

@ -178,7 +178,8 @@ def create_logprobs(token_ids: List[int],
@app.post("/v1/chat/completions") @app.post("/v1/chat/completions")
async def create_chat_completion(raw_request: Request): async def create_chat_completion(request: ChatCompletionRequest,
raw_request: Request):
"""Completion API similar to OpenAI's API. """Completion API similar to OpenAI's API.
See https://platform.openai.com/docs/api-reference/chat/create See https://platform.openai.com/docs/api-reference/chat/create
@ -188,7 +189,6 @@ async def create_chat_completion(raw_request: Request):
- function_call (Users should implement this by themselves) - function_call (Users should implement this by themselves)
- logit_bias (to be supported by vLLM engine) - logit_bias (to be supported by vLLM engine)
""" """
request = ChatCompletionRequest(**await raw_request.json())
logger.info(f"Received chat completion request: {request}") logger.info(f"Received chat completion request: {request}")
error_check_ret = await check_model(request) error_check_ret = await check_model(request)
@ -348,7 +348,7 @@ async def create_chat_completion(raw_request: Request):
@app.post("/v1/completions") @app.post("/v1/completions")
async def create_completion(raw_request: Request): async def create_completion(request: CompletionRequest, raw_request: Request):
"""Completion API similar to OpenAI's API. """Completion API similar to OpenAI's API.
See https://platform.openai.com/docs/api-reference/completions/create See https://platform.openai.com/docs/api-reference/completions/create
@ -361,7 +361,6 @@ async def create_completion(raw_request: Request):
suffix) suffix)
- logit_bias (to be supported by vLLM engine) - logit_bias (to be supported by vLLM engine)
""" """
request = CompletionRequest(**await raw_request.json())
logger.info(f"Received completion request: {request}") logger.info(f"Received completion request: {request}")
error_check_ret = await check_model(request) error_check_ret = await check_model(request)