Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix stream=false doesn't work issue #124

Merged
merged 1 commit into from
May 31, 2024
Merged

Fix stream=false doesn't work issue #124

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions comps/cores/mega/gateway.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,7 @@ def __init__(self, megaservice, host="0.0.0.0", port=8888):

async def handle_request(self, request: Request):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.parse_obj(data)
prompt = self._handle_message(chat_request.messages)
parameters = LLMParams(
Expand All @@ -126,7 +127,7 @@ async def handle_request(self, request: Request):
top_p=chat_request.top_p if chat_request.top_p else 0.95,
temperature=chat_request.temperature if chat_request.temperature else 0.01,
repetition_penalty=chat_request.presence_penalty if chat_request.presence_penalty else 1.03,
streaming=chat_request.stream if chat_request.stream else True,
streaming=stream_opt,
)
await self.megaservice.schedule(initial_inputs={"text": prompt}, llm_parameters=parameters)
for node, response in self.megaservice.result_dict.items():
Expand Down Expand Up @@ -159,6 +160,7 @@ def __init__(self, megaservice, host="0.0.0.0", port=8888):

async def handle_request(self, request: Request):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.parse_obj(data)
prompt = self._handle_message(chat_request.messages)
parameters = LLMParams(
Expand All @@ -167,7 +169,7 @@ async def handle_request(self, request: Request):
top_p=chat_request.top_p if chat_request.top_p else 0.95,
temperature=chat_request.temperature if chat_request.temperature else 0.01,
repetition_penalty=chat_request.presence_penalty if chat_request.presence_penalty else 1.03,
streaming=chat_request.stream if chat_request.stream else True,
streaming=stream_opt,
)
await self.megaservice.schedule(initial_inputs={"query": prompt}, llm_parameters=parameters)
for node, response in self.megaservice.result_dict.items():
Expand Down Expand Up @@ -247,6 +249,7 @@ def __init__(self, megaservice, host="0.0.0.0", port=8888):

async def handle_request(self, request: Request):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.parse_obj(data)
prompt = self._handle_message(chat_request.messages)
parameters = LLMParams(
Expand All @@ -255,7 +258,7 @@ async def handle_request(self, request: Request):
top_p=chat_request.top_p if chat_request.top_p else 0.95,
temperature=chat_request.temperature if chat_request.temperature else 0.01,
repetition_penalty=chat_request.presence_penalty if chat_request.presence_penalty else 1.03,
streaming=chat_request.stream if chat_request.stream else True,
streaming=stream_opt,
)
await self.megaservice.schedule(initial_inputs={"query": prompt}, llm_parameters=parameters)
for node, response in self.megaservice.result_dict.items():
Expand Down
Loading