Skip to content

bugfix of openai_api_server for fastchat.serve.vllm_worker #2398

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

Merged
merrymercy merged 1 commit into from
Sep 11, 2023
Merged

bugfix of openai_api_server for fastchat.serve.vllm_worker #2398

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
54 changes: 40 additions & 14 deletions fastchat/serve/openai_api_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,15 +399,28 @@ async def create_chat_completion(request: ChatCompletionRequest):
for i, content in enumerate(all_tasks):
if content["error_code"] != 0:
return create_error_response(content["error_code"], content["text"])
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=content["text"]),
finish_reason=content.get("finish_reason", "stop"),
if isinstance(content["text"], list):
for t in content["text"]:
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=t),
finish_reason=content.get("finish_reason", "stop"),
)
)
else:
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=content["text"]),
finish_reason=content.get("finish_reason", "stop"),
)
Comment on lines +402 to +417
Copy link
Member

@infwinston infwinston Sep 11, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why don't we do this to reduce LoC and repeated codes

if isinstance(content["text"], str):
    contents = [context["text"]]
for t in contents:
    choices.append(
        ChatCompletionResponseChoice(
            index=i,
            message=ChatMessage(role="assistant", content=t),
            finish_reason=content.get("finish_reason", "stop"),
        )
    )

)
)
if "usage" in content:
task_usage = UsageInfo.parse_obj(content["usage"])
if isinstance(content["usage"], list):
task_usage = UsageInfo.parse_obj(content["usage"][0])
else:
task_usage = UsageInfo.parse_obj(content["usage"])
for usage_key, usage_value in task_usage.dict().items():
setattr(usage, usage_key, getattr(usage, usage_key) + usage_value)

Expand Down Expand Up @@ -775,14 +788,27 @@ async def create_chat_completion(request: APIChatCompletionRequest):
for i, content in enumerate(all_tasks):
if content["error_code"] != 0:
return create_error_response(content["error_code"], content["text"])
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=content["text"]),
finish_reason=content.get("finish_reason", "stop"),
if isinstance(content["text"], list):
for t in content["text"]:
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=t),
finish_reason=content.get("finish_reason", "stop"),
)
)
else:
choices.append(
ChatCompletionResponseChoice(
index=i,
message=ChatMessage(role="assistant", content=content["text"]),
finish_reason=content.get("finish_reason", "stop"),
)
)
)
task_usage = UsageInfo.parse_obj(content["usage"])
if isinstance(content["usage"], list):
task_usage = UsageInfo.parse_obj(content["usage"][0])
else:
task_usage = UsageInfo.parse_obj(content["usage"])
for usage_key, usage_value in task_usage.dict().items():
setattr(usage, usage_key, getattr(usage, usage_key) + usage_value)

Expand Down