Skip to content

[Serving] Add customized generation configs #442

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
wongzhenhao merged 1 commit into from
Jan 14, 2026
Merged

[Serving] Add customized generation configs #442

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
20 changes: 13 additions & 7 deletions dataflow/serving/api_llm_serving_request.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,14 +26,17 @@ def __init__(self,
max_workers: int = 10,
max_retries: int = 5,
timeout: tuple[float, float] = (10.0, 120.0), # connect timeout, read timeout
**configs
):
# Get API key from environment variable or config
self.api_url = api_url
self.model_name = model_name
self.temperature = temperature
# self.temperature = temperature
self.max_workers = max_workers
self.max_retries = max_retries
self.timeout = timeout
self.configs = configs
self.configs.update({"temperature": temperature})

self.logger = get_logger()

Expand Down Expand Up @@ -125,17 +128,17 @@ def _api_chat_with_id(
start = time.time()
try:
if is_embedding:
payload = json.dumps({
payload = {
"model": model,
"input": payload
})
}
elif json_schema is None:
payload = json.dumps({
payload = {
"model": model,
"messages": payload
})
}
else:
payload = json.dumps({
payload = {
"model": model,
"messages": payload,
"response_format": {
Expand All @@ -146,7 +149,10 @@ def _api_chat_with_id(
"schema": json_schema
}
}
})
}

payload.update(self.configs)
payload = json.dumps(payload)
# Make a POST request to the API
response = self.session.post(self.api_url, headers=self.headers, data=payload, timeout=self.timeout)
cost = time.time() - start
Expand Down