Skip to content

Add llm completions custom timeout #156

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
merged 2 commits into from
Aug 30, 2023
Merged

Add llm completions custom timeout #156

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b0e4a5
add llm completions timeout
seanshi-scale Aug 30, 2023
51787ff
add configurable timeout
seanshi-scale Aug 30, 2023
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions launch/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,6 +160,7 @@
from launch.request_validation import validate_task_request

DEFAULT_NETWORK_TIMEOUT_SEC = 120
DEFAULT_LLM_COMPLETIONS_TIMEOUT = 300

logger = logging.getLogger(__name__)
logging.basicConfig()
Expand Down Expand Up @@ -2911,6 +2912,7 @@ def completions_sync(
temperature: float,
stop_sequences: Optional[List[str]] = None,
return_token_log_probs: Optional[bool] = False,
timeout: float = DEFAULT_LLM_COMPLETIONS_TIMEOUT,
) -> CompletionSyncV1Response:
"""
Run prompt completion on a sync LLM endpoint. Will fail if the endpoint is not sync.
Expand Down Expand Up @@ -2945,6 +2947,7 @@ def completions_sync(
body=request,
query_params=query_params,
skip_deserialization=True,
timeout=timeout,
)
resp = json.loads(response.response.data)
return resp
Expand All @@ -2957,6 +2960,7 @@ def completions_stream(
temperature: float,
stop_sequences: Optional[List[str]] = None,
return_token_log_probs: Optional[bool] = False,
timeout: float = DEFAULT_LLM_COMPLETIONS_TIMEOUT,
) -> Iterable[CompletionStreamV1Response]:
"""
Run prompt completion on an LLM endpoint in streaming fashion. Will fail if endpoint does not support streaming.
Expand Down Expand Up @@ -2989,6 +2993,7 @@ def completions_stream(
json=request,
auth=(self.configuration.username, self.configuration.password),
stream=True,
timeout=timeout,
)
sse_client = sseclient.SSEClient(response)
events = sse_client.events()
Expand Down