Skip to content

feat(openai): expose max_output_tokens on Responses API LLM #5449

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

Open
piyush-gambhir wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −0
Open

feat(openai): expose max_output_tokens on Responses API LLM #5449

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/responses/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ def __init__(
tool_choice: NotGivenOr[ToolChoice] = NOT_GIVEN,
timeout: httpx.Timeout | None = None,
reasoning: NotGivenOr[Reasoning] = NOT_GIVEN,
max_output_tokens: NotGivenOr[int] = NOT_GIVEN,
) -> None:
"""
This automatically infers the following arguments from their corresponding environment variables if they are not provided:
Expand Down Expand Up @@ -68,6 +69,7 @@ def __init__(
parallel_tool_calls=parallel_tool_calls,
tool_choice=tool_choice,
reasoning=reasoning,
max_output_tokens=max_output_tokens,
)
self._azure_client = azure_client

Expand Down
6 changes: 6 additions & 0 deletions livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/responses/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,6 +144,7 @@ class _LLMOptions:
reasoning: NotGivenOr[Reasoning]
metadata: NotGivenOr[dict[str, str]]
service_tier: NotGivenOr[ServiceTier]
max_output_tokens: NotGivenOr[int]
use_websocket: bool


Expand All @@ -164,6 +165,7 @@ def __init__(
store: NotGivenOr[bool] = NOT_GIVEN,
metadata: NotGivenOr[dict[str, str]] = NOT_GIVEN,
service_tier: NotGivenOr[ServiceTier] = NOT_GIVEN,
max_output_tokens: NotGivenOr[int] = NOT_GIVEN,
timeout: httpx.Timeout | None = None,
) -> None:
"""
Expand Down Expand Up @@ -194,6 +196,7 @@ def __init__(
metadata=metadata,
reasoning=reasoning,
service_tier=service_tier,
max_output_tokens=max_output_tokens,
use_websocket=use_websocket,
)
self._client = client
Expand Down Expand Up @@ -290,6 +293,9 @@ def chat(
if is_given(self._opts.service_tier):
extra["service_tier"] = self._opts.service_tier

if is_given(self._opts.max_output_tokens):
extra["max_output_tokens"] = self._opts.max_output_tokens

parallel_tool_calls = (
parallel_tool_calls if is_given(parallel_tool_calls) else self._opts.parallel_tool_calls
)
Expand Down
2 changes: 2 additions & 0 deletions livekit-plugins/livekit-plugins-xai/livekit/plugins/xai/responses/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ def __init__(
tool_choice: NotGivenOr[ToolChoice] = NOT_GIVEN,
timeout: httpx.Timeout | None = None,
reasoning: NotGivenOr[Reasoning] = NOT_GIVEN,
max_output_tokens: NotGivenOr[int] = NOT_GIVEN,
) -> None:
api_key = api_key or os.environ.get("XAI_API_KEY")
if api_key is None:
Expand All @@ -44,4 +45,5 @@ def __init__(
tool_choice=tool_choice,
reasoning=reasoning,
timeout=timeout,
max_output_tokens=max_output_tokens,
)