Skip to content
Closed
Changes from all commits
Commits
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
8 changes: 7 additions & 1 deletion predictionguard/src/chat.py
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,7 @@ def create(
max_tokens: Optional[int] = None,
parallel_tool_calls: Optional[bool] = None,
presence_penalty: Optional[float] = None,
reasoning_effort: Optional[str] = None,
stop: Optional[
Union[
str, List[str]
Expand Down Expand Up @@ -126,9 +127,10 @@ def create(
:param max_completion_tokens: The maximum amount of tokens the model should return.
:param parallel_tool_calls: The parallel tool calls to use.
:param presence_penalty: The presence penalty to use.
:param reasoning_effort: The reasoning effort to use.
:param stop: The completion stopping criteria.
:param stream: Option to stream the API response
:param temperature: The consistency of the model responses to the same prompt. The higher the more consistent.
:param temperature: The consistency of the model responses to the same prompt. The higher, the more consistent.
:param tool_choice: The tool choice to use.
:param tools: Options to pass to the tool choice.
:param top_p: The sampling for the model to use.
Expand Down Expand Up @@ -157,6 +159,7 @@ def create(
max_completion_tokens,
parallel_tool_calls,
presence_penalty,
reasoning_effort,
stop,
stream,
temperature,
Expand All @@ -182,6 +185,7 @@ def _generate_chat(
max_completion_tokens,
parallel_tool_calls,
presence_penalty,
reasoning_effort,
stop,
stream,
temperature,
Expand Down Expand Up @@ -321,6 +325,7 @@ def stream_generator(url, headers, payload, stream, timeout):
"max_completion_tokens": max_completion_tokens,
"parallel_tool_calls": parallel_tool_calls,
"presence_penalty": presence_penalty,
"reasoning_effort": reasoning_effort,
"stop": stop,
"stream": stream,
"temperature": temperature,
Expand All @@ -337,6 +342,7 @@ def stream_generator(url, headers, payload, stream, timeout):
"max_completion_tokens": max_completion_tokens,
"parallel_tool_calls": parallel_tool_calls,
"presence_penalty": presence_penalty,
"reasoning_effort": reasoning_effort,
"stop": stop,
"stream": stream,
"temperature": temperature,
Expand Down
Loading